mirror of
https://github.com/windmill-labs/windmill.git
synced 2026-08-18 16:02:10 +00:00
v1.792.0
63 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 hugocasa
|
53eb94659b |
feat(telemetry): extend feature-usage tracking beyond AI features (#10681)
* feat(telemetry): extend feature-usage tracking to long-tail features Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs: describe telemetry as product feature usage rather than AI usage Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * refactor(telemetry): trim disclosure copy and drop unused pick origin Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(telemetry): count trigger fires per run and key hub picks from hub data Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(telemetry): slugify hub keys and order both writers' upserts Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(telemetry): key native trigger adoption by service so it matches fires Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref for native trigger adoption fix Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * refactor(telemetry): move feature-usage collection into the ee crate * docs: point feature-telemetry at the moved registry and rust writer * docs: correct the trigger-fire gate comment to match measured step counts * docs: put the private-build caveat on the verification step * chore: update ee-repo-ref to f079db9e7962a413b349c4ff8036080894f30771 This commit updates the EE repository reference after PR #725 was merged in windmill-ee-private. Previous ee-repo-ref: 055adb80416f9339c9a28ae7fbaeadad30d74959 New ee-repo-ref: f079db9e7962a413b349c4ff8036080894f30771 Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: Ruben Fiszel <ruben@windmill.dev> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
 Ruben Fiszel
|
0a40b3806f | fix(agents): let the scratch-dir hooks own their permission prompt (#10702) | ||
|
hugocasa
|
c3b2275864 |
docs(agents): rework agent context, fix dev-env docs, vendor skills (#10667)
* docs(agents): scope agent guidance to where it loads AGENTS.md loads in every session. Three of its sections only ever applied to one directory, and docs/autonomous-mode.md was unreferenced by anything in the repo, so none of its content was in effect. - Move "Verifying Backend Changes" to backend/CLAUDE.md, "Verifying Frontend Changes" and "Banned Patterns" to frontend/CLAUDE.md. They now load when working under those directories, which is when they apply. - Update the two cross-references that pointed at the moved sections (pr and svelte-frontend skills). - Delete docs/autonomous-mode.md. Its "don't stop early" half is already in .webmux.yaml's oneshot system prompt, which actually loads; its trigger was bypassPermissions, which does not imply an absent user; and it restated AGENTS.md and the pr skill with copies that had drifted (hardcoded ports, relative screenshot paths). Salvaged the UI traps it uniquely documented into frontend/CLAUDE.md and dropped the three stale profile references. AGENTS.md drops ~3.6k characters with no guidance lost. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(agents): guidance for building a feature — reuse, telemetry, live verification Three recurring gaps, all cases where a pointer existed but nothing triggered on it. Component reuse. The svelte-frontend skill documented three components with props, which reads as the whole catalog; the barrel exports 23 and common/ has 34 subdirectories against those 23. So "never use raw HTML elements" was an instruction agents could not follow. Added a mandatory discovery step: read the barrel, grep the tree, and treat the documented three as examples. Brand guidelines. frontend/brand-guidelines.md is 34k characters referenced by bare path, which nothing opens speculatively. Added a table mapping what you are building to the section that governs it, entered with grep rather than a full read. Product telemetry. feature_usage has 14 registered actions across three features, and an unregistered (feature, kind) pair is dropped by valid_feature_usage_event with a bare continue — no error, still a 204 — so frontend-only instrumentation silently records nothing. New docs/feature-telemetry.md carries the criteria for when to instrument, the four-step recipe including the allowlist and the InstanceSettings disclosure, and the privacy rules. Raised in the plan for user-facing work, not as a separate question, and not at all for bugfixes or refactors. Also: validation now ends at exercising the change on the running instance, with standing permission to spin up whatever that takes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(dev): correct the worktree dev-environment guidance Several things agents were told to do did not match what the machine does. - Env discovery pointed at .env / .env.local / backend/.env. In a webmux worktree the real values are in $(git rev-parse --git-dir)/webmux/runtime.env (BACKEND_PORT, FRONTEND_PORT, DATABASE_URL, CARGO_FEATURES, WM_DB_NAME), sourced by every pane and undocumented. Reading it is also not blocked by the Read(**/.env) deny rules, which the old instruction walked straight into. - The database name rule said branch-with-underscores. worktree-common.sh uses the worktree directory basename, and Postgres truncates at 63 characters, so branch hugo/win-2340-… resolves to windmill_win_2340_…_and_eval with no hugo_ prefix and the tail chopped. A wrong DATABASE_URL guts the sqlx cache. - The restart procedure said "tmux pane 1" and sent keys to an undefined <pane1>. Pane 1 is the backend under the full profile and the frontend under frontendOnly. Replaced with finding the pane by pane_current_command, recovering the live feature set from the running process (CARGO_FEATURES in runtime.env only records what the pane started with), and restarting in place. - Added recovery for an orphaned backend holding the port: it reparents to systemd when its shell dies, so it survives anything that looks like cleanup. Three checks before killing a single pid, because pkill -f windmill takes out every sibling worktree. - Agents spawned their own servers because AGENTS.md opened by telling them to. Now it checks for the existing panes first; the spawn commands are scoped to a plain checkout. - New EE worktrees branched from the EE repo's local main, which nothing fast-forwards, so they started behind the commit pinned in backend/ee-repo-ref.txt — the one CI builds against. They now base on the pin, falling back to main only when it is unreadable. - Enabled webmux autoPull so local main stays current; new worktrees are branched from it. Documented what WM_CLONE_DB does, including that it terminates every connection to the base windmill database. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat(skills): vendor grilling/architecture skills; tighten PR ready and review rounds Vendors five skills from https://github.com/mattpocock/skills (MIT, pinned at 84fdeffd12f2ee307994d1eb6feb48173b6e0502). They are one dependency closure: grill-me is a stub that runs grilling, and improve-codebase-architecture draws its vocabulary from codebase-design and its CONTEXT.md upkeep from domain-modeling. .agents/skills/UPSTREAM.md records the license, the pin, and the four local deltas so a refresh stays a diff: - flattened the upstream engineering/ and productivity/ split - rewrote bundled-file links to repo-root paths, since relative links break when read through the .claude/skills symlink - dropped the upstream agents/openai.yaml packaging metadata - removed every ADR path. This repo has not adopted ADRs, and a skill that offers to create them is how the practice arrives by side effect rather than by decision. PR workflow changes, all in the pr skill: - A round that never starts is usually a conflict with main, not a CI outage. Resolve by merging, not rebasing — a rebase rewrites the head SHA that round verdicts and the clean-round marker are keyed to. If the merge advances backend/ee-repo-ref.txt, the EE worktree has to follow or cargo check --features private compiles a tree neither the author nor CI intends. - A clean round no longer means an automatic flip to ready. Wide blast radius (*_ee.rs, migrations, OpenAPI or the generated client, auth paths, shared worker infrastructure, a new public surface) asks first; self-contained changes flip. Unattended, the judgement holds and the action degrades: flip the small ones, leave the rest at a clean draft with the reason in the PR body. - Rounds that never converge are usually structural. After three without convergence, stop, name the module the findings cluster around, and suggest improve-codebase-architecture rather than burning more CI. AGENTS.local.md (gitignored, with CLAUDE.local.md importing it) holds the ready/ask calibration, recorded as dated observations rather than a rule. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(dev): state that each worktree gets its own fresh database The per-worktree section warned which DATABASE_URL to use but never said where the database comes from: the post-create hook creates and migrates a new one per worktree, so it starts with none of the main instance's workspaces, scripts or flows. WM_CLONE_DB was documented only as a comment in .webmux.yaml, which reads as how things work rather than as a per-project opt-in. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(sqlx): script the cache backup/restore instead of documenting it The update-sqlx skill spelled out a cp/comm/rm dance around `cargo sqlx prepare`, which empties backend/.sqlx before regenerating — a failed run leaves the cache gutted (observed: 2350 -> 142 entries), and a --all-targets run in a CE checkout fails that way every time. Three problems with documenting it: - The backup path was the literal /tmp/sqlx_backup, shared by every worktree. Two concurrent runs overwrite each other's backup, which is the only thing standing between a failed prepare and a gutted cache. - The restore was a copy-pasted `rm -rf .sqlx && cp -r ... && cp ...` chain. - Skipping the backup is what turns a routine failure into a lost cache, and a convention is easier to skip than a command. sqlx-cache.sh has backup / newq / restore, keeps state in a per-worktree directory, and leaves the judgement call where it belongs: `newq` prints each added entry's query field for review, and only `restore` writes them in. Also adds the general rule that scratch files belong outside the checkout — anything written into the tree has to be deleted again, and rm prompts each time. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(agents): state why a routine cleanup prompts, and where scratch goes The guard hook already auto-allows a plain rm whose operands are under /tmp or inside a git checkout in $HOME, so deleting a temp dir or a stale .sqlx entry costs nothing. What prompts is the command shape: the hook's tokenizer defers on &&, ;, redirects, quotes and $VAR, so a chained cleanup falls through to the Bash(rm:*) ask rule. That was recorded only inside a paragraph about screenshot file paths in frontend/CLAUDE.md, where nobody looking for it would find it. Stated in Core Principles instead, alongside the rule that scratch belongs outside the tree — for the reason that actually applies, which is not committing junk rather than avoiding prompts. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(security): deny agent edits to the permission hooks and project settings .claude/hooks/guard-rm-outside-tmp.sh and guard-main-branch.sh are the enforcement points for everything the permission rules are meant to catch, and nothing stopped an agent editing them. One sed -i disables the guard for every later command, silently, and the deny list in .claude/settings.json has the same exposure. Defence in depth rather than a boundary: an agent with arbitrary bash can still delete, and this may only close the Edit-tool path if Bash writes are not covered by Edit deny rules. It costs nothing and removes the cheapest way to turn the guards off. Changing them now means editing the files by hand, which is the intent. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: address review round findings on head |
||
|
Ruben Fiszel
|
a6157ba104 |
feat: bound how much disk a single duckdb job can spill (#10645)
* feat: bound how much disk a single duckdb job can spill * fix: name the env var and correct duckdb's unreachable spill-cap advice * fix: do not blame an unset env var for duckdb's default spill cap * style: keep the duckdb spill-cap invariant comments within four lines * docs: size the duckdb spill cap against the disk cloud pods actually use |
||
|
Ruben Fiszel
|
3394546657 |
feat(npm-proxy): keep package files on disk and in the object store (#10638)
* docs: design for where the npm proxy keeps cached registry content * feat(npm-proxy): keep package files on disk and in the object store * fix(npm-proxy): degrade when the cache is unwritable, stream and bound it * fix(npm-proxy): keep the happy path off the heap and isolate pull scratch * fix(npm-proxy): bound the upload, verify pulled trees, keep oversized manifests * fix(npm-proxy): protect live scratch, bound uploads by parts, refuse traversals * fix: let the blocking unpack own the scratch it writes into * fix: replace a cache directory that is not a package instead of deferring to it * fix: evict by moving a package off the live path, not by deleting it in place * fix: leave a package the sweep cannot move rather than deleting it in place * fix: take one registry snapshot through a cache miss * fix: stamp a pulled package as used so the sweep does not evict it first |
||
|
Ruben Fiszel
|
18ae0bdfbf |
feat: keep duckdb spilling behind the local-filesystem fence (#10607)
* fix: explain duckdb failures caused by job isolation Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: apply the isolation policy to the schema-sync pre-pass Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: bump ee ref for the out-of-memory hint wording Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: bump the bundled DuckDB engine to 1.5.5 The 1.5.5 duckdb crate no longer hands back a 96-bit `rust_decimal`, so a DECIMAL wider than that renders instead of panicking inside an `extern "C"` frame — which, being unable to unwind, aborted the whole worker process and left the job running as a zombie. `SELECT '1234567890123456789012345678.9012345678'::DECIMAL(38, 10)` was enough. Adapting to the crate's API: `Value` is now `#[non_exhaustive]` and gained `UHugeInt` and `Geometry`, and `rust_decimal` became an optional feature that the `decimal`/`numeric` argument path still needs. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: address review findings on the duckdb bump Run the FFI crate's own tests in CI: it is excluded from the workspace, so the `cargo test --all` in backend-test never reached them and the new guard against the worker-aborting DECIMAL would not have run. build_dev.sh now honors a caller-pinned CARGO_TARGET_DIR so the test build reuses that compile instead of building the bundled engine a second time. Also pin UHUGEINT rendering, and correct the rust_decimal rationale — `Decimal::new` is public without the feature, so the reason is that the feature reproduces the exact binding the crate used to derive, not that nothing else can. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: address review nits on the duckdb bump Name the unsupported DuckDB type rather than dumping the value, which may be arbitrarily large or hold data that does not belong in an error message, and say which column it came from. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: pin the ee ref to the narrowed duckdb extension allowlist Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: keep duckdb spilling behind the local-filesystem fence * chore: repin the duckdb fork after adding the reset-test exclusion * docs: stop claiming the duckdb patch has been filed upstream * docs: point the backend duckdb bullet at the fork's rationale * fix: place lock_temp_directory so no existing struct member moves * fix: skip the extension-load guard when the repo is unreachable * refactor: trim the fork comments and fail the extension guard in CI * chore: repin the duckdb fork onto upstream duckdb-rs main * fix: keep the engine patch applying on a CRLF checkout * docs: link the upstream issue tracking the underlying problem * chore: repin the duckdb fork onto the patch as filed upstream Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref to 88568d11162ffa11723e7955e613224bab4f0568 This commit updates the EE repository reference after PR #720 was merged in windmill-ee-private. Previous ee-repo-ref: 22f075c1164d9dd5a3ba92d682905aabd071d273 New ee-repo-ref: 88568d11162ffa11723e7955e613224bab4f0568 Automated by sync-ee-ref workflow. * chore: repin the duckdb fork onto the cmake/fmt build fix Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test: pin the immutability half of lock_temp_directory The spill test proves the exemption works; nothing proved the lock that makes it sound. A rebase could drop the refusals and leave every other tripwire green. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
hugocasa
|
c09de594b6 |
feat: version resource values with history, diff and restore (#10596)
* feat: version resource values with history, diff and restore Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: record resource versions in a trigger so direct writes are covered Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: show the selected version's value and tighten history write access Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * perf: gate resource version recording in trigger WHEN clauses Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: clear a resource's past versions, and address review nits Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: restore the displayed version and keep author attribution on pooled writes Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: scope history to the selected workspace and gate clearing on ownership Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: gate restore on write access and clearing on the signed-in workspace Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * refactor(frontend): share the version-history row between script and resource drawers Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * perf: trim resource version history in the monitor sweep, not on write Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(frontend): match the script versions drawer shell for resource history Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * perf(frontend): highlight version values instead of mounting monaco Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(frontend): match the script drawer's code preview presentation Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: rank version trim in one windowed pass instead of a correlated delete Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * refactor(frontend): treat the newest version as current by position Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * perf: gate the resource version trim to an hourly sweep Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: unnest the version row action and correct the trim cadence docs * perf: cap the history listing and use sets for reference lookup * feat: warn when a resource is written more than 60 times a minute * fix: lower the resource write advisory to 20 per minute * fix: discard stale history loads and never diff against an unread value * fix: correct the write advisory boundary and document the eviction lock * fix: read history and the live value from one snapshot * refactor: read the drawer's diff baseline from versions, not the live resource * fix: open the history drawer with no version selected * fix: disarm the clear confirmation and clear the pane when the selection moves * fix: explain the missing diff and drop a guard that can no longer fire --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
340d3cd565 |
feat(dbt): reach any dbt adapter through a dbt_profile resource, and constrain the warehouse picker (#10525)
* feat(dbt): reach any dbt adapter through a dbt_profile resource, and constrain the warehouse picker
The workspace dbt warehouse picker listed every resource in the workspace, so a
slack or github resource was an offerable answer to a field that can only be a
warehouse. Constraining it exposed that the set of resource types that actually
work is both smaller than the docs claim and too small to be useful:
- `render_profile` translates only six adapters from a Windmill resource; the
rest (clickhouse, duckdb, salesforce, mssql, oracle) refused one outright.
- `redshift` and `duckdb` name no resource type anywhere, so two of the
adapters the quickstart advertises were unreachable.
- the `databricks` resource carries `workspace_url`, while the renderer demanded
`host`, so that warehouse could never render at all.
So the picker gets a constraint and dbt gets an escape hatch wide enough to make
it honest. `dbt_profile` is a resource whose value IS a `profiles.yml` target —
`{ type, target }` — passed to dbt unchanged, so any adapter and any key it
documents works.
`DbtAdapter` is now open: it carries dbt's own `type:` spelling plus an optional
`KnownAdapter` (the eleven Windmill has facts about — a field mapping, a pip
package, the license gate). Anything else is carried by name and installed as
`dbt-<name>`, the convention every adapter on PyPI follows, so "whatever dbt
supports" no longer means "whatever this enum lists". The license gate is
unaffected: `sqlserver`/`oracle` still resolve to their `KnownAdapter` and are
still gated. The name is confined to `[a-z0-9_-]` starting alphanumeric because
it reaches a pip requirement and a venv path on the host.
Two adjacent fixes fall out: the project's own `profiles.yml` and the
descriptor's `profile.type` now accept any adapter instead of the closed list,
and a databricks resource renders its `host` from `workspace_url`.
The picker is constrained to `dbt_profile` plus the translated types, so nothing
it offers can fail for want of a mapping.
Fixes WIN-2320
* fix: drop the unused DbtAdapter::from_resource_type wrapper
Nothing calls it: a Windmill resource type maps through
KnownAdapter::from_resource_type, and the executor resolves an adapter from
the resource's own dbt spelling or by inference. CI builds with -D warnings,
so the dead wrapper failed every backend check.
* fix(dbt): make dbt_profile the block itself, and address the review findings
**A `dbt_profile`'s value IS a `profiles.yml` output block**, `type` included.
It was `{ type, output }`, which asked the user to restructure their block
before pasting it — a translation step, in the one type that exists to avoid
translation. The schema now declares no properties, so the resource form renders
a single JSON editor over the value.
That means the value's shape can no longer say what it is: a `dbt_profile` and
Windmill's bigquery resource are both objects with a `type` (the latter says
`type: service_account`). So the warehouse carries its resource's type
(`DbtWarehouseConnection.resource_type`), and detection is exact. It also makes
decision 9's "the resource type name is the authority" true at runtime for the
translated path, which until now resolved its adapter by sniffing fields.
Review findings, all three reviewers:
- **[P0] an author-chosen adapter became an unsandboxed PyPI install.** `dbt-` is
not a reserved prefix, and `provision_core_1x` installs through `run_tool`,
outside the nsjail ordinary dependency installation uses — so `dbt-<name>` from
a script author's `type` could run a PEP 517 build backend as the worker. Now
gated on a list of published adapters plus `DBT_EXTRA_ADAPTERS`, so trust stays
the admin's call. The open set survives: the engines that ship their adapters
install nothing and take any type.
- **[P1] `type: fabric` rendered as `sqlserver`.** dbt's `type:` was resolved
through the resource-type table, where `fabric` is a Windmill alias for SQL
Server — so a Fabric profile installed dbt-sqlserver, was enterprise-gated, and
failed on an ODBC driver without ever naming Fabric. dbt types now have their
own table.
- **[P1] two spellings of one adapter compared unequal.** `PartialEq` covers the
carried name, so `postgres` != `postgresql` even resolving to one adapter, and
the descriptor/resource check rejected valid configs with a message naming the
same adapter twice. The name is normalised to the adapter's dbt spelling.
- **[P2] identity keys.** `database_key` is what a Windmill resource spells it,
and only translated adapters have one; the rest read dbt's `database`.
- **[P2] duplicate `sslrootcert`** when a block carried both a PEM and a path.
Verified with three real dbt builds: a flat `dbt_profile` postgres block, the
same with `type: postgresql` under a `profile.type: postgres` descriptor (the
alias case, which failed before), and trino for the unknown-adapter path.
* docs(dbt): say that installing an adapter is gated, not just using one
The open-adapter text promised every future adapter is installed as dbt-<name>,
which ensure_adapter_installable refuses outside PUBLISHED_ADAPTERS and
DBT_EXTRA_ADAPTERS. Separates the two: rendering, licensing and identity are open
to any adapter, and only the dbt-core 1.x PyPI install is gated, because that is
the step that runs outside the sandbox.
* fix(dbt): keep a dbt_profile's own sslrootcert when Windmill writes none
The previous round skipped the block's sslrootcert unconditionally to avoid
emitting the key twice, which drops a path-only CA reference — a certificate
baked into the image or mounted on the worker, which is the block's own trust
source. Skipped now only when a root_certificate_pem is present, which is when
Windmill writes a replacement.
* fix(frontend): let a resource type declare no properties
A schema without `properties` is a JSON-edited resource type, not a broken one -
`dbt_profile` is a profiles.yml block whose keys belong to its adapter, so there
is nothing for Windmill to declare. Both editors assumed properties exist:
- ResourceEditor threw on Object.keys(undefined) while deriving the field order,
which left the drawer on its loading skeleton forever, so the resource could
not be viewed or edited at all.
- ApiConnectForm caught the same throw and reported the type as missing from the
workspace, offering to sync a type it already had.
Both now fall back to the raw JSON editor, which is what usesRawEditor already
intended for a schema with no properties.
* chore: cut the new comments to AGENTS.md's four-line cap
Each still states its constraint once; the long-form rationale belongs in
docs/dbt-runtime.md and the PR, not beside the code.
* fix(dbt): keep a dbt_profile's empty and nested collections intact
A block with no children reads back as null, so `extensions: []` reached the
adapter as a missing value rather than the empty list dbt was handed, and a
nested array went through the scalar path and arrived as a quoted JSON string.
Both are keys dbt passes to the adapter as it finds them, so the type has to
survive: empty collections are emitted inline, and the value half of an entry
recurses instead of bottoming out at a scalar.
The test parses the rendered YAML back rather than string-matching it, since
what matters is what a YAML reader sees.
Also cuts DbtWarehouseConnection.resource_type's comment to the four-line cap.
|
||
|
Ruben Fiszel
|
9d820f3517 |
chore: re-land vite 8.2.0 with the chunk cycle that broke it (#10472)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
d5095515ed |
fix: return result.json and stdout results from sandboxed containers (#10460)
* fix: return result.json and stdout results from sandboxed containers Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: capture unmasked stdout-only last line, validate container result.json Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: reject image WorkingDir that escapes the container root Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: verify the whole result mount destination against the extracted rootfs Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: name the right skip reason and gate the symlink test to unix Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
baefa1345b |
feat: give dbt its own editor with an explicitly refreshed model graph (#10448)
* feat: give dbt its own editor with an explicitly refreshed model graph Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: bump ee ref for the agent-worker dbt editor graph Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: scope editor graph retention by principal, carry parse context, honor nlang Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: bump ee ref Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: keep the dbt editor's model graph and log panel mounted across tabs Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: keep the dbt_edge to dbt_node joins on an index-usable equality Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: poll a parse until the job ends, resolve the project key, correct the docs Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: surface a slow parse's job, bound poll failures, drop banned bindable defaults Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: hide the dbt Generated UI content, not only its tab Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: honor disabled Triggers in the dbt tab fallback, record permissioned_as Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: one dbt pane with the run drawn on the models, and a full-height script graph Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: move the dbt build arguments behind the Build button Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: trim the dbt editor toolbar and stop the graph asserting a cause it lacks Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: mark dbt as alpha in the language picker and announce it once Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: trim the dbt alpha notice Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * feat: give a selected dbt model the whole detail section, with a close that deselects Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: close the dbt detail panel by clicking away, and make its close obvious Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: cache the agent-worker dbt query, which needs the private feature to compile Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: never fall back to a settings tab the embedder disabled Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: preview dbt rows from the same project the graph was parsed from * feat: hide the script-kind selector for dbt projects * fix: pin a dbt row preview to the project its graph was parsed from * fix: pin a dbt row preview to the arguments its graph was parsed under * fix: keep dbt preview placeholders live while its vars stay pinned * fix: report a warehouse-less dbt parse's counts and flag stale preview args * fix: tell the pinned-vars case apart from a stale placeholder * chore: update ee-repo-ref to 59044635769f18f8ff5073236cfc7b5f41e917cc This commit updates the EE repository reference after PR #707 was merged in windmill-ee-private. Previous ee-repo-ref: 7e424384cdd4cef8653b55b04f17ad3f801bc50c New ee-repo-ref: 59044635769f18f8ff5073236cfc7b5f41e917cc Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
Ruben Fiszel
|
8d9c81a4da |
order script hard-delete and dbt graph publication locks consistently (#10446)
* fix: order script hard-delete and dbt graph publication locks consistently Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: clear dbt retry state after the script delete, not before Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
032300e28e |
feat: run dbt projects as a first-class Windmill runtime (#10326)
* fix: mount only the engine in the dbt jail, reject shadowed and malformed args
Review round 42.
The jail mounted the whole dbt cache directory, whose siblings of the
engine are `repos/` and `packages/` — other workspaces' private checkouts
and package trees, kept apart by cache key rather than by permissions. A
jailed project could read them. It now mounts the engine's own directory,
which the provisioner names; verified from inside the jail that `repos/`,
`packages/` and `state/` are invisible while the engine stays usable.
A `{{ placeholder }}` may no longer take the name of a run argument this
runtime defines. It was silently dropped from the signature, so a
descriptor like `value: "{{ select }}"` deployed and then could not be
run at all: the built-in `select` is an array and the interpolation needs
a scalar. Refused at parse, so the deploy says so.
A `vars` override that is not an object is refused rather than ignored.
Argument-schema validation is opt-in, so a string or an array silently
ran the descriptor's own vars — against a different schema or alias than
the caller asked for. `select` and `exclude` already refused theirs.
* feat(dbt): the project is the script's module bundle, not a git checkout
A dbt script now carries its whole dbt project as its module bundle. The
descriptor is the script content; `<script>__dbt/` holds the project verbatim,
so importing an existing project is `cp -r` plus `wmill sync push`, and the
worker materialises the bundle into the job directory instead of cloning.
Backend
- `prepare_project` writes the script's modules and requires `dbt_project.yml`
at the bundle root. `checkout`, the git-ssh command, the clone cache and the
repository resource are gone, along with `repo`, `project`, `ref` and
`git_ssh_identity` on the descriptor.
- Run identity and the package cache key take a `project_digest` (sorted SHA256
over the bundle) where the commit used to sit, so an edited project cannot
resume a previous run's `run_results.json` or reuse its `dbt_packages`.
- The per-run graph re-ingest is now gated on `vars` placeholders and `$var:`
env alone.
- `capture_dependency_job` takes the script's modules so a dependency job, which
has no generic module-writing step, materialises them itself.
- `dbt deps` caching strips the git remote from every package it cached, not
just the tree root: `packages.yml` can render a token into a `git:` URL.
- `git_clone.rs` is dropped and `ansible_executor.rs` returns to its own copy of
the clone helpers.
CLI
- `wmill sync pull` keeps a dbt script's lock beside its folder rather than
inside it, so the folder holds nothing but the project.
- Directories dbt generates (`target-path`, `packages-install-path`,
`clean-targets` and the usual defaults, read from `dbt_project.yml`) are
excluded from the bundle, from the sync diff and from staleness hashing.
- A module-only edit now pushes its parent dbt script and is reported as a
changed module rather than passing unnoticed.
* fix: keep a script's modules in the worker's file-system cache
The first fetch of a script version reads the database and carries its
modules; every later fetch imports from the worker's cache directory, whose
`RawScript::import` hard-coded `modules: None` and whose `export` never wrote
them. A worker restart therefore started running the script without its own
files, silently — for a dbt script, without its project, which fails with
"carries no project"; for any other script with a module bundle, with the
imports missing.
`modules.json` is now written on every export and required on import, so an
entry written by an older version fails to import and is refetched rather than
serving a stripped script for as long as the directory lives.
Also derives a dbt run's `project_digest` from the bundle the run actually
carries: `handle_dbt_job` was passing `None`, which collapsed every project in
a workspace onto one digest and let `dbt retry` resume a different project's
`run_results.json`.
* fix(dbt): give every phase the script's environment, bound the cache copies
`dbt deps` ran without the script's environment variables on an unsandboxed
worker, so a `packages.yml` resolving a private package URL through
`env_var()` could not see them while the package cache key was still built on
their digest. `with_invocation_env`, applied at three of the four call sites,
is folded into `dbt_command` so no phase can be added without it, and
`DBT_TARGET_PATH` is set after both environments rather than before.
The package cache copies ran through a bare `Command::output()`: the tree is
the project's, so a cancelled or timed-out job held its worker slot until `cp`
finished. Both the restore and the publish now run under the job poller like
every other phase.
* fix(dbt): only offer commands whose writes match the graph, honour packages-install-path
`dbt_command: run` is dropped from the allowed overrides. Asset dispatch fires a
script's deploy-time writes on any successful job, and `dbt run` covers models
only, so a project with seeds or snapshots notified consumers of relations the
invocation left stale. That is the same reason `test` was already excluded.
Narrowing what a run touches is `select`/`exclude`, which scope the graph too.
`dbt deps` writes to the project's `packages-install-path`, so a project that
moved it got no package cache at all: the publish found nothing at
`dbt_packages` and every job resolved its dependencies over the network again.
The path is read from `dbt_project.yml` and validated as project-relative,
since both cache copies are rooted at it.
Also states the sidecar's mutator contract at the module level: the dbt manifest
tables carry no RLS and grant `windmill_user` full access, so a user-scoped
transaction is not enforcement and every caller must have verified write access
to the script itself.
CLI: a module file is now grouped with its parent script for the push. Left in
a group of its own it got its own `alreadySynced`, so a push touching several
files of one bundle deployed the script once per file; the resulting versions
raced, and the asset graph could end up describing none of them.
* fix(dbt): seed a project for browser-created scripts, refuse a no-op retry
A dbt script created in the browser only got a descriptor, and the runtime
refuses a script whose bundle has no `dbt_project.yml`, so the advertised
Create → Deploy → Run path always failed its dependency job. New dbt scripts
now start with a project that builds: pointing `profile.resource` at a
warehouse is the one edit, and growing it is `wmill sync pull` plus a local
editor, which is where dbt development happens.
`dbt retry` builds its graph from the previous run's error, fail and skipped
nodes alone, so retrying an all-green run selected nothing and wrote nothing —
and a job that succeeds having written nothing still dispatches every
deploy-time write, waking every downstream consumer for relations no one
touched. Refused, with the reason.
CLI: a configured `target-path` or `packages-install-path` may be nested
(`build/target`), and `clean-targets` has a block form as well as an inline
one. Both are now parsed, and the exclusion compares the project-relative path
rather than the top-level segment, so a nested generated tree no longer lands
in the bundle and no longer makes a local `dbt run` look like a project change.
* fix(dbt): lock a project once, find the parent on either path separator
A dbt script's modules are its dbt project, not helper code with dependencies
of its own, so the generic per-module lock loop is skipped for it: the parent
lock already ran `dbt deps` and `dbt parse` over the whole project. Locking
each file separately re-materialised the bundle and re-invoked dbt once per
file, so a project of N files paid N project-sized passes and a large one timed
the deploy out. The 13-file fixture went from 14 relock passes to 1.
`pushParentScriptForModule` searched the raw path for `__dbt/`, so on Windows,
where the folder is spelled `__dbt\`, a module-only edit returned without
deploying its parent while the caller still recorded the file as synced. It now
goes through `getScriptBasePathFromModulePath`, which normalizes separators.
Also drops the last of the external-repository wording from the descriptor's
module docs and from the `codebase` rejection a user can hit.
* feat(dbt): infer the run form locally, keep test-only retries from cascading
`windmill-parser-wasm-yaml` 1.770.0 carries `parse_dbt`, so the browser and the
CLI derive a dbt script's run arguments from its descriptor instead of waiting
for the deploy to hand back a schema. Pins bumped in both.
`generate-metadata` was rewriting a dbt script's `lock` field on every run: a
dbt lock comes from the dependency job on a worker, so nothing generates it
locally and the resolved `!inline` reference was left inlined into the metadata
or blanked. It is restored instead, and a push straight after
`generate-metadata` is a no-op again.
A retry now needs a failed node that materialises something. `dbt retry` builds
its graph from error, fail and skipped nodes, and with `test_behavior:
after_all` a failing test is what `run_results.json` ends up describing — so the
retry reran tests, wrote nothing, succeeded, and still dispatched every
deploy-time write.
The dbt badge's destination is deterministic: writers outrank readers, and among
several writers of one relation (which the backend permits) the smallest id
wins, rather than whichever write edge arrived last.
* feat(dbt): browse the project and read a run's per-node result
Two views a dbt user expects and that the generic script surfaces do not give.
**The project.** A dbt script's editor gains a Project tab beside its
descriptor: the module bundle as the tree dbt itself expects, each file
read-only with syntax highlighting. The existing module tab strip is a flat row
built for a couple of helper files and does not survive a real project; a
13-file fixture already overflows it. Directories sort before files so it reads
like the checkout on disk, and an empty bundle explains the `cp -r` instead of
showing a blank pane.
**The run.** `DisplayResult` renders a dbt invocation's per-node breakdown above
the raw payload: totals, then a table of node, kind, target relation, rows and
time, with failures and warnings sorted first and carrying their message. The
data was already structured; it was being shown as JSON to scroll and PASS/WARN
counts to find in the log. On a failed run the same JSON rides in the error
message after the exit-status line, so it is parsed back out — that is the case
worth rendering, since the failing node is what the user came for.
* docs(dbt): say that profile.resource is what buys the asset graph
The starter descriptor described `profile.resource` as the thing rendered into
profiles.yml, with the project's own file as an equal alternative. It is not
equal: the resource PATH is the warehouse's identity in the asset graph, so a
project bringing its own profiles.yml runs fine and silently gets no assets, no
lineage and no cascade. The deploy already says so in its log; now the
descriptor a user starts from says it too, before they choose.
* fix(dbt): authorize a resource used only for asset identity, clean up after failed installs
A descriptor setting both `profile.profiles_yml` and `profile.resource` took
its connection from the project's file but returned the resource path as the
graph's warehouse identity without ever reading it. A script editor could
therefore publish `table://<any resource>/...` writes, and wake that
warehouse's subscribers, while connecting somewhere else. The resource is now
read on that path too — reading is what authorizes it — so the combination
keeps working for the case that wants it (keep your own profiles.yml, still get
lineage) and fails closed otherwise.
Provisioning cleaned up its staging directory only on the paths someone
remembered, so a run of failed or cancelled first-use installs accumulated
venvs, tarballs and installer scripts until the worker's disk was gone. All
three engines now hold their scratch paths in a guard that removes them on
drop, which is the one exit every path takes, cancellation included.
Frontend: `partial success` is dbt's word for a node that built but whose tests
failed, counted in `totals.error` and redone by a retry, so it ranks with the
failures instead of rendering green with its message hidden. And the run panel
now keys off the worker's engine discriminator rather than `{nodes, totals}`,
which is a shape an ordinary script can return. Both pinned by unit tests on
the extracted `parseDbtRun` helpers.
* feat(dbt): show a run's models on the run page
The run page is where you land on a running job, and until now it showed a dbt
run as streaming text: the per-node table only renders once the job has
produced a result, and the graph that moves per model lived on the pipeline
page you had to navigate to. A Models section now sits above the result,
scoped to the running script's own relations and its `ref()` lineage, polling
while the job is in flight so nodes move as dbt walks the DAG.
No `resolveGraph`: that merges drafts and live editor buffers into the
persisted graph, and a run page has neither.
* feat(dbt): retry failed nodes automatically, and from any worker
**Node-level retry, in the job.** `retry_failed_nodes: {attempts, delay_seconds}`
rebuilds only what a failed build left failed or skipped, before the job reports
failure. dbt confines a failure to its own subtree and `dbt retry` resumes
exactly that set, so a transient warehouse error costs those nodes rather than
the project. Doing it in-job is what keeps the state question out of it: the
previous attempt's `run_results.json` is still in the job directory, so there is
nothing to persist and no worker to land back on. This is the granularity
astronomer-cosmos gets from one Airflow task per model, without the ~6x that
per-model tasks measured.
A retry's `run_results.json` names only the nodes it redid, so it overlays the
accumulated results rather than replacing them: the job's result has to be every
node the job touched, or the nodes that succeeded before the retry settle no
materializations. Pinned by a test.
**Durable retry state.** `run_results.json` is now saved to `dbt_run_state` as
well as the worker's local cache, so an explicit `dbt_command: retry` works from
any worker of the group rather than only the one that failed. Only the results
are stored: `dbt retry` also needs `manifest.json`, roughly sixty times larger
and growing with the project (732 KB against 12 KB on the six-node fixture), but
the manifest is a pure function of the project files, vars and env, all of which
the stored identity already pins, so a worker restoring from the database
re-derives it with a `dbt parse` of about a second.
* fix(dbt): restore the sqlx cache, make retries cancellable and path-aware
**SQLx cache.** A `cargo sqlx prepare` deleted 750 entries, including the
enterprise queries CI needs under `SQLX_OFFLINE=true`, and the check that was
supposed to catch it reported zero losses because it was run from `backend/`
with a `backend/`-prefixed path, so its baseline was empty and it failed open.
All 750 are restored; the branch now adds 19 and deletes none, and
`SQLX_OFFLINE=true cargo check` passes.
**Retry backoff observes cancellation.** `canceled_by` is only written by the
job poller, which does not run between attempts, so re-reading it reported the
state as of the failed attempt and missed every cancel issued during the wait
— the whole window the check exists to cover. The wait now reads
`v2_job_queue.canceled_by` each second, and the job's deadline is honoured
before starting another dbt process.
**Retry state follows its script.** `dbt_run_state` is path-keyed like the
manifest sidecar but, unlike it, nothing regenerates it: a rename moves the row
so a resumable failure survives, while archive and delete clear it, so a script
later created at that path cannot inherit a stranger's failure and its
arguments.
**CLI.** `table` joins ducklake and s3object in the local graph's auto-trigger
kinds, matching `is_auto_trigger_kind` and the frontend's set; without it a
local graph and the generated docs omitted a cascade edge the deploy has.
* fix(dbt): carry only the project files a bundle can hold, and say what it drops
Exploring real and edge-case projects surfaced three frictions, all in the
import path a user hits first.
**A binary file broke the push, opaquely.** dbt projects carry images under
`docs/`, stray `.DS_Store` files and occasionally a parquet seed. Read as text
they become mojibake, and a NUL among them is rejected by Postgres with
`unsupported Unicode escape sequence` — which `wmill sync push` then reported as
success, exiting 0 with the script never created. Binary files are now detected
the way `git` detects them, by a NUL in the first 8000 bytes rather than by
extension, and skipped with the reason.
**The size guard the docs promised did not exist.** Now it does: 5 MB per file,
which only ever catches a committed dataset. Real dbt code is about 500 bytes
median and 1.9 KB at p90.
**Skipped files became a permanent phantom diff.** The push dropped them while
the sync diff still offered them, so every push reported changes no push could
resolve. One predicate now answers for the push, the staleness hash and the
diff.
Verified on a project with unicode filenames and content, CRLF endings, an
empty model, an ephemeral model, a disabled model, a `.md` docs block, an
extensionless README, six levels of nesting, a 7.6 MB seed and a PNG: it
pushes, round-trips byte-for-byte through pull, deploys to 7 dbt nodes and 6
`table://` assets (ephemeral and disabled correctly absent), and runs green.
* fix(dbt): resolve dbt-core against the adapter, settle partial success, unify status
**Adapters could not be provisioned.** The 1.x engine pinned `dbt-core` to a
fixed version independent of the adapter, but several adapters cap below it:
`dbt-mysql` at `~=1.7`, `dbt-oracle` and `dbt-databricks` below 1.12, and
`dbt-salesforce` has no package at all (it exists only inside Fusion). Those
projects failed at provisioning with a uv resolver dump. The install now asks
for a range and lets the adapter choose, and records what the resolver picked so
the lock pins a version that adapter can take.
The floor is the CLI this runtime invokes: resolving down to dbt-core 1.7
produced a working venv that then failed with `No such option '--target'`, which
is worse than not resolving. An adapter with no release in range now fails
naming itself and pointing at `dbt-core-2x` or `fusion`, instead of a resolver
dump. Salesforce is refused up front with the reason.
**`partial success` left a model stuck on `Running`.** It is dbt's word for a
node that built and then failed its tests, and it was already treated as a
failure when counting totals and deciding a retry — but the two sites that
settle the RELATION fell through to "says nothing", so the tailer's `Running`
was never replaced and a finished job showed a model still building. Six status
comparisons had drifted apart, two folding case and four not, while dbt-core 1.x
echoes the author's casing and 2.x uppercases; they are now one classifier.
**Agent workers.** The durable retry state and the cancellation poll both need a
database, which an agent worker reaches only through the API. The automatic node
retry is refused there rather than running a wait it could not interrupt, and
the docs say "any worker with a database connection" instead of overclaiming.
Also clears `dbt_run_state` when a path stops being a dbt script, and moves
`run_identity`'s contract onto `run_identity` from the digest helper below it.
* feat(dbt): show the transform behind a model on the run graph
The run page's graph carried a node for the script itself and drew every
relation as a bare table. Both were wrong for that page: the graph there is
already scoped to one script, so a node standing for it distinguishes nothing
(on the pipeline page it separates one project from another, which is why it
exists), and dbt's own DAG node is the model — the SQL and the relation it
writes are one thing, so a graph of relations alone leaves out what a reader
came to see.
The script node is dropped, and selecting a model now shows its SQL underneath
the canvas with its file path and materialization, read-only, the same view the
pipeline details pane gives.
* feat(dbt): move the graph with the run
The worker has always recorded a state per relation as dbt walks the DAG —
`running` when a model starts, `materialized` or `failed` when it ends — but
nothing rendered it: the graph response carries what a relation IS, not what a
particular run is doing to it, so the canvas had nothing to show and a running
job looked identical to a finished one.
`assets/run_progress/{job_id}` returns that state for one job, the run page
polls it beside the graph, and the asset node carries a spinner or its outcome.
Errors and retries need nothing extra: a failed node writes `failed`, and an
in-job retry rewrites the same row, so the node returns to `running` and on to
its new outcome by itself.
`materialized_partition` holds a relation's CURRENT state keyed by relation, so
filtering on `job_id` returns exactly what this run last touched — which is the
question a run page asks, and why a superseded older run shows nothing.
* feat(dbt): a dbt project is not a data pipeline
Deploying a dbt script marked it `auto_kind = 'pipeline'`, which enrolled it
in pipeline membership: the folder became a Pipeline entry on the home page,
the script folded into it, and `/pipeline/<folder>` opened a canvas holding
the project's whole model DAG next to the pipeline's own scripts. A folder
holding both then read as two projects in one editor, and the pipeline editor
offered to author transforms that are in fact authored in a local `dbt run`
loop and pushed as the script's bundle.
A dbt script is now never a pipeline member, and the pipeline canvas drops the
dbt script node. Its models stay, with their `ref()` lineage: the relations are
what a downstream pipeline script reads, and dropping them would break the
cascade from a dbt run — the point of giving dbt models `table://` identity.
Also drops a screenshot committed to this branch by accident.
* fix(dbt): authorize run_progress through the job, drop dbt from the local graph
`run_progress` read `materialized_partition` through `user_db` on the
assumption that RLS would scope the rows. That table has RLS disabled and no
policies, so any workspace member could pass a job id and read that run's
relation paths, row counts and error text. It now joins `v2_job`, which does
carry per-user policies, so a caller who cannot see the job sees nothing —
the same pattern `v2_job_completed` reads need. Verified as a plain member:
the old query returned 6 rows for another user's run, the new one returns 0,
while the job's owner still sees all 6.
The CLI's local graph still forced `in_pipeline` on every dbt script, so
`pipeline docs --local` and `pipeline dev` kept presenting a dbt project as a
pipeline the deploy no longer enrolls. It now skips them, matching the server.
A dbt descriptor has no asset parser locally, so nothing is lost: its models
come from the manifest the deploy derives.
Declares `run_progress` in openapi.yaml so the frontend uses the generated
client instead of a handwritten fetch; the generated `status` union also
replaces a hand-rolled string mapping.
* fix(dbt): drop the dbt node from the CLI's deployed pipeline views too
`pipeline dev` and `pipeline docs` (without `--local`) read `/assets/graph`
directly. That endpoint is asset-usage driven rather than membership driven, so
it returns a dbt script like any producer — and both commands render every
runnable, so a dbt project still showed up as a pipeline script there after the
local builder stopped emitting one.
`hideDbtRunnables` mirrors the frontend's projection of the same payload. It is
generic over the graph shape so the bounded-cascade view (`BCGraph`, a narrower
type over identical JSON) passes through without a cast.
The relations stay: they are what a downstream pipeline script reads, and the
node is what attributes them to a producer for every other consumer of the
endpoint, so the filter belongs in the views rather than the query.
* fix(dbt): narrow a selective run's cascade, settle the finished run graph
Review-round fixes.
A `select`/`exclude` run builds part of the project, but asset dispatch reads
the deploy-time write set for the whole script, so a run selecting one model
woke the subscribers of every other. Dispatch now intersects that set with the
relations the run actually recorded as materialized, scoped to dbt because it is
the only producer whose write set is decided per run. A run that recorded
nothing still dispatches everything, so an agent worker whose reconciliation
failed cascades as before. Verified both ways: `select: [extra_model]` no longer
wakes the `fct_orders` subscriber, and a full run still does.
`hideDbtRunnables` keyed its removal set on path alone while the graph keys
runnables by `(usage_kind, path)`, so a flow sharing a path with a dbt script
lost its node, edges and triggers too. Both copies now key on the pair.
The run graph never took a final reading when a job finished, so the last state
shown was whatever the tick before completion saw. Only `dbt-core-1x` streams
node events; the other engines record every relation during end-of-run
reconciliation, so their finished graph showed nothing until a reload.
`DbtNodeOutcome::Inconclusive` collapsed statuses the tally has to tell apart,
so two sites re-lowercased the status beside the classifier and `no-op` landed
in `totals.error` — a clean run reporting an error in its own result. Split into
Warn / Skipped / NoOp / Unknown so every site falls out of one match; `no-op` is
kept out of the retry set, which dbt spells as error / fail / skipped.
Also: reattach two doc comments to the items they describe, and correct the
engine-distribution table — only dbt-core-2x is baked into the images, 1.x is a
per-adapter venv provisioned on first use, and the default is compiled in rather
than an instance setting.
* fix(dbt): make the model chip inert where its project node is not on the graph
The canvas passed `onDbtSelect` unconditionally, so the chip always rendered
`cursor-pointer` and hover-highlighted — but the owner map is empty on both
graphs this feature added, since the run page carries no runnables and the
pipeline page hides the dbt node. The chip advertised a click that resolved to
nothing. It now takes its handlers only when the relation has an owner on this
graph, so it stays live on the surfaces that do show the project node.
`classify_status` and `DbtNodeOutcome` were `pub` in a private module with no
caller outside the file, unlike every neighbour.
* fix(dbt): take the cascade's write set from the run's own result
The previous narrowing read `materialized_partition`, which was wrong twice.
That table keeps one row per relation and the newest writer takes `job_id`, so
two overlapping runs over the same model erase each other's claim to it: the
earlier job would dispatch a subset of what it built, or none of it.
And an empty row set was read as "recording failed, dispatch everything" when it
is also a real answer. A `select` matching no model, or one resolving to tests
only, exits 0 having built nothing — and then woke every consumer of every model
in the project, which is the opposite of what the narrowing exists to do and is
reachable by a typo in a run argument.
The run now reports the relations it materialized in its own result, which is
immutable and per job. Absent means the producer said nothing (a job from before
the field, a non-dbt producer) and the whole deploy-time set dispatches as
before; present-and-empty means it built nothing and dispatches nothing.
Verified on all three: an unmatched selector builds nothing and wakes nobody, a
selector naming one unsubscribed model wakes nobody, and a full run wakes the
subscriber.
Also indexes `materialized_partition (workspace_id, job_id)` -- the run page
polls that shape every 2s and no existing index leads with `job_id` -- corrects
the selective-cascade section of the design doc, which still described the old
deploy-time behavior, and reattaches `buildLocalPipelineGraph`'s doc comment.
* docs(dbt): attach the CLI JSDoc to its function, correct the index rationale
The `hideDbtRunnables` JSDoc ended up documenting the type declared beneath it —
made while fixing the same mistake one function down.
The migration's comment credited the cascade with a `job_id` lookup that the
same commit replaced with a read of the job's own result. The run page's poll is
the only reader keyed on that column.
* fix(dbt): refuse graph publication for a removed script, allow test-only retries
An archived or hard-deleted script could still republish its graph: the
publication guard filtered `deleted` but not `archived`, and treated a missing
row as "nothing newer exists" rather than "nothing left to publish for". A
dependency job or dynamic run finishing after the removal put the asset,
provenance and subscription rows back with nothing left to clear them.
`dbt_command: retry` refused a run whose only failures were tests, which is
precisely what `test_behavior: after_all` produces. That restriction existed
because a successful job dispatched its whole deploy-time write set, so a
test-only retry would have woken every consumer for relations no one touched —
the cascade now dispatches what the run reports materializing, so it wakes
nobody and the restriction only blocked a legitimate retry.
* fix(dbt): gate run progress behind the job-read check, not RLS alone
The endpoint joined `v2_job` so RLS would decide visibility, which it does — but
`require_job_read_access` adds two things RLS does not: a scoped token's
`if_jobs:filter_tags` restriction, and the app-embed cutoff that stops untrusted
app JS from inheriting the viewer's broader job access. A scoped or embed token
could therefore read relation names, statuses, row counts and errors for jobs
the ordinary job endpoints deny it.
That helper is private to `windmill-api`, which depends on `windmill-api-assets`
rather than the reverse, so the endpoint moves to the job routes instead of the
check being duplicated. It is job-scoped anyway:
`/w/{ws}/assets/run_progress/{job_id}` becomes
`/w/{ws}/jobs/run_progress/{id}`, and the frontend follows the generated client.
* feat(dbt): a dbt run does not trigger downstream runs
dbt orders its own DAG, so a cascade only ever adds one thing: waking a Windmill
script that reads a mart. That edge is narrow, and only half of it can even be
expressed — nothing outside dbt can declare a `table://` write, since
`// materialize` accepts DuckLake targets only, so an ingestion script cannot
wake a dbt project.
Against that, dispatching correctly is not cheap. A run's `select` can build any
subset of the project, so the deploy-time write set is not what ran; using it
wakes consumers of relations the run never touched, and narrowing it needs a
per-job record of what was built. The per-relation state table cannot supply one
(it keeps a single row per relation stamped with the last writer), and the
result field added for it made a run's own output carry the cascade's bookkeeping.
So `asset_dispatch` returns early for `ScriptLang::Dbt`, before the producer
gate. dbt still materializes, records per-model state and publishes its graph:
models, `ref()` lineage and live run progress are unchanged, and a
`# on table://<mart>` reader still renders beside the model it reads. It simply
does not fire. Wiring it up later means deciding what a selective run should
notify, which is the actual work.
Verified: a full run of a 6-model project succeeds and starts nothing, where it
previously triggered its subscriber; the run page still reports all 6 relations
and the folder graph still carries 14 tables and 8 ref() edges.
* fix(dbt): remove the cascade surface, settle stranded models, fix nested __mod
Stopping dispatch left its surface behind. `table://` was still an auto-trigger
kind, `persist_ingest` still derived subscriptions from a manifest's reads, and
the deploy still accepted `# on table://` — so the canvas drew cascade arrows
into scripts nothing could wake. All three are gone: the kind no longer derives,
the ingest only deletes rows earlier versions wrote, and the deploy refuses the
annotation with a message saying why rather than persisting a silent no-op.
`DescriptorTriggers` went with them; every field it parsed was cascade config.
A model marked `running` by the live tailer was never settled when the run did
not finish: reconciliation only revisits nodes `run_results.json` names, and a
cancelled or timed-out run has none for the model in flight, so the finished job
showed a relation building forever. It is now settled on every exit path.
Verified by cancelling a run mid-flight: 3 models `running` before, 3 `failed`
after, none stranded.
`getScriptBasePathFromModulePath` took the first matching suffix rather than the
outermost boundary, so `proj__dbt/models/legacy__mod/a.sql` resolved to
`proj__dbt/models/legacy`. dbt owns its directory names verbatim, so a folder
ending `__mod` is legal inside a project, and a module-only sync would have
looked for a descriptor that is not there and skipped the deploy.
* fix(dbt): colour a finished run's models from its own result
`materialized_partition` keeps one row per relation stamped with whichever job
wrote it last, so reopening a run showed only the models no later run had
touched since — down to none for an old run, which reads as a broken page rather
than as stale data. Reproduced: a 6-model run reported 6 relations, then a second
run rebuilt one shared model and the first reported 5.
A finished run already carries the answer. Its result lists every node with a
status, and the graph carries each asset's dbt `unique_id`, so the two join
directly — no path derivation, nothing stored twice, and nothing a later run can
overwrite. The endpoint stays for the live window, where the result does not
exist yet, and as the fallback for a run that never produced one (cancelled or
killed, whose relations the worker settles in the table instead).
`relationOutcome` mirrors the worker's `classify_status` so the colour drawn over
a record agrees with the record: `warn`, `skipped` and `no-op` leave the relation
untouched and stay uncoloured, as do tests and analyses, which match no asset.
Verified in the browser on the run whose model had been stolen: all six
relations green again, both sources correctly uncoloured.
* docs(dbt): record why only dbt-core 1.x has live per-model progress
`emits_node_events()` reads as "the Rust engines produce no node events", which
is false and would close off the option. They produce exactly the same events;
they put them on the console and ignore `--log-format-file json`, which both
accept. Measured on 2.0.0-alpha.5 and fusion 2.0.0-preview.202: 15 node events
each on stdout, 0 in the file log, for a three-model project.
Taking them means owning the job log's presentation to work around a flag that
is documented and simply unimplemented, so the note records the measurement, the
sample event, and that flipping the predicate is the whole change once either
engine honours it.
* fix(dbt): give HighlightCode a dialect-agnostic sql language
`npm run check` had three errors the fast check does not reach: `"sql"` is not a
value `HighlightCode` accepts. Every SQL dialect it knows maps to one grammar,
but a dbt model is compiled by whichever adapter the project targets, so naming
a dialect would be a guess — `sql` is now a value in its own right.
`langOf` was typed `string` and returned `markdown`, `python` and `text`, none
of which the component accepts either, so a dbt project's YAML and Python files
rendered unhighlighted. It now returns the component's own prop type, which is
what caught them, and `undefined` for what has no grammar rather than a name
that silently means the same thing.
Verified in the project panel: SQL 22 tokens, YAML 27, where YAML was plain.
* fix(dbt): stop failing no-op models, drop table triggers client-side, keep cross-selection edges
The sweep that settles a run's stranded relations was marking `no-op`, `warn`
and `skipped` models FAILED on successful runs: reconciliation reports those
nodes without settling their record, so they were indistinguishable from a model
the run never reached. It now excludes every relation the run accounted for, so
only the genuinely abandoned ones are settled.
`table` was removed from the backend's auto-trigger kinds but left in both
client mirrors, so the editor and `pipeline dev`/`docs` kept drawing cascade
arrows the deploy will not create.
`isModuleEntryPoint` scanned for the first `__mod/`, the same bug its sibling
just had: a `legacy__mod/script.ts` nested in a dbt project — dbt owns those
names verbatim — read as that script's entry point. Both now anchor on the
outermost boundary.
A script selecting a model whose parent another script builds dropped the parent
entirely, so no `dbt_edge` could reach it and the two relations sat on the graph
unconnected. The parent is now kept as an endpoint and recorded as a READ, since
this script does not build it — splitting a project across selections only
composes if the seam still draws.
* fix(dbt): don't double-run after-all tests, count only models a script builds
An `after_all` run whose test phase failed saves a `run_results.json` holding
tests alone. Retrying it reran exactly those tests — and then the test phase ran
the whole suite again, appending a second copy of every result: duplicate ids in
the run table, doubled totals. A retry whose saved results are tests alone IS
the test phase, so the suite is not run after it, and the two phases now merge
by node id rather than concatenating.
Keeping a selection's unselected parents as nodes made them count toward the
`×N` badge, whose tooltip says "materializes N models" — a script selecting one
mart claimed the staging models upstream of it, and the number grew with the
seam. The count now comes from the relations the script writes.
That change also made the cross-selection read block dead, with a comment
asserting the inverse of what now happens; it is removed, and the test that
covered it still passes on the new arm. The test I added landed between a
neighbouring test's comment and its `#[test]`, orphaning the attribute so that
test stopped running.
Two display fixes: the run page no longer shows a relation's SQL when the
provenance belongs to another project that materializes the same relation, and
the editor no longer draws an explicit `# on table://` arrow the deploy refuses.
The starter descriptor no longer promises the removed cascade.
* fix(dbt): clear untouched models, reject unknown descriptor fields
A `no-op` model was left `running` forever on a successful run. The previous
attempt at this stopped the sweep marking such models FAILED but gave them no
terminal state instead, so they simply never settled. Reconciliation now returns
what it settled and what the run reported but did not build, and the two get
opposite treatment: a relation the run left untouched has its row DELETED, which
is what the finished run's own result says about it (`relationOutcome` colours a
`no-op` nothing), so the live and settled views agree; only a relation the run
never reached at all is failed.
The descriptor accepted unknown fields, so `selcet:` was ignored and left an
empty selection — building the whole project — and a misspelled `target` fell
back to the profile's default. It rejects them now. That immediately caught two
of our own test fixtures still passing `repo:`, a field removed with the git
path, which is exactly the class of mistake it exists to stop.
`isDbtModulePath` matched `__dbt/` anywhere in a path, the third site with that
bug: `foo__mod/vendor/x__dbt/a.ts` read as a dbt project file, and the push then
looked for `foo.script.yaml` and could skip the edit.
A verbatim dbt bundle dropped any file named `*.lock` before it reached the
module map, so an authored `uv.lock` never deployed and the unmodified-project
round trip quietly lost it. The exclusion now applies only to `__mod` bundles,
where `.lock` really is the script's own lockfile — in the walker that hashes
modules too, or a change to such a file would not register as one.
Also: `langOf` fell back to `undefined`, which HighlightCode resolves to
TypeScript rather than to no highlighting, so seeds and Markdown were coloured
as code; and four comments still gave the removed cascade as the reason for
sharing an asset node, which is now lineage.
* fix(dbt): retry failed tests too, anchor the last __dbt path check
`retry_failed_nodes` only ran after the model phase, which fails before the
`after_all` test phase exists — so a project whose models built and whose tests
failed got no retry at all, exempting exactly the failure mode that separate
phase produces. The loop is now a function, called after both phases.
`isDbtGeneratedPath` matched `__dbt/` anywhere, the fourth site with that bug:
`foo__mod/vendor/x__dbt/target/a.ts` counted as generated dbt output, so
`ignoreF` excluded an ordinary module file and a module-only edit never deployed
its parent script.
`wmill sync push` still dropped an ADDED or DELETED `.lock` three branches
before the module arm, so the earlier fix only covered a first push: adding a
`uv.lock` to a deployed project was reported as a change forever and never
applied, and deleting one left it deployed. Editing worked, which is what made
the round trip look whole.
Also removes a duplicate `#[test]` that was double-registering a test and
detaching its neighbour's comment, and rewrites seven comments that still gave
the cascade as the reason for behaviour that now serves lineage only.
* fix(dbt): bound the excluded-file read, keep the retry budget job-wide
`isBundledModuleFile` read a file in full before deciding it was too big or
binary, so a project sitting next to a multi-gigabyte parquet seed loaded the
whole thing only to reject it. It now takes the size from `stat` and reads at
most the 8 KB the NUL check needs: a 191 MB file is rejected in 0.0ms at 82 MB
RSS.
Calling the retry helper after both phases gave each its own `attempts` budget,
so a job could spend double what the descriptor asked for — the bound exists
because every attempt is a real dbt invocation holding a worker slot. The budget
is now the job's, spent across whichever phases fail, and the field says so.
Extracting that helper had also placed it between `#[allow(clippy::
too_many_arguments)]` and `run_dbt`, taking the attribute off the 12-argument
function it was written for.
* fix(dbt): actually spend the retry budget
`retry_failed_nodes` looped on `while *remaining > 0` and never decremented it,
so a failing job reissued `dbt retry` — logging "attempt 1 of 3" each time —
until the job's deadline instead of `attempts` times. The decrement existed
briefly and was lost when the function was re-extracted by hand.
Claiming and counting are now one operation, `claim_attempt`, because keeping
them apart is exactly how the bound goes missing: the loop cannot iterate
without spending the budget.
Its test is bounded by its own `for` rather than by the function under test. An
earlier version collected `std::iter::from_fn(|| claim_attempt(..))`, which
against a non-spending `claim_attempt` is an infinite iterator — it allocated
until the machine died. A test for a loop bound must fail an assertion when the
bound regresses, not consume the host: it now reports `[1, 1, 1, …]` against
`[1, 2, 3]` in 0.00s.
* fix(dbt): ask before reading, not after
Bounding `isBundledModuleFile` did nothing for the bundle builder, which read
the whole file into memory and only then asked whether to keep it — so a
multi-gigabyte seed beside a project was still loaded in full just to be
skipped. The predicate is now consulted first, and the read happens only for
files the bundle actually carries.
* feat(dbt): animate the ref() edges feeding the model being built
The nodes moved during a run but the edges did not, so the graph showed where
dbt had got to without showing it flowing there.
Reuses the canvas's existing rule rather than adding a second one: an edge
animates when it touches what is happening. For a pipeline that is the running
script; for dbt the unit of work is the model, so a `ref()` edge animates while
its target builds. Same `animated` field, same visual language, no new styling.
Verified mid-run on a 7-model project: of six `ref()` edges only the two feeding
the model then building were animated, and none once the job finished.
* feat(dbt): show what each model wrote, and say when its SQL is another project's
Three things a reader wanted from the run graph and could not get.
Row counts: the worker already records one per relation and `run_progress`
already returned it, but the graph used only `status` and dropped the number. A
model that built green having emitted zero rows is the failure that looks like a
success, so the count is on the node.
The relation's fully-qualified name, copyable: there is no table browser to open,
so the next best affordance is the exact identifier to paste into a SQL client.
It is parsed with `splitRelation`, which honours quoting the way the worker's
`split_relation` does — splitting on every period renders
`"wh"."analytics.v2"."orders"` as a relation `orders` in a schema `v2`, which
does not exist.
And when two projects materialize one relation, the graph keeps a single
provenance winner, so the losing project's node carries the other's model. The
SQL was already suppressed there — correctly, it is not this run's code — but
silently, which reads as a dead click. It now says so.
* fix(dbt): a finished run's graph is the models it built, not today's project
`/assets/graph` is the current deploy, so an old run's graph drifted with the
project: a model added after it appeared as though the run had built it, and the
older the run the wronger the picture. A finished run's node set now comes from
its own result, which named exactly what it touched.
Sources survive the filter regardless — dbt never lists them in
`run_results.json` because it does not build them, but they are the upstream the
run read, and dropping them would leave the models hanging.
The graph is still the current deploy's, so a model renamed or deleted since
cannot be drawn at all. Rather than a silently shorter graph, the count is
stated above it.
Verified by adding a model after a run: the old run renders 7 models without it,
a fresh run renders 8 with it.
* feat(dbt): preview a model's rows with `dbt show`
There was no way to see the data behind a node — only its SQL and its row count.
`dbt show` selects from a model and returns rows, and every engine ships it, so
the preview needs no adapter code of ours: no connection path, no dialect-correct
quoting, no type coercion for ten warehouses. It runs against the profile the
run already renders.
It is a `dbt_command` rather than a new endpoint, so it inherits the whole job
path — authorization, isolation, cancellation, logs, engine provisioning — and
`limit` joins the run form beside it. That the allowlist can admit it at all is a
consequence of dropping the cascade: while a successful job dispatched its
deploy-time write set, a command that wrote nothing woke every consumer for
relations nothing had touched.
Read-only, and treated as such: no graph republish, no materialization records,
no retry state, no test phase. Captured rather than streamed, like `dbt ls` —
these rows are the result, not commentary, and the job-log writer is what
`NO_LOGS_AT_ALL` discards.
Verified: `{"dbt_command":"show","select":["stg_customers"],"limit":3}` returns
three rows; a preview leaves `materialized_partition` untouched (62 → 62, 0 rows
for the job); `clean` is still refused by the allowlist.
* feat(dbt): preview a model's rows from the graph, and keep our locks out of dbt projects
The run page could show a model's SQL and how many rows it wrote, but not the
data. Selecting a model now offers "Preview rows", which runs the script with
`dbt_command: show` and renders the result as a table.
Explicit rather than on-select: a preview is a job, so it costs a worker slot
and the engine's start-up, and previewing on every click would spend both on
mere navigation. Sources are excluded — dbt shows what a model SELECTs, and a
source is not one.
Also: `updateModuleLocks` was the one module helper that never learned about
verbatim bundles, so it walked a dbt project writing `foo.lock` beside `foo.sql`.
None of those files is a Windmill script needing a lockfile, and the bundle
promises to round-trip the project byte-for-byte — our artifacts have no business
in it.
Verified in the browser: selecting `stg_customers` and previewing returns the
columns `id`/`src` and five rows from the warehouse.
* fix(dbt): keep a run's models when another project owns their provenance
Scoping a finished run's graph to the ids it named dropped relations whose
provenance winner belongs to a different project — so a run of a project sharing
a schema showed 3 of the 6 models it had built. An id that was never this run's
package cannot be judged against its result, so it is kept: the relation IS one
the run wrote, and hiding it understates the run. The same rule applies to the
"no longer in the project" count, which otherwise reported deletions that were
only provenance collisions.
Previews are now cached per model and survive the selection moving. One was
thrown away whenever the reader clicked elsewhere, which for a job costing a
worker slot and an engine start-up meant re-running it to see it again — and the
run continues in the background, so leaving and returning finds the rows there.
The spinner also never span: `startIcon` takes the icon and its classes
separately, so the animation has to be passed alongside.
How long it took is shown with the rows. A preview is a job, and its cost should
not be something the reader has to guess at.
* fix(dbt): resolve argument references, clamp the show limit, flag renamed relations
`handle_dbt_job` cloned `job.args` where every other executor calls
`build_args_map`, so a `$var:` / `$res:` / `$encrypted:` argument reached dbt as
the literal string. A placeholder holding a schema or an `enabled` flag would
then build a different slice of the project than the caller asked for.
`--limit` took any positive i64, and the worker buffers the whole of dbt's
stdout to read the rows out of it — so a caller with only run permission could
make it hold an unbounded allocation. It is clamped to a ceiling now, extracted
as `show_limit` so the bound is pinned by a test rather than inline in an async
function nothing can reach.
And a model keeps its id when its alias or schema changes, so an old run's node
showed today's relation while the run wrote another — the page asserting it had
materialized a table that did not exist yet. The run's result carries the
relation each node actually wrote, so the drift is detectable without a graph
snapshot, and the count is stated above the graph. Rendering the run's own
lineage still needs a per-job snapshot; this stops the page claiming otherwise.
* fix(dbt): stop persisting resolved secrets, bound the preview by bytes
Resolving `$var:` / `$res:` / `$encrypted:` for dbt — added in the previous
commit — meant `save_run_state` wrote the resolved PLAINTEXT into
`dbt_run_state.args` and the worker's `state.json`. The row outlives the job, so
a secret stayed in the database and a later `dbt_command: retry` replayed it
after the grant was revoked or the value rotated. The invocation now carries the
args as submitted alongside the resolved ones, run state persists those, and the
restore path resolves them again under whoever is retrying.
Clamping `--limit` bounded the row COUNT, not the size: one column can hold a
megabyte, so a thousand rows is a thousand megabytes, and `run_capturing`
buffers all of it. The captured output has a byte ceiling now.
`limit` became a built-in argument without joining `RESERVED_ARG_NAMES`, so a
descriptor writing `{{ limit }}` was silently handed the preview control's
default instead of being told the name is taken.
Two display fixes: the relation-drift banner compared a canonicalized (lower
case) asset path against the warehouse's own spelling, so it fired on every
model of every finished Snowflake run; and caching a preview's failure left
`Preview rows` dead for that model until reload.
* feat(dbt): key the graph by script version so a run renders its own project
The dbt graph was keyed by path alone, so a deploy overwrote the only copy and a
run page could only ever show today's project — an older run rendered today's
models, SQL and `ref()` lineage no matter what it had run. My previous attempt
filtered that view to the ids the run named, which stopped it lying but could not
show what was gone: the data no longer existed.
`dbt_node` / `dbt_edge` now carry `script_hash` in their primary key, so each
deployed version keeps its own graph, and the run page passes the version its job
recorded. Per DEPLOY, not per run — ten thousand runs of one version share one
graph — and a composite FK to `script (workspace_id, hash)` with ON DELETE
CASCADE means a version's graph dies with it. Nothing pruned these before,
because there was one copy per path; they would otherwise have accumulated with
no sweep.
Two deploys of one path now write disjoint rows, so the graph can no longer be
lost to a race. `claim_graph_publication` remains only for what is still
path-keyed — the `asset` usage rows — and an older deploy finishing late records
its own graph before declining to touch those, where before it published nothing
at all.
A pinned request is scoped by the version's own nodes rather than by `asset`:
that table describes the current deploy, so scoping through it would filter a
model out of the very run that built it.
Verified end to end: deployed v1 (8 models), ran it, deployed v2 with four models
removed and one rewritten. The old run renders 8 models, 6 ref() edges and v1's
SQL; a new run renders 4 and the v2 rewrite.
* fix(dbt): scope graph cleanup to one version, bound the preview capture
Archive and delete both act on a single `hash`, but the graph cleanup they
called deleted every row for the path. Now that the graph is keyed per
version, archiving an old version erased the live one's models, SQL and
lineage, and nothing repaired it. Both callers have the path in hand, so the
by-hash wrapper is gone and they use the version-scoped clear directly.
`dbt show` checked its 8 MB ceiling after `wait_with_output` had already
buffered everything, so the ceiling could not bound what the worker held.
`run_capturing` now reads both pipes incrementally against a caller-supplied
limit and kills the child on overflow. The read buffers are heap-allocated:
as arrays they were baked into the future, which the job poller boxes several
layers deep, and that overflowed the worker thread's stack — a `dbt show` run
aborted the whole worker process.
A retry's `dbt parse` ran on the arguments as submitted while the build ran on
resolved ones, so a `$var:` shaping the graph parsed verbatim. The parse moves
to the caller, after resolution.
A run that names its own `select`/`exclude` now drops the descriptor's
`selector`: dbt resolves `--selector` instead of `--select`, so passing both
made a preview of one model return another's rows.
Also: log instead of silently swallowing a `modules` column that fails to
deserialize (pre-existing, but for dbt it means running with no project at
all); keep the model SQL reachable once a preview has landed; render which
node the rows came from; stringify object-valued cells; document
`dbt_script_hash` in the OpenAPI spec.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* docs: record the per-worktree dev environment and the backend-run check
Three mistakes this guidance would have prevented, each of which cost a cycle:
A worktree has its own database and ports, but AGENTS.md stated the
single-checkout defaults as facts. Pointing `DATABASE_URL` at another
worktree's database makes `cargo sqlx prepare` fail on every query touching a
table your migrations added — and it deletes `.sqlx/` before it fails, so the
cache is gutted rather than merely stale. Starting a backend on the wrong port
leaves the UI up with every call 502ing, which reads as an application bug.
Both values are now discoverable with commands that work as written.
`prepare` is also documented as the wrong tool for a removal-only change: the
cache is already complete for CI, and the only residue is orphaned entries that
can be found by text-matching against the sources without a database.
Nothing told a reader that `cargo check` does not exercise a worker path. A
read buffer declared as an array inside an async block is baked into the
future, and once boxed by the job poller it overflows the worker thread's
stack — compiling and unit-testing clean while aborting the whole worker
process at runtime.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): scope the remaining path-wide reads and clears to one version
Four places still spoke for a whole path after the graph became per-version:
The relation-root drift check read `dbt_node` by path with an unordered
`LIMIT 1`, so with v1 at root A and v2 at root B it could answer with v1's
row, suppress the refresh v2 needed, and leave v2's graph naming relations the
run does not build. It now reads this job's version.
`dbt_dep`'s no-resource branch cleared the path, so a descriptor edited to
bring its own `profiles.yml` emptied every earlier version's graph and with it
every finished run's page. The ownership being given up is the path-keyed
`asset` usages cleared beside it; the graph clear is now this version's.
The graph was inserted before the publication claim checked the version was
still live. Archive and delete only soft-update `script`, so the foreign key
still accepted an in-flight dependency job's rows and the failed claim
committed them — and because pinned queries deliberately serve archived
versions, deleted model SQL became readable again. The write is now gated on a
`FOR UPDATE` liveness check.
`clear_dbt_run_state_by_script_hash` resolved a hash to a path and deleted the
path's saved run. `dbt_run_state` is keyed by path by design — one saved run
per script — so archiving one version discarded the live version's resumable
failure. It clears only once no live version of the path is left; `identity`
already refuses a resume whose project, warehouse or engine moved.
"Preview rows" ran `runScriptByPath` while the SQL beside it was pinned to a
hash, so an old run showed its own SQL over today's rows. Verified end to end:
with v3 deployed, the v2 run's preview runs v2's hash and returns v2's rows.
Also: keep the TAIL of a captured stderr, since dbt prints its summary last;
one `$derived` for the parsed result rather than five; collapse three
near-identical argument accessors onto one generic; fold the single-use
`copy_dir_command` into its caller; and give `parseDbtRun.ts` one status
classifier instead of spelling dbt's failure vocabulary twice.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor(dbt): one JobCtx down the executor, one table per adapter
Two changes aimed at the operations this code will keep having: adding a
phase, and adding a warehouse.
`JobCtx` already bundled the five values every phase needs, and nine functions
took it — but the top of the executor threaded the fields apart and rebuilt the
struct at each call, so the same literal appeared eight times and each new
phase meant five more parameters. It is now built once per entry point and
reborrowed. `prepare_project` goes from 21 parameters to 17, `retry_failed_nodes`
from 15 to 11, and `run_dbt` drops below the lint threshold. The two remaining
constructions are the worker boundary, where the pieces genuinely arrive apart.
`DbtAdapter` answered five questions with five parallel matches over the same
eleven variants, plus a sixth list of adapters kept by hand in a test. The
facts now live in one `AdapterSpec` per adapter, reached through one exhaustive
match, so adding a warehouse states its name, driver, package, port, database
key and licensing together and the compiler demands the arm. Each arm spreads
from a Postgres base, which makes the inheritance visible per adapter instead
of hidden in the `_ =>` defaults `default_port` and `database_key` used to
carry. `DbtAdapter::ALL` replaces the list the test kept separately.
Verified by dumping all seven facts for all eleven adapters before and after:
byte-identical.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): job-keyed run progress, and stop path-wide reads and clears
Six findings from the last round, in the order they bite.
The publication liveness gate refused on `archived`, but `create_script`
archives the parent on every redeploy — so deploying v2 while v1's dependency
job was still parsing left v1 without a graph, permanently, which is the exact
case the unconditional write existed to serve. It gates on `deleted` alone now;
an explicit archive is still covered by the `FOR UPDATE` ordering.
A project-owned `profiles.yml` trusted `profile.type` instead of reading the
file. The Rust engines carry every adapter, so a CE script could declare
`postgres` over a target that is `sqlserver` and have dbt connect with the
enterprise adapter. The file is read whichever way, and a descriptor that
disagrees with it is refused.
Renaming a dbt script, or editing one so its newest version is no longer dbt,
cleared the graph for the whole path — every older version's models, SQL and
lineage, which their own finished runs still render. Neither needs it: graph
queries join on `(path, hash)` through a `language = 'dbt'` CTE, so an old
version's rows cannot attach to whatever lives at that path next.
Live progress read `materialized_partition`, whose key is the relation and
whose `job_id` is only the last writer. Two runs of one project took rows from
each other. Progress now has its own job-keyed table; the relation table is
untouched, because one row per relation is right for the pipeline canvas and
fork defer. Verified with two overlapping builds: both keep 6 rows in the new
table, while the old one attributes 6 to one run and 0 to the other.
`Scratch::drop` removed a half-installed virtualenv synchronously from inside
the job future, blocking a runtime thread; it goes to `spawn_blocking`, with a
direct call when there is no runtime to hand it to.
The E2E list asked for a `# on table://` subscription the deploy now refuses.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* feat(dbt): snapshot a dynamic descriptor's graph per run
A `{{ }}` placeholder in `vars` can enable a different set of models per run, so
those runs re-ingest the graph. Keyed by version alone, each re-ingest
overwrote the last: reopening an older run showed the newer run's project, and
a model only the older run built was gone entirely — no SQL, no lineage, and
nothing the saved result could colour, since it can only tint nodes that are
there.
`dbt_node` / `dbt_edge` gain `job_id`. A run of a dynamic descriptor writes its
own snapshot under its job id and its page reads it back; a static descriptor
writes the version's graph once, under a zero-UUID sentinel, and every run of it
reads that. The sentinel is a value rather than NULL because `job_id` is part of
the primary key and Postgres does not treat two NULLs as the same key, so each
re-ingest would add a row set instead of replacing one.
`/assets/graph` takes `dbt_job_id` and prefers a snapshot when one exists,
falling back to the version's graph otherwise — so a run page passes it
unconditionally and static descriptors are unaffected. Snapshots age out after
30 days, pruned by the runs that write them, so no background sweep has to learn
about these tables.
Verified end to end: one deploy, two runs of it with `extra=yes` and `extra=no`
gating a model's `enabled`. The version's graph holds 6 models, run 1's snapshot
7 including `opt_extra`, run 2's 6 without it; the endpoint returns each run's
own and falls back to the version's when the parameter is omitted.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* perf(dbt): only snapshot a run whose graph differs, and prune from every run
Two costs the per-run snapshot carried, both found by measuring it rather than
by reading it.
A snapshot was written for every run of a dynamic descriptor, but marking one
dynamic is conservative: `graph_is_per_run` is true whenever `vars` holds a
`{{ }}` placeholder or `env` holds a `$var:`, which says the arguments reach dbt
and not that they change which models exist. The usual case is a date var, whose
graph is identical run after run, so the table filled with copies of an
unchanging picture — around 1 KB per model per run, which is a gigabyte or so a
month for a 200-model project on an hourly schedule. A row set now carries a
digest of its nodes, edges and relation root, and a run whose digest matches the
version's writes nothing; the read already falls back to the version's graph, so
those pages are unchanged. Only a run whose model set really differs pays.
The prune was hung off the progress reporter, which exists only for engines that
emit node events — so a Fusion or dbt-core-2x instance accumulated snapshots and
never deleted any. Retention that stops working because of an engine choice is
not retention; it runs detached from every dbt run instead.
Verified against a descriptor with a var-gated model: the version's graph holds
8 rows, a run that resolves to that same graph stores none at all, and a run
that enables the extra model stores its own 9. Both pages still render their own
project — 6 assets without the extra model, 7 with it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): scope every dbt_node join to the chosen snapshot
`job_id` joined the key, but only the scoping CTE and `dbt_edge` were taught to
filter on it. The outer node SELECT and the parent/child joins in the edge query
were not, so each model came back once per retained snapshot plus once for the
version's graph, and each edge matched every combination of the two — the model
count multiplied and the edge join fanned out quadratically. Measured against
one stored snapshot: 17 node rows where 8 are wanted, and 28 edge pairs where 7
are. The response dedup hid the edge blow-up from the payload, not from the
plan, and the run page refetches the graph every two seconds.
The progress table gained writers it was missing. `terminalize_running_relations`
settled only the relation-keyed table, so a cancelled or killed run — the case
that function exists for, since it leaves no `run_results.json` — showed every
in-flight model still spinning on the run page for as long as the row lived. An
agent worker cannot write the new table at all, having no database of its own,
so the read falls back to the relation-keyed one when a job has no rows there.
Also: a wrapped string literal missing its backslash put eighteen spaces in the
middle of the profile-disagreement error; a comment still described concurrent
runs of one dynamic version overwriting each other's graph, which is what
keying by job removed; and the `materialized_partition` index justified itself
by a run-page poll that has since moved to another table, though the closing
sweep still earns it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): give a graph snapshot a marker row, and scope what reads it
Five findings, four of which are the same mistake in different places: a
snapshot's identity was inferred from its contents.
Existence was inferred from a `dbt_node` row, so a dynamic run that disabled
every model — a legitimately empty graph — read as "no snapshot" and its page
showed the deployed models instead. The digest was a column repeated on every
node and read back with a `LIMIT 1` carrying no `job_id`, so a run could compare
itself against another run's digest and suppress a snapshot it needed. The
relation-root drift check read the same rows unscoped, so after a drift it could
find a previous run's root and conclude nothing had moved.
`dbt_graph_snapshot` holds one row per stored graph — path, version, job,
digest, timestamp. Existence is that row, the digest lives there once, the drift
check reads the deployed row explicitly, and the retention sweep deletes markers
first and then the rows no marker stands for. The digest is SHA-256 rather than
`DefaultHasher`, whose output is documented as unstable across Rust releases:
this value outlives the process that computed it, so a toolchain bump would have
silently stopped every comparison matching and quietly reinstated the duplicate
snapshots the digest exists to prevent.
`/run_progress` ignored the view token, so a share-link viewer got the graph and
was refused the progress that colours it.
A preview sent only its own three arguments, so a descriptor with a required
`{{ }}` var could not be previewed at all and an overridden one previewed a
different relation than the page was showing. The run's arguments go first now,
with the preview's three overriding.
Verified on a project whose only model is var-gated: the deploy stores a marker
with zero nodes, a run with the var set stores a marker with one, and the
endpoint answers 0 and 1 respectively rather than showing the deployed models
for both.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor(dbt): squash the runtime's migrations into one
Ten migrations reshaping the same three tables is a history no installation
ever had. `dbt_node` gained `script_hash`, then `job_id`, then `ingested_at`,
with its primary key rebuilt twice; `graph_digest` was added by one migration
and dropped by the next after the digest moved to its own table. On a fresh
database all of that replays to arrive at a shape the schema can simply state,
and this feature has never shipped, so there is no upgrade path to preserve.
One migration now creates `dbt_node`, `dbt_edge`, `dbt_graph_snapshot`,
`dbt_run_state` and `dbt_run_progress` in their final shape, carrying forward
the rationale each of the replaced migrations recorded. The enum additions stay
in `add_dbt_lang`, since a value cannot be added and used in one transaction,
and the `materialized_partition` index stays separate because it belongs to a
table this feature did not introduce.
Verified by rebuilding: dropped the five tables, replayed from the single
migration, and confirmed the result is identical — same primary keys, the same
two composite `script` foreign keys, the same seven indexes. Every `sqlx::query!`
in the workspace then compiled against it, which checks each column's name, type
and nullability, and a deploy plus run on the rebuilt schema produced 8 nodes,
7 edges, a snapshot marker and 6 progress rows.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): authorize snapshot reads, bound the prune, give the marker a lifecycle
`dbt_job_id` is caller-supplied and selected straight from `dbt_graph_snapshot`,
which carries no RLS — so a caller who could see the script could read any run's
model set and relation paths, which a dynamic alias or schema can encode. Both
graph queries now require the job itself to be visible, in the authed
transaction, the same gate `raw_code` already applies to the script that
produced it.
The drift check compared against the deployed graph alone, which misses the way
back: a run at root B republishes the path-keyed `asset` usages at B, and
returning the profile to A then matches the deploy and skips the refresh,
leaving those usages at B while dbt builds A. It reads the most recent ingest
for the version instead — the one that last wrote them — ordered rather than an
arbitrary `LIMIT 1`.
The prune anti-joined every non-deployed node and edge with no age predicate, so
each run scanned the whole retained sidecar and concurrent runs duplicated it.
All three deletes share one age bound again, with the sentinel spelled as a
literal so the partial indexes apply — a bound parameter cannot be proven to
match the index predicate.
`dbt_graph_snapshot` was the one dbt table nothing in the script lifecycle
deleted: no `script` foreign key and absent from both `clear_dbt_manifest*`
sites. A marker outliving its rows is read as a snapshot with no nodes, and its
digest still answers the suppression check, so an identical run would write
nothing and then render an empty graph. It cascades like the rows now and both
clears take it.
Also: the preview cleared `exclude` rather than inheriting it, since previewing
a model the run excluded reached dbt as `--select m --exclude m`; and
`terminalize_running_relations` no longer claims to cover a killed worker, which
never reaches it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): quote profile names, record where usages were published, stop polling the graph
A profile name comes from the project's own `dbt_project.yml` and a target from
the descriptor, and both were interpolated into `profiles.yml` as bare YAML —
including as mapping keys. A name like `prod # hidden` truncates the mapping and
a newline opens a sibling key of the author's choosing. Both are rendered as
quoted scalars now, as are the BigQuery keyfile's keys, with a test that asserts
the document still parses to exactly the keys we wrote.
The drift check read the most recent ingest, which latches: a run that returns
to the deployed root re-ingests but stores no snapshot (its digest matches the
version's), so the moved run's rows stay newest and every later run pays an
extra parse and ingest. The publisher now records the root it published the
path-keyed usages at, which is the only thing that answers "where do the current
usages point" — the deploy's own root goes stale as soon as a run republishes.
The run page polled `/assets/graph` every two seconds alongside progress, so it
re-sent every node's SQL for the length of a run — hundreds of KB a tick on a
real project, for a graph that a dynamic descriptor re-ingests exactly once
before the build. It fetches once more shortly after mount and then polls
progress alone.
Node results carry `outcome` beside `status`. `status` stays dbt's own word, but
dbt owns that vocabulary — 1.x and 2.x differ on casing and `no-op` arrived in a
minor release — so publishing only it would force a break or a lie the first
time it moves. `outcome` is the stable half a downstream script branches on.
Also: the worker's dbt entry points are `pub(crate)`, since nothing outside the
crate calls them and they resolve secrets and launch processes; and the snapshot
gate records that it is RLS-only where `/jobs/run_progress` also honours a
share-link token, which is a gap in what a shared page shows rather than in what
it protects.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test(dbt): pin the graph storage invariants against a real database
Every defect review found in this area was DB-shaped — which row set a read
resolves to, which rows a clear takes, whether a snapshot exists at all — and
none of it is reachable from a unit test on a pure function. Four rounds
established these answers and nothing guarded them, which is why each round kept
finding another.
Six cases, on the harness the repo already uses for schema-shaped behaviour:
an identical run stores no snapshot and leaves no marker; a differing run keeps
its own while the version's is untouched; an empty run graph is still a snapshot
rather than an absent one; clearing one version leaves the others whole; the
path-wide clear takes the markers with it; and the sweep ages out run snapshots
while never touching a version's own graph.
`IngestedNode` gains `Default` so a test can state the two fields a case is
about rather than the eighteen it is not.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* perf(dbt): bound a script's stored graphs by deploy count
Run snapshots expire on a clock, but a VERSION's graph could not: its reader is
every finished run of that version, and a run page is as old as its job. So
nothing reclaimed them — a deploy graph went only when its `script` row was hard
deleted, which Windmill does not routinely do. A CI deploying on every commit
added a full model set with SQL bodies per commit, forever: roughly 200 KB a
deploy for a 200-model project, which is gigabytes a year across an instance.
Bounded by COUNT instead of age, since age is the thing that cannot be right
here. The newest 50 deploys per path keep their graph and older ones are
reclaimed, making growth `versions x models` rather than unbounded in time.
Generous on purpose: reaching the bound empties that version's run pages, so it
exists to stop unbounded growth rather than to be hit in normal use. Ordered by
the script's own `created_at`, so a late-finishing job re-ingesting an old
version cannot promote it.
Pinned by a test that deploys past the bound and asserts both halves: the count
holds, and the newest version is always among the survivors.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): let the run page know when its snapshot has landed
The one-shot graph refetch was wrong: a dynamic descriptor's ingest happens
before the build but after cloning, dependency install and parse, so a fixed
delay either fires too early — and the run page then shows the deployed models
for the whole run, never that run's own — or keeps re-sending the whole graph
for the length of it. Neither is a timing problem to tune; the page had no way
to tell "the snapshot is not written yet" from "this run has none".
`/assets/graph` answers that directly: `dbt_snapshot_job` is the job the dbt half
resolved from, when one was asked for and found. The page polls the graph until
that is its own job, and stops. A static descriptor never snapshots, so an
attempt cap ends it there rather than polling for the run's duration.
`dbt_node.relation_root` is gone. The drift check moved to the marker's
`published_relation_root`, which left the column written on every node and read
by nothing.
`outcome` was published as the stable half of the result contract, but the
in-tree consumer still ranked and coloured from dbt's own word — so the field
existed and nothing used it. `statusRank` takes it, `DbtRunResult` passes it, and
`classifyStatus` is documented as the fallback for results that predate it and
for the live event stream, which carries dbt's word alone.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* docs(dbt): record what a share-link viewer actually sees
The comment at the snapshot gate said the graph "falls back to the deployed
set", which is only the rarer half of it. A share link is an extra grant for a
logged-in user who lacks access to the job, so the usual case is no read on the
script either — and then the `live` CTE matches nothing and the whole dbt half
comes back empty. A blank Models panel over working progress rows, not a
fallback.
`docs/dbt-runtime.md` now carries the analysis a follow-up needs: that relaxing
this leaks nothing, because `v2_job_completed.result` already gives that viewer
every node's `unique_id` and `relation_name` — the graph's only incremental
exposure is `raw_code`, which is gated separately on seeing the script. And the
shape of the fix: `OptViewToken` and `validate_view_token` are self-contained
enough to move into `windmill-api-auth`, which `windmill-api-assets` already
depends on, after which the gate can honour a token for that job's snapshot
alone while `raw_code` stays where it is.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): keep model SQL behind the scripts:read scope, and unbreak CI
`/assets/graph` is authorized as `assets:read`, and RLS decides whether the
caller can see the script that produced a node — but RLS is not a scoped
token's grants. A token deliberately narrowed to `assets:read` could therefore
read model source and repository paths for scripts outside its `scripts:read`
paths. The same `build_scope_path_predicate` the macro endpoint already applies
now gates `raw_code` and `original_file_path`; the relation's shape is
unaffected, only its body is withheld.
`DbtAdapter::ALL` exists for the tests that must cover every adapter, so it is
dead in a release build and `-D warnings` failed all four backend checks on it.
It is `#[cfg(test)]` now.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): stop the graph poll at the ingest, and type `limit` in the schema
The poll's stop condition was a snapshot appearing, with a 40-attempt cap
behind it — so a STATIC descriptor, which never snapshots, took the cap every
time and re-fetched the whole graph forty times. That is most of what removing
the poll was meant to save, and static is the common case.
The ingest runs BEFORE the build, so the first model to report progress proves
it has already happened: a snapshot absent by then is one this run never
writes. Progress arriving is now the second exit, and the cap is only a
backstop for a run that reports none at all.
`limit` is declared `Typ::Int` but `dbt_arg_schema` had no integer arm, so the
run form and the generated clients saw an untyped default and offered no
numeric control for a value the worker clamps. Covered by the schema test.
`relationOutcome` still re-derived from dbt's word while `statusRank` had moved
to `outcome`; both read it now.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): make a retry prove its arguments still resolve the same
The saved arguments are the ones SUBMITTED, so a `$var:` in them is re-resolved
on retry. The identity did not cover the resolved values, so a variable that
changed between the failed run and the retry was accepted — and which graph the
retry then used depended on WHERE it landed: a worker holding the local
snapshot replays the saved manifest, while a database restore reparses with the
new value. Placement decided whether the resumed failures described the
relations being built.
The identity gains a digest of the resolved arguments, and is compared in two
halves because resolution happens between them. Project, warehouse, engine and
env are checkable up front; the arguments are not, because a retry request
carries only `dbt_command` and the ones to compare are the SAVED arguments after
this caller has re-resolved them. Comparing the whole string up front would have
refused every retry — which is what the obvious version of this fix does.
A row written before the digest existed has no last segment, and still restores
rather than being refused.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): keep pre-upgrade retries working, and stop losing a late snapshot
Splitting the identity on its last `|` read a pre-upgrade row's env digest as an
arguments digest and left only `<run_identity>` as the prefix, so every saved
failure on an upgraded instance became unretryable — a regression the previous
commit's own test missed by using an identity with no `|` in it at all, which is
not what an old one looks like. The digest is tagged (`|args=`) rather than
positional, and the test now uses a real pre-upgrade identity.
The graph poll gave up after a bounded number of tries, but provisioning and
`dbt deps` precede the ingest and can outlast that on a cold worker — and the
engines that emit no node events never produce the progress that ends it early.
A finished run now reloads the graph unconditionally, and the poll's own exit
issues one last load: progress proves the ingest happened, not that the previous
tick saw it, and dbt's compile window is wider than one tick.
A `dbt retry` restores the failed run's arguments inside the worker and they are
never written back to the retry job, whose own args are just
`{"dbt_command": "retry"}` — so previewing a row on a retry's page ran without
the vars the run used. The result now carries the invocation's arguments as
SUBMITTED, so a `$var:` stays a reference and no resolved value is published.
The deploy-count sweep ran instance-wide on every dbt run: `FROM script WHERE
language = 'dbt'` has no index to stand on, and both orphan deletes are the
complement of every partial index here. It is scoped to the running script's
`(workspace_id, path)` — which `index_script_on_path_created_at` serves — and
the orphan deletes only run when a marker actually went.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): hide dbt from module-less pickers, and stabilise the retry digests
`processLangs` feeds every language picker, including flow steps and app inline
scripts. Those are raw bodies with nowhere to carry a module bundle, and a dbt
script IS its bundle — so choosing dbt there produced a job that could only fail
once the worker looked for `dbt_project.yml`. Those two surfaces use
`processInlineLangs`, which drops the languages that need modules; a flow still
reaches dbt the way it reaches any script, by path to a deployed one.
`graph_digest` moved to SHA-256 because it is persisted and compared by a later
worker, and `DefaultHasher` is documented as unstable across Rust releases — but
the retry identity's own digests were left on it, and they are persisted in
`dbt_run_state.identity` for exactly the same comparison. A toolchain bump would
have refused every saved failure as a different project. All three go through
one `stable_digest`, length-prefixed so no split of the same bytes collides.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): enforce the tag scope on snapshot reads, reset state between runs
A tag scope is an orthogonal hard restriction: a token limited to some tags must
not read a job outside them however else it is authorized. The snapshot lookup
went through `v2_job` RLS alone, which knows nothing about tags, so such a token
could still retrieve a run's model set and its dynamic relation paths. The same
predicate `require_job_read_access` applies for the progress half of the page is
applied here — `get_scope_tags` is already public in `windmill-api-auth`, and it
is `None` for an unscoped caller, so a normal session pays nothing.
SvelteKit reuses the run graph between run ids, and `graphTries`, `polled` and
`raw` all describe the previous job: a spent retry count stopped the next run's
snapshot poll before it began, and stale progress coloured its models with
another run's statuses. All three reset when the graph key changes.
Also a wrapped string literal missing its backslashes, which put two ~22-space
runs in the middle of the retry-refusal message.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* docs(dbt): put each digest helper's rationale on its own function
Inserting `stable_digest` above `split_identity` split that function's doc, so
five lines describing where the identity divides ended up introducing the
hasher. Each is back on the function it describes, stated once.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix(dbt): read the run-pinned graph through the job, not the asset graph
Pinning the asset graph to one run is job-scoped data, but `dbt_job_id` sat on
`/assets/graph`, authorized as `assets:read`. The job-read contract —
`require_job_read_access` — is five parts that pull in opposite directions (tag
scope restrictive, `created_by` permissive, app-embed restrictive-overriding,
view token permissive, RLS underneath), so plain RLS is neither a stricter nor a
looser approximation of it. Restating the parts near the graph query kept leaving
one out: first the job check entirely, then the share-link asymmetry, then the
tag scope, and the app-embed restriction was still missing and failing open.
The helper cannot be called from `windmill-api-assets`, because `windmill-api`
depends on that crate. So move the read instead of the check: the run-pinned
graph is now `GET /w/{w_id}/jobs/dbt_graph/{id}` in `windmill-api`, on the same
gate as the `run_progress` it colours, and `/assets/graph` has no `dbt_job_id`
parameter at all.
- `asset_graph_for` takes the job as an argument from an already-authorized
caller; the route handler passes `None`.
- Extract the graph response into a `AssetGraph` component schema, now that two
paths return it.
- The run page fetches the job route when it has a job id.
* fix(dbt): charge assets:read on the run-graph route, trust the job gate in SQL
Round 13 findings on the route moved last commit.
The scope domain comes from the URL segment, so putting the read under `/jobs`
asked a scoped token for `jobs:read` alone while returning asset-graph data that
`/assets/graph` charges `assets:read` for. A token narrowed to polling run status
could read workspace topology, and the missing-job fallback made it cheaper still
— any random UUID skipped the job gate. Both scopes are now required: the job
gate reaches this run, `assets:read` reaches asset data at all.
The `chosen` CTE re-decided job visibility under plain RLS after the caller had
already passed `require_job_read_access`. It could only disagree, and did so
silently by falling back to the deployed graph — a share-link viewer entitled to
the run was shown a different run's model set. Dropped; the contract is that a
job reaching `asset_graph_for` is already authorized.
Also: the flow editor's `+` insert menu still offered dbt (the third
`processLangs` caller, missed when the other two moved to `processInlineLangs`),
the docs still described the deleted `dbt_job_id` parameter, and the new handler
had again been inserted between `get_run_progress`'s doc comment and its
function.
* fix(dbt): resolve a pinned run's version from the job row, not script RLS
Local codex review of the branch.
A share-link viewer is entitled to the run and usually has no grant on the
project — that is what the link works around. The graph's `live` CTE resolved the
version by selecting `script` inside the viewer's RLS transaction, so it answered
for their access to the project rather than for the run they were given: the
Models panel came back blank beneath working progress rows.
A pinned run now takes its path and hash from the job row the handler already
read after authorizing the job, so `live` does not consult `script` at all.
`raw_code` keeps its own `EXISTS` against `script`, so the model bodies stay
behind access to the project. Verified under RLS as an unprivileged role: the
shape query goes 0 rows -> 1, the `raw_code` gate stays 0.
Taking the version from the job also means a caller can no longer pin one
project's version while naming another's run, since `dbt_script_hash` is ignored
when a job is given.
The run page's graph fetch is a raw `fetch`, which bypasses the interceptor that
adds `X-View-Token` to generated-client calls, so a shared page was refused
before any of this mattered; it goes through `appendViewToken` now.
Also trims three comments to the AGENTS.md limit, dropping drafting-history
rationale that belongs in docs/dbt-runtime.md.
* fix(dbt): snapshot vars-overridden runs, carry the pinned version everywhere
Second local codex pass.
A `vars` run argument overrides the descriptor's, and vars drive `enabled`,
alias, schema, database and materialization — so such a run builds relations the
deployed graph does not describe. It now snapshots under its own job id, which
per-job keying makes safe: the version's graph stays for runs that did not
override. The old comment claimed gating on it would strand the override's graph
for the next default run, which was true only when the write went to the
deployed slot.
Two sites still read the caller's `dbt_script_hash` instead of the version
resolved from the job, so `/jobs/dbt_graph/{id}` without that redundant
parameter dropped models the run's version had and a later deploy removed.
The `dbt_snapshot_job` marker re-checked `v2_job` under RLS — the recheck the
graph query itself drops. A share-link viewer got the right graph and a null
marker, so the run page refetched it 40 times before giving up.
`wmill script preview` read the bundle with the generic `__mod` suffix and
script-module parsing, so previewing a `.dbt.yaml` omitted the project and failed
on the missing `dbt_project.yml`. It uses the same suffix and verbatim read as
deploy.
* fix(dbt): key retry state by principal, not by script path alone
`dbt_run_state` held one row per (workspace, script path), and a retry replaces
the caller's arguments with the saved ones. Anyone able to run the script could
therefore retry whoever ran it last, replaying that run's literal `select` and
`vars` against the warehouse and publishing them as their own job's
`invocation_args`. Running the script was already theirs to do; seeing another
principal's arguments was not.
`permissioned_as` joins the key, so a retry resumes only state written under the
same authority. Two runs sharing an authority can already act for each other, so
this is the boundary that matches the rest of the job model.
* test(dbt): pin what a caller without access to the project sees of its run
The share-link case had no regression guard, and every fix in this area touched
one of its two halves: the graph's SHAPE has to survive a caller who cannot read
the script, and the model SQL must not.
Two cases against a real database, calling `asset_graph_for` as a member with no
grant on the project's folder: pinned to a run, the models render and `raw_code`
is withheld; unpinned, the same caller sees nothing of it, so making the first
work did not relax the second.
Both assertions were checked by mutation — reverting the `live` bypass empties
the graph, and dropping the `raw_code` script gate leaks `select 1` — so neither
passes on the code it is meant to catch.
* fix(dbt): key the worker-local retry cache by principal too
Keying `dbt_run_state` by `permissioned_as` left its worker-local twin keyed by
workspace and script path alone, so the boundary held only where the database row
was consulted. An agent worker never reads that table — `Connection::Http` leaves
`latest_job` as `None` — so there the local cache was the whole boundary and it
had none: the next principal to retry the script on that worker restored the
previous one's `select` and `vars`.
Also records the sqlx `--all-targets` trap in the update-sqlx skill: it is needed
for queries inside tests, and in a CE checkout it aborts on `tests/otel.rs`
(EE-only `otel_ee`) after having already emptied the cache.
* fix(dbt): log a dropped retry-state save, correct the run-progress contract
Saving retry state is best-effort — losing it costs a retry, not the run that
just finished — but `.ok()` dropped the reason too. The only symptom was `dbt
retry` reporting nothing to resume, which reads as a bug in retry rather than a
failed write. Found by running a real failing build against a worker whose
binary predated the `permissioned_as` column: the insert violated NOT NULL and
said nothing.
The run-progress endpoint's OpenAPI description promised an empty list for a
caller who cannot see the job. It is refused instead; an empty list means the job
recorded nothing yet or is unknown here.
* fix(dbt): return the retry-state write failure the warning was added to report
`save_run_state` discarded the insert result, so the caller's warning could never
fire and a lost retry row stayed silent — the symptom being `dbt retry` finding
nothing on another worker.
The error is held rather than returned at once: the worker-local copy is what an
agent worker resumes from, so a failed insert must not cost that too. Every exit
after it surfaces it, including the ones that give up on the local save.
* fix(dbt): decide a retry's graph from its restored args, keep local state in step
Three from the seventh local review.
A retry submits only `dbt_command`, so the vars-override check ran against an
empty argument set and left `graph_is_per_run` false. The failed run's arguments
are restored afterwards, and those are what the retry builds with — an overridden
one wrote no snapshot for its own job and its page fell back to the deployed
graph, showing the wrong enabled models, aliases and schemas. The decision is
re-asked once the restore has happened.
A failed durable write no longer publishes the worker-local generation either.
`restore` accepts a local generation only when the database row names it, so
publishing one the database never recorded made this worker reject its own newest
state and resume the previous run's — its selection and vars, or "nothing to
retry" if that one had succeeded. An agent worker attempts no durable write, so
it keeps its local copy as before.
A rename that also converts away from dbt moved the old path's retry state onto
the new one, reinstating what the conversion had just cleared and leaving one
user's arguments and results under a path no dbt script occupies. It moves only
while the destination stays dbt, and clears the source otherwise.
* fix(dbt): drop retry state when a run produced none, let module pushes fail loudly
Three from the eighth local review.
A run that never wrote `run_results.json` — cancelled, timed out, or dead before
dbt got there — left the PREVIOUS run's state authoritative in both the database
and the local pointer, so a later `dbt retry` resumed that older invocation's
failed nodes. Producing nothing resumable now clears both copies, so neither can
answer for the other.
`wmill sync push` wrapped the descriptor lookup and its deployment in one
try/catch meant for a missing parent. Any API failure or invalid descriptor was
reported as "no parent found" and swallowed, so a module-only push exited zero
with the remote project unchanged. Only the lookup is tolerated now.
Also condenses a comment that narrated how earlier status comparisons behaved.
* fix(dbt): forget retry state on pre-build exits too, drop cascade claims
A dynamic run whose pre-build `dbt parse` or graph ingest fails returns before
the save that clears stale state, so the previous run stayed authoritative in
both the database and the local pointer and `dbt retry` resumed ITS failed nodes
— writing relations the run that just failed never touched. Both exits now
invalidate, through one helper shared with the no-artifact case.
Two frontend comments described dbt producer rows as driving cascade dispatch.
The executor returns before dispatch for every dbt job and deployment rejects
`table://` subscriptions, so they promised behaviour that cannot occur; they
describe the lineage and ownership that is actually retained.
* fix(dbt): let the database decide retry state where it is reachable
A SQL worker treated "no `dbt_run_state` row" as no opinion and accepted any
worker-local generation. But no row is the authoritative answer that the last
invocation left nothing resumable, so a local pointer that outlived it — an
unlink that failed, a process killed between the delete and the removal, a stale
cache — resurrected a replaced run and let `dbt retry` write relations it never
touched. An agent worker keeps accepting its local copy: it has no authority to
consult.
Invalidation failures are logged rather than dropped, since a silent one is
exactly what leaves the pointer behind.
* docs(dbt): record how to run an agent worker locally, keep archived graphs
Every step of standing one up fails as something else: a normal build cannot
start one at all, the server's routes need a separate feature, and all three
token mistakes surface as a bare 401 on the agent with the reason only in the
server log. Written down with the error each produces.
Also keeps a dbt script's graph when it is ARCHIVED rather than deleted. The
pinned read resolves versions through a CTE that already skips archived rows, so
clearing bought nothing and emptied the Models panel of every completed run of
the project. Deletion still clears it.
* feat(dbt): let an agent worker publish its graph, through one endpoint
An agent worker was refused any dbt script whose profile comes from a Windmill
resource — the common case — because it could neither read the stored relation
root to check for drift nor re-ingest a corrected one.
Those look like two needs but collapse into one: verification exists only to
decide whether the stored graph still describes reality, so a worker that can
PUBLISH never has to ask. It stores what it just parsed.
`POST /api/agent_workers/dbt_graph/{workspace_id}` is the whole addition. It
wraps the same `replace_dbt_manifest` the SQL path calls, so digest suppression,
the marker write and retention cannot drift between the two transports, and it
refuses a job the token's tags do not cover. `IngestedManifest`/`IngestedNode`
gain Deserialize to cross the wire.
Two guards go, both now false: the pre-build refusal, and the `Connection::Sql`
gate added earlier to stop a `vars` override grounding an agent run.
Live progress stays SQL-only — that is a per-model event stream, and routing it
through the API would mean a round trip per node.
* docs(dbt): warn that a differing cargo feature set swaps the shared binary
* docs(dbt): record the verified agent-worker behaviour and the tmpfs quota trap
An agent worker now runs a dbt job end to end, retries, and publishes its graph
— confirmed with a dynamic descriptor whose per-run snapshot came back through
the new endpoint. The doc said it was refused; that was true before the endpoint
existed.
Also `WINDMILL_DIR`: on a dev box the job dies with `Disk quota exceeded (os
error 122)` writing the project's files while `df` shows free space AND free
inodes, because /tmp is a tmpfs carrying a per-USER quota. Point the worker at a
real disk rather than trying to clean up beneath it.
* chore(dbt): pin the EE revision carrying the agent graph endpoint
* fix(dbt): bind the published graph to the job, break the completed-page poll loop
Five from the thirteenth local review.
The EE endpoint took `script_path` and `script_hash` from the payload and checked
only that the supplied job carried one of the agent's tags, so an agent holding
any matching-tag job could name another script and replace its graph. Both are
read from the verified queue row now and the request carries only the job id. A
raw preview has no version, so it no-ops rather than 422ing before dbt runs.
`IngestedManifest`/`IngestedNode` take `#[serde(default)]`: they were
serialize-only, and a field the serializer skips made the whole manifest
unparseable on the receiving side.
A completed run page fetched the graph forever — `load()` assigns `raw`, which
recomputes `settled`, which re-entered the same effect. The final fetch is keyed
to the job by a plain (non-reactive) variable, and `settled` is read untracked.
The pin now names a revision that compiles: the previous one still called
`authed.tags()`, a method that does not exist, because both that fix and the JSON
response landed after it was committed.
* fix(dbt): keep a run snapshot out of the script's deployed ownership
Everything `persist_ingest` writes after the manifest is keyed by PATH — one row
set per script, describing what is deployed there. A run snapshot was still
reaching it, so a one-off `vars` override republished that invocation's relations
as the script's ownership and the workspace graph stayed on the override's
schemas and aliases: an ordinary run of a static descriptor never ingests again
to correct it, so only a redeploy would. A snapshot now stops after recording its
own rows.
The row preview also selected a bare model name, which dbt resolves across every
installed package while `show` takes a single node — a project model sharing its
name with a package's was previewed wrongly or refused. It selects the
package-qualified FQN.
* fix(dbt): forget stale retry state when preparation itself fails
`prepare_project` runs before every path that could clear it, and it fails for
reasons unrelated to the saved run — a profile that stopped resolving, a
provision cancelled, packages that will not install. The invocation still left
nothing resumable, so the previous one must not stay authoritative: a repaired
project would otherwise let `dbt retry` rebuild an older run's selection and
write relations the latest invocation never reached. A retry is exempt, since it
is trying to use that state and failing to prepare says nothing about it.
Also corrects the runtime doc, which still described agent workers as unable to
run dynamic descriptors or Windmill-resolved profiles. They publish their graph
through the API now; what they do not get is live progress and a durable retry
row, and the doc says so.
* fix(dbt): spell the whole FQN for preview, bound retained retry generations
The FQN selector added last commit was `<package>.<name>`, but a dbt FQN is the
resource's path within its package and the matcher must consume the selector and
end on equal lengths — so it matched nothing for a model under `models/marts/`,
which is the layout most projects use and the one this repo's own complex fixture
has. The middle segments come from `original_file_path`, whose first element is
the resource root the FQN excludes. Without a path it falls back to the bare
name: ambiguous across packages, but a selector dbt resolves rather than rejects.
Tested on a nested model, which is the input that separates the three spellings.
Superseded retry generations were removed only when a later run published one,
and never inside the hour-long grace period — so a burst left a manifest and a
results copy per run with nothing afterwards to collect them. At most four now
sit in the grace window, oldest evicted first.
* fix(dbt): scope preview state to the run, seed the project on a language switch
Previews are keyed by `unique_id`, which is the same string for the same model in
every run, and the run-change effect reset only the graph and progress. Opening a
second run of one project therefore showed the previous run's rows immediately,
and `runPreview` treated them as cached and refused to fetch. A generation
counter also drops a preview that resolves after navigation, which the reset
alone cannot catch.
The dbt project was seeded only by the empty-script bootstrap, but dbt is in the
ordinary language picker: reaching it by switching a draft produced a script with
no `dbt_project.yml`, which the runtime refuses to deploy or run. Both entry
points seed now, and neither touches modules that already exist.
* chore(dbt): cache the agent graph endpoint's query for the EE offline build
* fix(dbt): publish the graph a moved profile built
A run snapshot stopped before everything `persist_ingest` keys by PATH, which is
right for a one-off `vars` override and wrong for the other two reasons a run
re-ingests. `graph_is_per_run` was one bool for all of them, and the profile
drift check both sets it and reads back what the publisher recorded: a profile
moved A->B was detected by every run forever, each paying a `dbt parse` for a
snapshot nobody reads while the asset rows went on naming schema A.
The reason is carried now (`GraphRefresh`), and it decides both writes. Drift is
the version's own move, so it rewrites the VERSION's graph and republishes the
ownership that ends the drift; a dynamic descriptor snapshots under its job id
and still publishes; anything the CALLER scoped — an overridden `vars`, a
narrowed `select` — snapshots and publishes nothing, so one invocation's subset
can neither stand as what the script owns nor drop the models it left out from
the version's graph. Where they meet the caller wins, and the next ordinary run
settles the drift.
A restore also rebuilt `run_results.json` by copying the generation directory a
second time, so a burst of saves pruning it mid-restore left `dbt retry` with
nothing to resume and a job that reported success. It is written from the bytes
the restore already read; a manifest that went the same way falls back to the
parse a database restore pays anyway, and a generation that vanished before
either read falls back to the database's row for that same run instead of
reporting there is nothing to retry.
* fix(dbt): select a row preview by package, not by file path
The preview built dbt's FQN by dropping one segment of `original_file_path`,
which assumes the model root is `models/`. A project setting
`model-paths: ["src/models"]` turned `src/models/marts/orders.sql` into
`pkg.models.marts.orders`, and dbt's matcher — equal lengths, compared from the
front — resolves that to nothing: the preview came back empty for every model in
the project.
It selects `<name>,package:<pkg>` instead. The comma is dbt's intersection
operator, so this names the node by its own name and the package it belongs to,
which is what the FQN was reaching for and needs no knowledge of the resource
root. Verified on dbt-core 1.12, dbt-core 2.0.0-alpha.5 and fusion
2.0.0-preview.202, including a package shipping a model whose name the root
project also uses.
* fix(dbt): refuse a lockfile version that is not one, keep a named selector
Two things a preview reaches that a deploy does not vouch for.
A raw preview submits its own `lock`, so `engine_version` arrives from the
caller and was interpolated straight into the engine cache path — `../..` in it
made the download, extraction and rename land anywhere the worker can write,
and provisioning runs on the host rather than inside the dbt jail. Both it and
`adapter_version` (a pip requirement) are now accepted only as a plain version
token.
`effective_selector` also read any submitted `select`/`exclude` as an override
of the descriptor's named selector. The generated run form posts a default back
for every field the caller left untouched, and a selector descriptor's `select`
default is `[]` — so pressing Test, saving a schedule or firing a webhook built
the WHOLE project instead of `--selector nightly`. An override is now one that
DIFFERS from the descriptor's own value; a run that wants the whole project
despite the selector asks with `["*"]`.
* fix(dbt): let a moved profile settle, from the runs that actually happen
Two ways the drift check could never come to rest, both verified against a real
run of a real project on a normal worker.
`add_caller_args` read any submitted `select`/`exclude` as a caller's narrowing.
The generated run form posts a default back for every field left untouched, so
every run from the UI, a schedule, a webhook or a flow step carried them and was
marked caller-scoped: with the profile moved A->B, each one stored its models
under its own job id and left the workspace graph — and the root the check reads
back — at A. Since no UI run omits the field, the "an ordinary run settles it"
escape hatch was unreachable. Both this and `effective_selector` now ask one
question, `selection_is_overridden`: DIFFERENT from the descriptor's, not merely
submitted.
The root was also recorded beside the path-keyed publication rather than beside
the graph it describes, so a version that cannot claim the path — an older one
run by hash, a deploy overtaken by a newer one — rewrote its graph at the moved
root and recorded nothing. Its next run then compared against a root that was
absent or two moves stale and skipped the refresh its own run page needed. It is
written wherever the deployed row's graph is.
Verified end to end: same UI-shaped arguments before and after, the moved
profile now republishes (asset rows and version graph both move to the new
schema), a second run detects nothing and re-parses nothing, and moving the
profile back settles it again.
`prune_dbt_run_graphs` also ran from runs alone, while a deploy writes a whole
node set of its own, `raw_code` per model included: a project redeployed on
every push by CI and run nightly kept one full graph per push until the next
run, and one deployed but never run kept them for good.
* fix(dbt): drop a self-dependent effect in the run graph
`previewGen` was `$state` written by the effect that also reads it, three lines
under a `finalLoadFor` that is a plain `let` for exactly that reason. Nothing
reactive reads it — the only reads are inside `runPreview`, a plain async
function — so it becomes a plain `let` too.
* fix(dbt): pin a retry to the engine versions it resolved
`run_identity` carried the engine KIND but not the version it resolved, nor the
dbt-core 1.x adapter's. Redeploy an unchanged project after a release and it
locks a newer dbt or adapter while the saved `run_results.json` still passes the
check, so `dbt retry` feeds one version's artifacts to another — the exact
reproducibility the lockfile exists to hold. Both resolved versions are in the
identity now; a real failure and retry still resumes.
Also drops three comments that outlived what they describe: two said `[]`
clears a descriptor's selector, which `selection_is_overridden` reversed, and
one pointed at an agent-worker guard that no longer exists — the agent path
reaches the ingest deliberately and publishes through the API.
* fix(dbt): discard a run graph the page has already navigated away from
The component is reused across runs, so a slow `/jobs/dbt_graph` or progress
response could land after the reset and put the previous run's models, statuses
and failure state on the current run's page, where nothing would fetch again to
correct it. Every response is now checked against the generation it was
requested under — the counter the preview path already used, renamed for what
it means.
The graph poll also backs off. Neither of its stops is reachable for a whole
class of runs — `dbt_snapshot_job` never matches a static descriptor, and
`polled` stays empty for the engines that emit no node events — so an ordinary
run walked to the cap, re-sending every model's SQL 40 times in two minutes.
* fix(dbt): forget the previous run when the durable save fails, keep quoting
`save_run_state` returns the database error when its upsert fails, which leaves
run N-1's row and local generation in place: same project, same arguments, so a
`dbt retry` matches them and resumes an older attempt's failed nodes against
this checkout — the outcome the no-results branch twelve lines above calls
`invalidate_run_state` to prevent, reached by another door. It now goes through
the same call. Best effort, since the delete goes to the database that just
refused a write, but the local pointer is what a retry landing back here reads.
The run page also rejoined a relation's parts after `splitRelation` stripped
their quotes, so the one name the button exists to paste —
`"wh"."analytics.v2"."Order Items"` — was copied as something no client
resolves. It copies `relation_name` verbatim.
And a source on a finished run was called another project's: the check that
guards against two projects claiming one relation asks whether this run executed
the node, and a run executes no sources — they appear in no `run_results.json`.
Nothing materializes a source, so that warning could never be true of one.
Docs: the `vars`-override paragraph still said such a run does not refresh the
graph, which the table above it contradicts — it refreshes under its job id and
publishes nothing.
* fix(dbt): keep the asset rows and the version's models describing one graph
The workspace graph takes an asset's relations from the path-keyed `asset` rows
and its models, SQL, tests and lineage from the version's `dbt_node`/`dbt_edge`.
A dynamic descriptor published the former while storing the latter under its own
job id, so a placeholder that moved an alias or a schema left the current graph
with assets no model stands behind — nothing dbt contributes to them survives.
Ownership is published exactly when the VERSION's graph was written now, which
is the only state in which the two agree. Two cases are settled elsewhere by
design: an override's relations are a one-off, and a dynamic descriptor at a
moved profile keeps the deploy's ownership until a redeploy — its runs each show
their own models and it re-parses regardless, so the undetected drift costs it
nothing it was not already paying.
An agent worker has no durable row, so its local `current` pointer is the whole
of what a retry reads — and every local publication failure returned success
with the PREVIOUS run's pointer still in place. Where a row exists that is
harmless (`restore` takes a local generation only when the row names it), so the
abandonment is scoped to the agent case.
A failed `dbt show` also cleared the retry state: the preparation-failure exempts
`retry` but not a read-only command, and the run page's row preview is exactly
that, run as the principal the state is keyed by — so a preview that could not
provision took the retry away from the run being looked at.
Frontend: the run-change reset left `loading` and `failed` behind, so the gap
before the next run's answer rendered "no models in the asset graph" — a claim
about the descriptor — over a project that is fine. And three derivations argued
from "the graph is the current deploy", which the pinned endpoint made untrue;
each is still needed, for the version-graph rewrite and retention reasons now
written down.
* fix(cli): let --skip-scripts cover a script's module files
The module shortcut in `elementsToMap` maps the file and `continue`s before
every skip filter, and a module is deployed as part of its parent script — so
`wmill sync push --skip-scripts` still pushed the script whenever one of its
modules changed, and pull still overwrote them locally. Harmless while a module
was a rare helper file; every file of a dbt project is one of these now.
* docs(dbt): a dynamic descriptor's ownership stays the deploy's
* fix(dbt): read the run out of a failure whose message has braces of its own
`parseDbtRun` anchored on the FIRST `{` in the error message and parsed
everything after it. The worker appends the structured result after the error
text, and dbt's errors carry braces — a Jinja template, the compiled SQL, an
adapter's own JSON — so the failures most worth reading were the ones whose
summary and per-node outcomes the run page dropped. Every brace is tried now,
bounded, and the first that parses as a run wins.
Pins the EE revision that gives the agent publish endpoint the deleted-version
guard the SQL path takes: deletion is soft, the foreign key still accepts graph
rows, and the pinned graph query serves non-live versions, so an agent finishing
during a delete put a deleted project's model SQL back on screen. The query is
byte-identical to `persist_ingest`'s, so the offline cache already covers it —
verified with a full-EE `SQLX_OFFLINE=true` check.
* fix(dbt): seed a project when a modular draft switches to dbt
`seedDbtProject` returned whenever the draft carried any module at all, so a
modular script holding a `helper.ts` reached dbt with none of what dbt needs:
the project view is read-only, and the worker refuses a bundle without
`dbt_project.yml`, so that draft could neither run nor deploy. Keyed on the
project file now, and the seed goes in under whatever is already there — the
previous language's helpers are inert to dbt and the user's to remove.
Also records this runtime's schema in `backend/summarized_schema.txt`: the
`table` asset kind, the `dbt` script language, the five dbt tables and the
`materialization_status` enum the progress table uses.
* docs(dbt): move the pipeline-membership rationale out of the deploy path
* fix(dbt): gate a pinned run's model SQL on the version it belongs to
The `EXISTS` against `script` is the only thing standing between a share-link
viewer and the project's source, and it matched the workspace and path alone.
`extra_perms` is a grant on a ROW: archive a version that granted someone
access, recreate the path with narrower permissions, and that stale grant
satisfied the probe while the query returned the NEW version's `raw_code`. Both
probes name the hash now. The regression test drives exactly that shape and
fails without it, returning `select 2` to a caller granted only on the archived
version.
* fix(dbt): keep a delimiter an identifier escaped by doubling
Every dialect these relations come from escapes its own delimiter by doubling
it, and both split functions closed the quoted section on the first half and
reopened on the second: `"schema"."a""b"` came out as `a.b`. The manifest keeps
the real spelling, so the run wrote its per-model status and row counts under an
asset path no graph node has — the node simply never moves, which is the failure
mode this splitter exists to prevent.
Fixed in the worker and in its frontend mirror, which have to agree, with a case
per delimiter on both sides.
* fix(dbt): key retry state by the caller, not only by the principal it runs as
An `on_behalf_of` script executes every caller's job as its owner, so
`permissioned_as` names one principal for all of them and the retry state — the
durable row and the worker-local generation both — collapsed onto a single
entry. After one caller's run failed, the next could submit `dbt_command: retry`
and resume it: their arguments replayed against the warehouse, and handed back
through `invocation_args`. Nothing else separated them, and on an agent worker
the local directory is the whole boundary.
`created_by` joins the key in both places. For an ordinary script it changes
nothing — `permissioned_as` is already that caller — and a run that was itself
superseded was never resumable anyway.
Includes the offline cache for the four changed queries and the three the
pinned-graph regression test added last commit, which had none: `prepare`
without `--all-targets` does not compile test targets, so CI's
`SQLX_OFFLINE=true ... --all-targets` would have failed on them.
* fix(dbt): compare the schema too when reporting a relation that moved
`relationDrift` compared the leaf name alone, and the move it exists to report —
a profile repointed at another schema, which a later run then writes into the
version's graph — leaves every model's name exactly where it was. So the one
case that reliably produces a graph naming relations this run did not write was
the one case the notice stayed silent for.
The schema segment joins the comparison, qualified against qualified: an
unqualified one means the target's own database, which the relation names
anyway, so comparing that would report a move on every node.
* fix(dbt): bound the retry state now that it is keyed per caller
Keying by `created_by` fixed one caller resuming another's run and created a
growth problem doing it: a shared `on_behalf_of` script kept one row and one
worker directory for everyone who had ever run it, and the generation prune only
bounds files INSIDE a directory.
Three bounds, none of them new machinery. A run with nothing failed or skipped
saves nothing — `dbt retry` builds from those nodes alone, so that state could
only ever be refused — while still clearing what the previous run left, since
its failures are no longer what last happened here. The rows expire on the same
30-day clock as a run snapshot, swept per path by the prune every dbt job
already spawns. And the worker-local directories are swept there too, by the age
of the pointer a save rewrites, because their digest names neither the script
nor the caller.
* docs(dbt): the retry state is worker-affine only on an agent worker
* fix(auth): only the server may set a token label that names a user
`create_token_internal` wrote `NewToken.label` verbatim, and the auth layer reads
some labels as an IDENTITY: `username_override_from_label` maps
`ephemeral-script-end-user-<name>` to exactly `<name>`, which then becomes
`created_by` on every job that token pushes. The label is free-form request
input, so any member could mint a token that speaks as somebody else — the shape
`require_job_read_access` already works around when it refuses to trust
`username_override` and falls back to an RLS probe, and the one that made dbt's
retry-state key (`created_by`) forgeable for an `on_behalf_of` script.
The labels are refused where request input enters: the member-facing
`tokens/create`, and `impersonate`, which names its subject in
`impersonate_email` and has no business renaming the caller too. The legitimate
producers are unaffected — a job's own token comes from `create_token_for_owner`
in the worker, and native triggers and app-embed tokens build their labels
themselves rather than accepting one.
`Ephemeral lsp token` stays allowed: its override is the fixed sentinel `lsp`,
not a name the caller chose, and the editor mints exactly that label through this
endpoint for its language server. The test pins the two lists together, so an arm
added to `username_override_from_label` that lets a label choose a name fails
until it is reserved too.
* Revert "fix(auth): only the server may set a token label that names a user"
This reverts commit
|
||
|
Ruben Fiszel
|
3b95c947d4 |
test(wac): pin the failure record with one corpus both SDKs read (#10385)
* test(wac): pin the failure record with one corpus both SDKs read Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(wac): add the behaviour matrix that verified the failure record Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(wac): record how to exercise an unreleased SDK change Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(wac): guard the whole extra pair, not just its value Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(wac): never rehash an untrusted extra key Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(wac): walk only a real __dict__ when collecting extra Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(wac): name the divergence the corpus cannot pin Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(wac): state the extra-encoding constraints in four lines Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
3b95a2d096 |
feat: reusable AI agent steps with rigid linking and edit/fork (#9825)
* feat: reusable AI agent steps with hybrid linking and evals Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: make linked AI agents rigid (read-only) with unlink-to-fork Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: show inherited agent config read-only on linked step Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: edit/update a saved agent in place via upsert Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: bind linked AI agent tool inputs to host flow context Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: rebind linked AI agent tool inputs via graph tool nodes Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: linked AI agent tool nodes, step test, and read-only card Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: remove ai_agent resource type migration, sync from hub instead Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: remove AI agent eval suite and run endpoint, defer to later Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: unwire eval routes, types and UI (completes eval removal) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: update reusable AI agents guide for eval removal and tool rebinding Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: regenerate system prompts for AIAgent agent/tool_inputs schema Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: strip brain transforms on link, avoid dirtying flow on tool open Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: flow-local test form and linked-agent marker in read-only graph Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: store linked tool overrides as diff from resource base Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: resolve linked agent tools in read-only viewer with fallback Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: use operating workspace, block non-static provider, warn on unbound tool inputs Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: resolve linked parent's tools from resource for nested agent tool lookup Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: scope linked-agent tools by flow path, thread workspace to path check and embedded viewer Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: strip flow-context tool inputs on agent save, drop unbound-inputs warning Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: persist agent edit mode across tool selection, show linked tool code read-only Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: show linked agent resource path in node definition panel Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor: edit linked tool inputs in step panel, make tool nodes display-only Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor: wire step-panel tool bindings (completes display-only pivot) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: single scroll for linked card, agent path as node label, drop fill-inputs in tool cards Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * style: align linked-agent UI with design tokens and components Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: separate linked tool select target from module id to unbreak agent clicks Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@aanthropic.com> * fix: save agent tool inputs verbatim, host flows override via tool_inputs Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: scope agent edit state by flow path, require linked-tools scope at init Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: block saving an agent whose static provider is incomplete Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: type errors in agent tool bindings and save drawer input Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: key agent edit state by workspace, resync tool bindings on external changes Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: include workspace in linked-tools scope and tool schema fingerprint Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: remove unused workspace prop from FlowModuleSchemaMap Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor: drop linked-agent placeholder tool node, path label suffices Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: workspace-qualified resource links, guard stale tool schema loads Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: keep flow tool overrides out of the agent on edit, fold only on unlink Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: fold preserved tool overrides into the step on edit cancel Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: refuse overwriting non-agent resources on save, show memory kind on linked card Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: consume picker value, invalidate edit state on undo/reinit, cap nested agent tools Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: guard in-flight edit fork against restores, migrate edit state on rename Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor: validate agent edit state by fork identity instead of path keys Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: key agent edit entries by fork marker alone, immune to editor nesting Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: keep agent edit state across structural graph edits and flow renames Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B6kq9PYqNdc5q7ubidBYAs * fix: centralize agent edit reanchor, guard in-flight saves, seed rename scope from flow path Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B6kq9PYqNdc5q7ubidBYAs * fix: ancestry-keyed edit reanchor and doc-scope sweep for republished linked tools Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B6kq9PYqNdc5q7ubidBYAs * fix: guard stale linked-tool fetches and resolve while-loop nested linked agents Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B6kq9PYqNdc5q7ubidBYAs * fix: drop empty tool override entries on revert and correct stale viewer comment Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B6kq9PYqNdc5q7ubidBYAs * docs: drop stale eval mention from the linked-agent comment Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: deploy linked agent resource, guard viewer fetches, align tools schema Address review findings on the reusable-agent branch: - Cross-workspace deploy never collected a linked step's `agent` resource, so the deployed flow failed at runtime unless the agent already existed there. - The read-only viewer published resolved tools without the generation guard flowState uses, letting a superseded link's tools win a race. Share one guarded publisher (`publishLinkedAgentTools`) between both call sites. - `tools` was still required in the OpenFlow AiAgent schema while the deserializer defaults it, rejecting hand-authored linked steps; make it optional and narrow the call sites. - Overlay `tool_inputs` in the non-linked branch too, so a flow persisted while a step sits in "Editing" mode still binds tools to this flow. - Cap the linked-tools store's scope map; nothing evicted it before. - Drop the orphaned `.sqlx` entry left by the eval removal, regenerate the copilot OpenFlow schema, and fix the generator's nested-`z.record` arity. - Move `refreshFlowStateStore` out of `agentEditStore` into its own module. - Document that linked agents' tool scripts are outside the lock pipeline. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore: regenerate system prompts for optional AIAgent tools Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: follow saved-agent deps on deploy, accept the linked shape in the schema Round-18 review findings: - Deploying a linked flow queued only the outer ai_agent resource. Follow `$res:` refs inside a resource value (every UI-saved agent has a provider resource) and the agent's own tools, which reference scripts, flows, MCP resources and nested linked agents by bare path. - The AiAgent input_transforms schema still required provider/output_type, so it rejected the very shape linking persists (brain transforms stripped, flow-local inputs kept). Only user_message is always present. - dfs traversed `value.tools` unconditionally through a cast, which throws on a linked module that omits it now that the field is optional. - Trim the flow-refresh invariant comment to the 4-line limit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: recurse into inline nested agent tools on deploy, require provider when unlinked Round-19 review findings: - The deploy walk only inspected a saved agent's top-level tools, so an inline nested agent tool's own scripts, flows and MCP resources were skipped. Recurse into it; a linked one is still queued as a resource instead. - Normalize a `$res:`-prefixed MCP tool resource_path like other refs. - Dropping provider/output_type from the schema's required list also let a standalone providerless agent validate, which deploys clean and then fails on every run. The constraint can't go in the schema: an `anyOf` makes AiAgent a union, which breaks the FlowModuleValue discriminated union it belongs to (verified: zod throws "Invalid discriminated union option"). Enforce it in validateFlowModules instead, next to the other cross-module checks, via a shared collectProviderlessAgentIds. - Correct the deploy paragraph in the docs: provider resources are traversed now. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: follow linked tool_inputs overrides on deploy, untrack vitest artifact Round-20 review findings: - A linked step's `tool_inputs` override replaces the resource tool's default at runtime, so a static `$res:`/`$var:` override is the dependency the flow actually uses. The deploy walk queued only the saved agent, leaving runs in an empty target workspace to fail on the missing override target. It also never scanned an aiagent module's own input_transforms, since the scan was gated to script/rawscript/flow. - Extract the pure walkers to deployDependencies.ts and cover them: three rounds have each found a further gap in this one function. - Untrack a vitest cache artifact committed by accident, and ignore a repo-root node_modules/ (only per-package paths were listed). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: collect inline agent provider and tool deps, correct tool_inputs docs Round-21 review findings: - An inline agent's provider credential sits inside an object-valued static transform, so the top-level string check missed it and such a flow deployed without its provider. Walk transform values instead of string-matching them. - An inline agent's own tools were only partly reachable: getAllModules drops MCP and websearch tools, so their resources were never queued. A standalone agent module now recurses through agentResourceDependencies, and the module's own input_transforms are scanned inside aiAgentModuleDependencies so one function owns the whole step rather than splitting it with the caller. - `tool_inputs` was documented as empty/absent for non-linked steps, which contradicts the runtime applying it when `agent` is unset so a flow persisted mid-Edit keeps its bindings. Describe that case in both the Rust doc and the OpenFlow description. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: keep linked steps brain-free on load, gate stale agent fetches, log linked tools Round-22 review findings: - loadSchemaFromModule filled every AI agent schema key with a placeholder transform, re-adding provider/memory to a linked step that deliberately carries none — persisted on the next save and rejected by the generated Copilot schema. Fill only the flow-local keys when the step is linked. - The linked-resource fetch was neither aborted nor tagged, so switching a step from agent A to B could publish A's tools under B and show A's brain next to B's link. Tag each result with the (workspace, path) it was fetched for and drop the ones that no longer match. - "Test this step" passed no tools for a linked agent, and the log viewer drops tool_call entries it cannot resolve to a definition, so the agent's invocations vanished from the log. Pass the resolved resource tools. - Correct the cancel-edit comment: the runtime does apply tool_inputs on an unlinked step, and folding is what leaves nothing for it to overlay. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: pin the edit session across saves, resolve linked tools in the run viewer Round-23 review findings: - Cancel stays enabled while a save awaits its requests, and it keeps the `tools` array identity, so the old guard passed and the completing save relinked the step and cleared the edits Cancel had just kept. It also accepted any replacement edit marker. Pin the path being saved and require the marker to still hold it, which still tolerates a content-preserving refresh re-anchoring the marker onto a clone. - Resolve linked agents' tools in the run/status viewer too: it reads module.value.tools straight from raw_flow, which is empty for a linked step, so AIAgentLogViewer dropped every tool_call it could not match and the graph drew the agent with no tool nodes. Same gap the previous commit closed for "Test this step" only. - Drop the overlay call-site comment: it claimed resource defaults are discarded and unmatched keys ignored, while overlay_tool_inputs preserves defaults and inserts new keys, as its own test asserts. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: scope linked tools without the trigger-node path, keep the standalone save guard Round-24 review findings, both regressions from the previous commit: - Passing `path` to the run viewer's graph also switched on its Trigger node (`triggerNode ? path : undefined`), which reads a TriggerContext that /run/[...run] does not provide — the page threw "Cannot read properties of undefined (reading 'triggersCount')". Give the graph a separate `linkedToolsPath` for the tools bucket so the two stay independent. - The rewritten save guard tracked only the edit path, so a plain "Save as agent" no longer noticed the step being replaced mid-request (undo, session sync): the replacement has no edit path either, so the stale completion relinked it and stripped its brain. Keep the array-identity check when there is no edit session, and use path re-anchoring only when there is one. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: keep recorded tool calls in run history, send tool_inputs from step previews Round-25 review findings: - The agent log viewer dropped any recorded tool_call whose definition it could not find among the supplied tools, so renaming or removing a tool — or losing read access to a linked agent's resource — erased calls that had actually run. Render the recorded call labelled by its function name; its args, logs and result come from the child job, not the definition. - "Test this step" sent tool_inputs only for a linked step, but a step forked for editing has no `agent` while still carrying the flow's bindings, which the runtime overlays. The preview ran resource-authored defaults instead of the bindings under test. Send them from both branches. - Polling a running flow replaces `job` every tick, so the run viewer re-read every linked agent's resource each time. Key the fetch on the set of linked steps instead. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: never discard edits made during a save, isolate the run viewer tools bucket Round-26 review findings: - The agent editor stays live while a save is in flight, so edits made after the snapshot were not in the resource yet linking stripped them from the step too, losing them outright. Compare the config against the snapshot on completion and, if it moved, leave the step alone and tell the user to save again. - The run viewer published into the editor's `${ws}:${flow path}` bucket, so opening an older run in the preview pane could flip the edited flow's tool nodes to that run's agent. Key it by job instead. - Drop the now-unreachable undefined filter in the agent log viewer. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: claim the linked-tools generation on direct publishes and clears Round-27 review findings: - The step editor wrote resolved tools (and cleared them on unlink) straight into the store, leaving the fetch generation untouched. An older in-flight load for the previous agent then still passed its own check and overwrote them, so the graph and binding editor could show agent A while the step links to B. Claim the generation before those writes. - Correct two comments that still described unmatched tool calls as dropped; they are kept and labelled by their recorded name. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: retain the loaded linked agent, rebuild run logs when tools resolve Round-28 review findings: - Rejecting a superseded resource response left the card with nothing: a late reply for a previous agent replaces `linkedResource.current` and no refetch follows, so the linked step lost its brain, tools and provider warning until remount. Retain the last response that matched the current link instead. - The agent log viewer built its module list on mount only, so a linked agent's asynchronously resolved tools never replaced the placeholders, and switching between completed runs reused the first snapshot. Rebuild on a value key — callers rebuild the agentJob object each render, so tracking its identity would reload in a loop. - Refresh a linked-tools scope's recency when it is read, not only when it is published: a run viewer opens one bucket per nested job, which could otherwise evict the bucket a still-displayed run is using. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: supersede stale log reloads and stale tools on a link change Round-29 review findings, both on the reloads added last round: - Every prop change starts another loadToolCalls, and it awaits child-job requests before writing the shared view, so a slower reload for a previous run could restore its logs and tool states over the run now selected — or replace newly resolved definitions with an earlier empty-tools snapshot. Build the states locally and let only the newest load publish, including the parent's index-keyed job cache. - While a newly linked agent resolves, the previous agent's tools stayed in the store, so its bindings were editable against a step already linked elsewhere, and a failed load left them indefinitely. Clear them once the link moves away from what this component published; tools resolved at flow load are untouched, so selecting a step still doesn't flicker. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: resolve a run's linked agents in the run's own workspace Round-30 review finding: the run viewer fetched linked agent resources with the navigation workspace, but session and fork previews render it with `workspaceId` pointing elsewhere. Those runs resolved nothing — or an unrelated resource sharing the path — losing tool nodes and log definitions. Prefer the explicit override, then the job's own workspace. The store scope stays keyed on `workspace` so it still matches what FlowGraphV2 reads; the job id in the key already makes the bucket unique. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: refetch a run viewer's linked tools if its scope is evicted Round-31 review nit: the viewer publishes one scope per mounted nested job, hidden ones included, so a loop with many loaded iterations can push a displayed scope past the store's cap. Nothing refetched it afterwards — the set of linked steps had not changed — leaving the run without tool nodes or log definitions. Track the store and republish when the bucket is gone; publishing always writes a key, so this settles instead of looping. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: retain in-use linked-tool scopes instead of refetching evicted ones Round-32 review findings. Republishing an evicted scope settles for one scope but not against the cap: with more than 32 mounted nested jobs holding linked agents, restoring one necessarily evicts another, and that mutation reran every viewer's effect — an endless round of resource requests. Hold a scope for as long as a viewer is mounted and skip retained scopes when evicting, so buckets in use are never dropped and nothing has to refetch. The cap yields to correctness when everything mounted is in use. Dropping the publish key also restores refetching when the fetch workspace changes for an otherwise unchanged job and link. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: guard non-static brain edits during save, retain every displayed scope Round-33 review findings: - The in-flight edit guard compared the saved config, which holds only static brain values. A computed system prompt, memory or temperature changed while the save was awaiting the API therefore compared equal, and linking stripped it with no warning. Compare what linking actually discards — every brain transform and the tools — leaving the flow-local inputs free to change. - Retaining run-viewer scopes made them fill the cap, and eviction then picked any unretained scope, including the editor bucket a user is looking at, with nothing to refetch it. Retain the scope each graph draws from for as long as it is mounted, so every displayed bucket is protected. - A failed agent job has no parseable action list; the loader returned early and left the previously selected step's tool tree under the new header. Clear the view instead. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: resolve only flow modules in viewer scans, prune scopes on release Round-34 review findings: - Both viewer scans used the default dfs, which descends into agent tools, and published each linked agent under its bare id. Tool ids imported from a resource are not flow-global, so a nested linked agent sharing an id with a top-level step superseded that step's fetch and showed its tools instead. Scan flow modules only — the graph resolves the store per module node. - Scopes skipped while retained were never reconsidered, so closing views left the store over its cap for the tab's life. Prune on release too. - Correct two comments that still argued the premises the retain mechanism and the read-recency policy replaced. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: don't report success when a save left the step unlinked Round-35 review nits: - persist warns that changes made during the save are not in the resource and leaves the step alone, but both callers then toasted success unconditionally, burying the only actionable message. Report whether the step was linked. - Condense the tool_inputs invariant to the four-line limit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: seed the published link at mount, keep run history for toolless agents Round-36 review findings: - `publishedFor` started unset, but initFlowState has already published for the step's link by then. A link change landing before this component's own request therefore skipped the clear, leaving the previous agent's tools under the new link — indefinitely if the new one fails. Seed it from the link at mount. - A standalone agent that omits `tools` kept `undefined` here, and the gate downstream then hid the AI message and tool-call history behind the generic result view. Default to an empty list like the other consumers. - A save that lands after the step was replaced writes the resource but leaves the step alone; say so instead of closing the drawer with no outcome. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: qualify nested agent tool store keys, keep an empty tools identity stable Round-37 review findings: - The step editor keyed the linked-tools store by the bare module id for nested agent tools too. Those ids come from a resource and are not flow-global, so a nested linked agent sharing an id with a top-level step read that step's tools — then overwrote them once its own fetch landed. Qualify the key by the parent agent, as the edit store already does; flow modules keep the bare id the graph looks up. - The `tools` binding handed the editor a fresh [] on every read when the module omits the field — a shape this PR made valid — so the save guard's identity check never matched and such a step could never link. Read through one shared empty array instead. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: accept the first tool on an agent module that omits tools Round-38 review nit: the graph's tool insert required an existing `tools` array, so a module authored without the field — valid since `tools` became optional — swallowed the insert while still pushing history and dispatching a change. Create the array on first use. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: don't evict a scope on the write that created it, and cover the store Round-39 review findings: - A rename removed the retained old key from the order but the new one is not retained until readers re-run, so eviction deleted the fresh bucket immediately. Reorder without evicting; the next publish or release enforces the cap, by which point the new key is held. - Writing the test for that surfaced the same shape in touchScope: it evicts right after appending, so once every older scope is retained the scope just published was the only eligible victim and was dropped at once. Exclude the scope being written. Add the store's first test: retention, eviction past the cap, pruning on release, and the rename handoff — four rounds landed fixes here with nothing pinning the behaviour. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: re-resolve linked agents when a wholesale edit changes the links Round-40 review findings: - Undo/redo, YAML apply, AI apply and session restore swap a step's `agent` without re-running initFlowState, and the step editor only watches the step it is mounted on — so an unselected step kept showing, and binding against, the previous agent's tools. Re-resolve from the editor whenever the set of links changes. - Document that linked resolution is live rather than pinned: an edit landing mid-run affects steps that have not started, and a nested agent tool looks its definition up by id when its own job starts, so it can run a changed definition. Pinning would mean carrying the resolved definition into the child job instead of its id; inline agents are unaffected because their tools are snapshotted with the flow value. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: per-module empty tools identity, invalidate tools when a link is replaced Both findings are over-corrections in the two preceding commits: - The shared empty-tools array made identity stable, but stable everywhere: a wholesale edit that keeps the module id reuses the component, so when both the old and the replacement module omit tools the save guard saw no change and could link and clear the replacement. Hand out one empty array per module value, which a replacement always renews. - The editor's link watcher resolved the replacement agent without dropping the previous one's tools first, so a step selected before the fetch landed still showed agent A under link B — and the freshly mounted editor seeds itself from B, so it could not tell. Clear the entry when the link for a module changes, seeding the map from the graph so the first run doesn't refetch what initFlowState just resolved. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: reserve graph space for linked tools, re-resolve only changed links Round-41 review nits: - The layout reservation read the module's own `tools`, which is empty for a linked agent, so its display-only tool nodes were drawn over the node above in read-only viewers. Count the resolved tools for a linked step. - The editor's link watcher refetched every linked agent on each run. Resolve only modules whose link actually changed, and skip the pass entirely on a rename, where the scope sweep has already carried the buckets over. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: protect a renamed scope until it is retained, drop the phantom tool row Round-42 review nits: - Readers release the old scope before retaining the new one, so a migrated bucket is unretained in between and, over the cap with everything else held, was the only thing eviction could take. Protect a just-migrated scope until a reader retains it, and cover that release/retain order in the store test. - The layout reserved an add-tool row for linked agents, which have no add-tool node, leaving dead vertical space. Match computeAIToolNodes. - Re-resolving links no longer short-circuits on a rename: comparing each module still costs nothing when only the path changed, and a restore that renames and relinks in one tick now gets both. - Hoist the duplicated linked-tools lookup in the graph's store update. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: kill a scope's in-flight fetches before migrating it Round-43 review finding: fetch generations are keyed by (scope, module), so a resolution still running against the pre-rename scope keeps a valid generation there. It publishes into the old bucket after the rename, and the doc-scope sweep — which gives the source precedence — carries it forward over a link resolved since under the new scope, leaving the graph and binding editor on the previous agent's tool ids with nothing to refetch them. Invalidate the source scope's fetches before each migration, and pin the behaviour: the new test fails without the invalidation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: re-resolve links a scope sweep cancelled, and only sweep a real bucket Round-44 review findings, both on the previous commit: - Invalidating the source scope killed fetches that were perfectly current — a link still loading when the rename landed — and nothing restarted them, because the watcher already records that link. Resolve again, in the destination, every link the migration left without tools. - The doc-scope sweep ran on every store version bump, so during a draft refresh the first completed fetch cancelled the others mid-flight. Skip the sweep entirely when the source scope holds nothing. - Condense a six-line invariant to the four-line limit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: split rename from doc sweep, hide brain fields of nested linked agents Round-45 review findings: - Two reviewers disagreed about invalidating a scope whose bucket is empty, because the two callers differ. A rename is a cut-off: every fetch still running against the old scope is stale whether or not anything resolved there, so it always invalidates. The doc-scope sweep has no cut-off — those fetches belong to the refresh in progress — so it still waits until that scope holds something. - Recording the swept links as published undid the rename+relink fix: a restore that renames and swaps a link in one tick would keep the previous agent's tools with nothing to refetch them. Leave that comparison to the watcher, which compares links rather than presence. - A nested agent that is itself linked was offered the whole agent schema in the tool bindings, but the runtime overlays only its flow-local inputs, so the rest were collected and dropped. Show what actually applies. - Condense the hybrid-linking comment to the constraint. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: don't resolve a shared agent's tool defaults when loading it Round-46 review finding: the whole agent resource was interpolated before tool_inputs was overlaid, so each tool's default `$res:`/`$var:` resolved first. A host flow overriding a default that points at the author's resource still had to resolve that resource, and an unused tool whose default is unreadable in the consumer's permission context failed the agent outright — defeating the point of sharing an agent across contexts. Read the resource raw, overlay the host's overrides, and interpolate only the brain; each tool resolves its effective inputs when it executes. The nested tool lookup reads raw too, since it only needs definitions. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: interpolate the brain before overlaying caller inputs Round-47 review findings, all on the previous commit: - user_message and user_attachments were inserted before interpolation, so they went through it a second time: a user message of `$WM_TOKEN` expanded to the job token and was sent to the model provider. Interpolate the resource first, then overlay the already-resolved flow-local inputs. - The relink watcher skips tool nodes, so a linked agent nested as a tool kept the previous agent's entry through undo, YAML/AI apply or a session restore, and the step editor seeds itself from the new link and cannot tell. Emit the ancestry-qualified key for those too. - Correct the guide, which still named the interpolation path this branch replaced, and condense two invariants to the four-line limit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: deploy $jsonvar deps, key run logs by tool identity, seed only top links Round-48 review findings: - The deploy walkers recognised `$res:` and `$var:` but not `$jsonvar:`, which the worker resolves too, so a secret referenced that way by an agent brain, a saved tool default or a host override never reached the target workspace. - The run log rebuilt only when a tool's name or the tool count changed, so a refreshed resource that altered a tool's path, code or id behind the same name kept showing the old definition. Key on the array identity instead: the store swaps it exactly when the contents differ. - Nested linked agents were seeded as already published, but initFlowState resolves only top-level links, so their tools never loaded until their editor was opened. Seed what initFlowState actually publishes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: let the watcher's fetch survive the step editor's stale-clear Round-49 review nits: - On a relink the step editor claimed the fetch generation before clearing the previous agent's tools, which discarded the watcher's already-running fetch for the new link. The tool nodes then only appeared if the step stayed selected until the editor's own refetch landed. Clear without claiming: the watcher superseded the old fetch when the link changed, so nothing stale can return. Unlink still claims, since no watcher fetch covers it. - Condense the store's opening invariant to the four-line limit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs: condense the stale-clear invariant Round-50 review nit. Also records why the branch deliberately doesn't claim a fetch generation: a reviewer asked for the opposite this round, but writing `agent` re-runs the editor's watcher, which supersedes the old fetch and starts one for the new link — claiming here would discard it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: guard Edit/Unlink by step identity, not just the link path Round-51 review finding: forkFromResource compared only the agent path after its fetch, so a module replaced mid-request while keeping the same link passed the check — the stale continuation then wrote the fetched brain and tools into the replacement and unlinked it. Compare the step's own `tools` array too, which is one instance per module value and so identifies the step. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix: report an Edit or Unlink abandoned because the step changed Round-52 non-blocking note: forkFromResource returns undefined when the step was replaced mid-request, and both callers treated that as do-nothing, so the click looked ignored. Say what happened, as the save path already does. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: hugocasa <hugo@casademont.ch> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@aanthropic.com> |
||
 Diego Imbert
|
7fb8a2e390 |
fix(parsers): keep s3 asset path suffix verbatim to preserve storage distinction (#10241)
* fix(parsers): keep s3 asset path suffix verbatim to preserve storage distinction Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01An2pTqSmqJd2XwnagvX4kM * package json * fix(pipelines): preserve named storage in generated TS/Python S3 URIs The TS/Python templates emitted `s3:///${s3Key(path)}`, stripping the leading slash and pinning the URI to default storage. For a named-storage asset path (`secondary/key`) that produced `s3:///secondary/key`, which resolves to the default storage with key `secondary/key`, dropping the named-storage dependency and reading/writing the wrong object. Emit the path verbatim after `s3://` (matching the DuckDB template) so a named-storage input/output keeps its storage; identical to the previous output for default-storage paths. Removes the now-unused `s3Key` helper. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(cli): align bun.lock parser versions with frontend The PR bumped windmill-parser-wasm-asset (1.749.0→1.753.0) and windmill-parser-wasm-regex (1.692.0→1.764.0) in package.json and the npm package-lock.json for both cli and frontend, but cli/bun.lock was left pinned to the old versions. Sync it so the CLI's wasm asset parser (used by localGraph inference) matches the frontend and deploy-time parser. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Ruben Fiszel <ruben@windmill.dev> |
||
|
Ruben Fiszel
|
fd51d40f12 | feat(pipelines): catalog declared measures and dimensions (#10190) | ||
|
hugocasa
|
4e63ca2cd4 |
gate PR ready on clean agent-driven review rounds (#10157)
* feat(ci): gate PR ready on clean review rounds driven from draft Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ci): robust review-round wait loop, require codex evidence for marker skip Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ci): require pre-marker codex evidence, fail open on marker fetch errors Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
hugocasa
|
51d8db6602 |
feat: automatic git-to-windmill sync (polling, webhooks, in-app PRs + checks) (#9552)
* docs: add design doc for automatic git-to-windmill pull sync
* docs: add migration plan and implementation phases to git-sync pull design
* feat(git-sync): add auto_pull settings schema and pull enqueue primitive
Adds AutoPullSettings/AutoPullMode/AutoPullStatus on GitRepositorySettings
(workspace_settings.git_sync JSONB), the GIT_SYNC_PULL_SCRIPT_PATH constant,
and should_pull/effective_poll_interval_s helpers with unit tests. Exports the
EE enqueue_git_pull_job primitive. Foundation for repo→Windmill auto-pull.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): poll repos and auto-pull new commits into the workspace
Phase 1 of automatic repo → Windmill sync. A monitor task (EE-licensed,
single-replica via advisory lock) git ls-remotes each auto-pull-enabled
repository ~every minute and enqueues a pull when the tracked branch moves,
reusing the {workspace_id}:git_sync concurrency key so pulls serialize with
in-flight push commits.
- windmill-store: background (no-authed) resolver get_git_repo_head_for_autopull
that resolves the repo resource (incl. $var: refs) and ls-remotes; GitHub-App
repos are skipped here and will sync via webhooks (phase 2).
- monitor.rs: poll/reconcile/persist with optimistic sha advance and failure
status; targeted jsonb update so concurrent settings edits aren't clobbered.
- edit_git_sync_repository: preserve server-owned auto_pull state on UI save.
- openapi: AutoPullSettings/AutoPullMode/AutoPullStatus + auto_pull field.
- frontend: per-repo "Automatically deploy changes from Git" toggle with last
sync status; demote the GitHub Actions link to an advanced CI option.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): wire webhook lifecycle + receiver; share reconcile logic
OSS side of phase 2 auto-pull webhooks:
- edit_git_sync_repository creates/removes the repo webhook on save (EE-gated,
best-effort → falls back to polling).
- monitor poller now delegates to the shared windmill_git_sync reconcile/persist
helpers (also used by the webhook receiver), removing duplicated logic.
- export the shared reconcile/persist/failure helpers; bump EE ref.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(git-sync): bump EE ref for phase 3 in-app PR creation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): show webhook vs polling status on the auto-pull toggle
When a repo has an active webhook (auto_pull.webhook_id set), the status line
reads "instant via webhook"; otherwise it reads the ~1-minute polling cadence.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(git-sync): post PR diff check on dry-run completion (phase 4)
Worker completion hook in process_completed_job: when a DeploymentCallback job
carrying the __git_sync_pr_check marker finishes, parse the dry-run SyncResponse
and patch the GitHub check run with the diff summary (success/neutral/failure).
Export enqueue_git_pull_dry_run; bump EE ref.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(git-sync): bump EE ref (drop unused GHES webhook_secret)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* revert(git-sync): defer phase 4 PR diff checks (OSS side)
Remove the worker completion hook that posted the PR check run, drop the
enqueue_git_pull_dry_run re-export and the orphaned sqlx cache, bump EE ref.
Phases 1-3 (polling, webhooks, in-app PR creation) are unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Revert "revert(git-sync): defer phase 4 PR diff checks (OSS side)"
This reverts commit
|
||
|
Ruben Fiszel
|
abbab4d423 |
security(docker): apt-get upgrade base OS in all runtime base stages (#10114)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
43044c2e28 |
feat(pipelines): wm_partition macro for grain-agnostic partition filters (#9950)
* wip: partial work before earlyoom-recovery relaunch
* fix(pipelines): scaffold the strftime {partition} filter idiom (frontend-only)
The DuckDB materialize scaffold and the AI pipeline prompt now teach the
grain-agnostic `WHERE strftime(<ts_col>, '<fmt>') = {partition}` filter instead
of the naive `= TIMESTAMP {partition}` cast. `{partition}` substitutes to the
partition IDENTITY string (`2026-07-05T23`, `2026-W27`, `2026-07`), which is not
a valid DuckDB TIMESTAMP literal for any non-daily grain — so the naive form
raises a `Conversion Error` for hourly/weekly/monthly (only daily parses).
Adds a frontend unit test asserting the hourly scaffold emits the strftime
idiom (`%Y-%m-%dT%H`) for every grain and never scaffolds the naive TIMESTAMP
cast as executable SQL.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(pipelines): scope strftime partition idiom to time grains
Review nit: `dynamic` partitioning's identity is a caller-supplied key, not a
timestamp, so `strftime` doesn't apply. Scope the scaffold + AI prompt claim to
time grains and add a `dynamic` example that filters on the user's own key.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(pipelines): wm_partition macro for grain-agnostic partition filters
The materialize runtime now injects a `wm_partition(ts)` temp macro as the first
setup statement of a time-partitioned script, so filtering the source to the
active slice is one grain-agnostic line — `WHERE wm_partition(<ts_col>) =
{partition}` — instead of a hand-written `strftime` format the author must keep
in lockstep with the resolver, or the `= TIMESTAMP {partition}` cast that only
parses for daily and Conversion-Errors for hourly/weekly/monthly.
The macro's format comes from `PartitionKind::default_time_format` in
windmill-parser, the same source the EE resolver reads to stamp the `{partition}`
identity, so the two can't drift. `dynamic` partitions get no macro (their
identity is a caller-supplied key → `WHERE <key_col> = {partition}`).
Replaces the earlier 9-line strftime comment block in the scaffold with the
single macro line; AI pipeline prompt and design doc updated to match.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(pipelines): verify wm_partition strftime parity vs chrono through real DuckDB
Runs the bundled DuckDB engine in-memory and asserts strftime renders every
grain format (daily/hourly/weekly `%G-W%V`/monthly) byte-for-byte identically to
chrono — the engine the resolver uses to stamp the `{partition}` identity —
across ISO-week year boundaries (2027-01-01 → 2026-W53 etc.). Also proves the
injected `wm_partition` macro buckets the whole slice and that the naive
`TIMESTAMP '<weekly|monthly identity>'` cast Conversion-Errors.
Closes the one cross-engine assumption the pure-Rust/frontend tests couldn't
reach (flagged by CI review for weekly ISO-week rendering).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: update ee-repo-ref to 0de2412ff0734b11e12ba378c9bcc373ff9ae800
This commit updates the EE repository reference after PR #649 was merged in windmill-ee-private.
Previous ee-repo-ref: ad6c6685689d7741058e7d2c9ecbe95d982e6268
New ee-repo-ref: 0de2412ff0734b11e12ba378c9bcc373ff9ae800
Automated by sync-ee-ref workflow.
* fix(pipelines): classify CREATE TEMP MACRO as a DuckDB prepare-path setup statement
The FFI prepare/diagnostics pass only EXECUTES statements recognized by
is_setup_statement (ATTACH/USE/INSTALL/…); everything else is merely prepared.
`CREATE [OR REPLACE] TEMP MACRO` wasn't recognized, so on a `-- prepare` run of a
partitioned materialize the injected `wm_partition` macro was never created on
the connection, and the later generated `CREATE TABLE … SELECT … WHERE
wm_partition(...)` failed to bind ("function does not exist"). The same latent
gap affected the workspace-macro splicer, which injects TEMP MACRO blocks too.
Classify CREATE [OR REPLACE] TEMP|TEMPORARY MACRO as setup so it's executed
before dependent blocks and excluded from the PrepareQueryResult count
(persistent CREATE MACRO stays a user statement). Adds a prepare-path test that
fails without the fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
|
||
|
Ruben Fiszel
|
b13113964a |
fix(pipelines): canonicalize S3 asset keys so SDK writes and DuckDB reads connect (#9939)
* fix(pipelines): canonicalize S3 asset keys so SDK writes and DuckDB reads connect
The SDK object forms — TS `writeS3File({s3:"exports/x"})` and Python
`write_s3_file(S3Object(s3="exports/x"))` — resolve to the URI `s3:///exports/x`
(empty default storage), whose parsed asset path was `/exports/x` (leading
slash). DuckDB `read_csv('s3://exports/x')` and the `// on s3://exports/x`
trigger form yielded the bare `exports/x`. The same object thus produced two
asset identities, so a DuckDB consumer never connected to a TS/Python producer
in the pipeline graph.
`parse_asset_syntax` (shared by the native backend parsers and the wasm parser
that drives `frontend/src/lib/infer.ts` and the CLI `localGraph`) now strips a
single leading slash from S3 paths, so `s3:///key`, `s3://storage/key`, DuckDB
`s3://…`, and `// on` all canonicalize to one key. Both deploy-time inference
and editor/CLI inference agree, and the producer's write edge and the
consumer's read/trigger edge share a node.
Only one leading slash is stripped, so `s3:///` triple-slash default-storage
keys collapse to the bare key while Hive-partition keys
(`s3://bucket/y=2024/f.parquet`) and explicit-storage `s3://storage/key` paths
are untouched. Non-S3 asset kinds (res://, ducklake://, …) keep their paths
verbatim.
Note: existing deployed pipelines that recorded `/key` paths need a redeploy to
pick up the canonical `key`; the fix is forward-consistent for anything parsed
after this change.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(pipelines): mark S3 asset-path normalization (item 6) resolved
The open-issues list still flagged the SDK-form leading-slash vs bare-URI
no-slash mismatch as "Still open", contradicting the fix in this PR. Mark it
resolved to match the updated Language-coverage prose.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs+test(pipelines): disclose S3 explicit-storage vs default-storage-nested-key aliasing
Collapsing to one canonical key means `s3://storage/key` (explicit storage) and
`s3:///storage/key` (default-storage nested key) now alias to the same node
`storage/key`, though they name different objects. Low-probability (needs a
storage config named to match a default-storage prefix) and inherent to a
best-effort lineage graph that doesn't split the first segment as a storage
name, but previously undisclosed. Document the tradeoff and pin the intended
aliasing with a test so it's intentional, not a latent surprise.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(pipelines): mirror S3 leading-slash strip in frontend live-preview parser
The pipeline graph live preview parses `// on` annotations client-side via the
hand-written `parsePipelineAnnotations.ts` (a TS mirror of the Rust annotation
scanner), NOT the wasm parser. Its `parseAssetSyntax` still returned the raw
suffix, so `// on s3:///exports/x` yielded `/exports/x` while the deploy-time
and wasm parsers now canonicalize to `exports/x`. `resolveGraph` synthesizes
trigger edges from that path, so the browser preview could still render
disconnected `/exports/x` and `exports/x` nodes for the exact triple-slash case
this PR fixes at deploy time.
Mirror the S3-only single-leading-slash strip in the TS parser and extend the
shared parity fixture corpus (run by both the Rust and TS parity suites) with
the triple-slash trigger case, so Rust/TS drift on this is now caught.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(pipelines): seed slashless S3 template asset paths to match canonical key
`autoOutputAsset` seeded new S3 template outputs with a leading slash
(`/pipelines/…`), which the old parser required to match `s3:///key` writes.
This PR made `parse_asset_syntax` strip that slash, so the seeded draft asset
(stored as `outputAssets`, used by `resolveGraph` for inactive-draft node
identity) no longer matched the body-inferred identity `pipelines/…` — the live
preview could render a duplicate `/pipelines/…` node and a phantom post-deploy
drift warning.
Seed the canonical slashless key instead, and switch the DuckDB body's S3 URIs
from `s3://${path}` to `s3:///${path}` so the generated runtime URI stays the
triple-slash default-storage form byte-for-byte (the SDK sites already build
`s3:///` + bare key). Add a pure-logic parity test asserting, for every
language and S3 output kind, that the seeded asset path is slashless and that
every S3 URI the generated body emits is triple-slash and canonicalizes back to
that seeded path.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(pipelines): canonicalize S3 keys in CLI + frontend bounded-cascade resolvers
Two more hand-written S3-URI sites returned the raw suffix, so `s3:///exports/x`
stayed `/exports/x` while native/wasm parsers now canonicalize to `exports/x`:
- `cli/src/commands/pipeline/localGraph.ts` — the no-wasm fallback `// on`
scanner (go/bash/ruby). A fallback consumer's `// on s3:///x` would not
connect to a wasm-inferred `x` producer in `wmill pipeline show/run --local`.
- `boundedCascade.ts` `assetUriToNodeId` (duplicated in the CLI and the frontend
AssetGraph engines, kept in sync) — `--to s3:///exports/x` / a cascade bound
token would not resolve against the canonical graph node `s3object:exports/x`.
`resolveToken` delegates here, so it is covered too.
Mirror the S3-only single-leading-slash strip in all three, and add `s3:///`
tests to the CLI local-graph fallback suite and both bounded-cascade suites
(explicit-storage and Hive-partition keys asserted untouched).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(pipelines): phrase S3 template test comment as a current invariant
Describe the slashless-seed requirement as the invariant it is, not as change
history, per the AGENTS.md "describe the code as it is" rule.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(pipelines): strip all leading slashes from S3 keys so trigger refs round-trip
`parse_asset_syntax` stripped only one leading slash, so `S3Object(s3="/x")` —
which resolves to the quad-slash URI `s3:////x` — parsed to path `/x`. But
`trigger_spec_to_row` rebuilds a stored trigger ref as `s3://<path>` =
`s3:///x`, which `parse_asset_trigger_ref` then parses back to `x`. The
producer recorded `/x` while its consumer trigger resolved to `x` → a broken
edge. The same asymmetry affects every `s3://`+path reconstruction site
(backend refs, frontend `assetUri`, page refs) whenever a path starts with `/`.
Strip ALL leading slashes so a canonical S3 path never starts with `/`; naive
`prefix + path` reconstruction then round-trips everywhere. Applied uniformly
across all six S3-URI sites (Rust `parse_asset_syntax`, the TS live-preview
parser, template `s3Key`, and the frontend+CLI `assetUriToNodeId` and CLI
fallback scanner). The pathological leading-slash key collapses to the bare key
— acceptable for a best-effort lineage graph that never split storage anyway.
Tests: a windmill-common round-trip test (parse → trigger_spec_to_row →
parse_asset_trigger_ref) over every URI form incl. the quad-slash case; a
`s3:////x` shared parity fixture (Rust + TS); and quad-slash assertions in the
Rust parser test and both bounded-cascade suites.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(pipelines): align S3 template parity helper with strip-all canonicalization
The template seed/body parity test's `canonicalS3Key` helper (and its comment)
still stripped a single leading slash, so it no longer mirrored the parser it
claims to pin. Strip all leading slashes to match `parse_asset_syntax` and the
frontend/CLI mirrors.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|
Ruben Fiszel
|
46be39dfb7 |
fix(pipelines): order data_test relationships refs before the tested script in a cascade (#9934)
* fix(pipelines): order data_test relationships refs before the tested script in a cascade Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): key custom-test reads by (usage_kind, path) to avoid same-path flow collisions Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
52ce805f61 |
fix(pipelines): dedup guard for keyed merge + deploy-time SCD2 validation (#9936)
Two correctness/validation improvements to managed materialization: 1. A keyed `merge` (`key=<col>`) is delete-by-key + insert-all and does NOT deduplicate its source, so two incoming rows sharing a key both landed under that key — silently breaking the one-row-per-key contract. Codegen now emits an in-transaction guard (same `error(...)` shape as the schema -drift guard) that fails the run when the SELECT returns more than one row for a non-NULL key, naming the key. Authors deduplicate in the SELECT or switch to `append`. NULL keys are exempt, matching the delete's `IN (...)` scope. 2. The two SCD2 misconfigurations that were only caught at run time — `history` without `key=`, and `history` + `// partitioned` — now fail fast at deploy via a shared `MaterializeSpec::validate`, called from `create_script_internal`. The DuckDB executor keeps the same check as a safety net for preview/test runs that never deploy (shared message, no drift). Adds unit tests for the merge guard codegen and for `validate` (all four cases), and updates docs/ducklake-materialization.md and docs/pipelines-vs-dbt.md. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
39eb9de1bc |
feat(pipelines): fork data environments for ducklake materialization (dev data) (#9915)
* feat(pipelines): fork-scoped ducklake namespaces with read-defer to parent Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(pipelines): fork graph indicator + fork ducklake namespace cleanup endpoint Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(pipelines): fork_views-keyed view transition, fork lineage clone, design doc Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): review hardening - fork DATA_PATH last-wins, registry cache TTL, defer tests Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(pipelines): per-lake isolated/shared choice at fork creation Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): chain-aware defer discovery + per-location fork namespace registry Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): lake-scoped fork schemas, catalog identity in registry, chain-aware graph chips Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): cleanup deletes fork data from the registered storage identity Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): collapse fork data-path segment to one component (slash-safe ids) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): per-catalog ancestor checks, ancestor extra_args passthrough, test compile fix Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): invalidate fork ancestor-chain cache on lineage mutations Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): sweep descendant ancestor-chain caches on delete/reparent Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): run fork ducklake cleanup inline in delete_workspace Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): resolve fork cleanup credentials pre-commit, destroy post-commit Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): shared dev-workspace authz gate for namespace drop, invalidatable registration cache, segment-boundary delete filter - extract require_prod_admin_for_dev_workspace, used by both delete_workspace and drop_forked_ducklake_namespaces so the gates cannot drift - key FORK_DUCKLAKE_REGISTERED per workspace and invalidate it in cleanup_fork_ducklake_namespaces so a same-id fork recreated within the TTL re-registers its namespaces - filter listed object locations to the segment boundary before deletion Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): keep orphaned wm-fork-* workspaces ducklake-isolated parent_workspace_id is ON DELETE SET NULL, so a fork can outlive its parent with an empty ancestor chain while its cloned config still points at the shared lake. Key the isolation gate on the wm-fork- prefix as well as the chain (mirroring workspace_is_fork): orphaned forks get the write redirect, registration and cleanup with zero ancestors (no defer), and keep their 'fork' graph chips. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): attach orphaned wm-fork-* ancestors at their fork namespace Chain position alone classified the last ancestor as a root, but an orphaned wm-fork-* ancestor (its own parent deleted, SET NULL) ends the chain the same way while its data lives in its fork namespace — its descendants' defer views bound the dead root's lake instead. Key the root-vs-fork decision on the wm-fork- prefix too, matching the resolution gate. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): never inherit shared lake opt-out; durable cleanup ledger for failed fork deletions - fork creation strips cloned fork_behavior stamps before applying the request's shared_ducklakes list: sharing is a per-creation choice, a fork of a shared fork defaults back to isolated - fork_ducklake_namespace loses its ON DELETE CASCADE FK: rows are the durable cleanup ledger and outlive the workspace when physical cleanup fails post-commit; fork creation retries leftover rows for the reused id and refuses to create while a metadata schema still cannot be dropped (data-file leftovers alone are inert once the schema is gone and are swept by the next successful same-prefix cleanup) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): make orphaned-namespace cleanup retries independent of deleted fork resources - ledger rows gain a schema_dropped phase flag: set when the schema drop succeeded but data cleanup failed, so later retries skip the schema phase and need no catalog credentials at all; registration resets it on re-attach (ON CONFLICT DO UPDATE) since attaching recreates the schema - retry-path $res: resolution falls back to the workspace being forked (the deleted fork's resources were clones of a parent's); live paths (delete_workspace prepare, drop endpoint) pass no fallback Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): fork tables from failed-after-commit runs stay fork-owned in defer and graph A failed materialization must not disguise a physically existing fork table as deferred: CREATE VIEW IF NOT EXISTS silently yields to the table, so reads hit fork data while the graph claims parent defer. - record_mat upsert preserves the last committed snapshot_id on failure - defer discovery and graph chips treat fork rows with a committed snapshot as fork-owned even when status is failed - inspect_fork_catalog also lists live fork tables (same round trip) and the defer list is filtered against them — covers rows recorded before this fix and tables created by raw SQL - drop stale FK-cascade wording in the design doc and sidebar comment Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(pipelines): fork-mode ducklake settings — per-lake isolated/shared chips + banner, fork_behavior round-trip The workspace-settings ducklake editor had no fork awareness: no reminder of each lake's isolated/shared choice and no warning about what edits mean in a fork. It also rebuilt each lake explicitly on save, silently dropping fork_behavior — any settings save in a shared fork flipped the lake back to isolated. - fork detection mirrors the backend gate (parent link or wm-fork- prefix) - info banner explaining isolated vs shared semantics in a fork - per-lake chip (emerald 'isolated' / amber 'shared with parent') with tooltips, matching the pipeline graph chip colors - fork_behavior added to DucklakeSettingsType and preserved through convertDucklakeSettingsToBackend Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
d4b4374de8 |
feat(pipelines): capture violating-row samples for data tests (#9919)
* feat(pipelines): capture violating-row samples for data tests Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): byte-accurate sample cap and leaf-level payload sanitize Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump ee-repo-ref to WAP guard probe adaptation Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: WAP failures are counts-only — samples exist only on commit-then-test Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: qualify where sample row data appears — job result and failed-job log line Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: error handlers receive the full result incl. samples, like any failed job Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: update ee-repo-ref to 80d309edebb899e36a3bdcdf4ea73c4db070534d This commit updates the EE repository reference after PR #646 was merged in windmill-ee-private. Previous ee-repo-ref: 16e916bf11f26381920560b55771fce693e668c6 New ee-repo-ref: 80d309edebb899e36a3bdcdf4ea73c4db070534d Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
Ruben Fiszel
|
5ad2de91a2 |
feat(sdk): enforce s3:// URIs for string S3 params + ingestion (EL) docs (#9912)
* feat(pipelines): ingestion (EL) templates + docs Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): review nits — draft collision guard, template-mode selection reset, invariant test Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipelines): lead the insert menu with ingestion templates Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(pipelines): ingestion story as docs-only — drop editor template UI The insert-menu template section mixed two selection grammars in one popover and confused more than it helped. The three E2E-verified example pipelines now live verbatim in docs/pipeline-ingestion.md; the Python bare-string S3 key fix in pipelineTemplates.ts stays. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(sdk): bare string S3 keys in py/ts clients + asset parsers A plain string passed where an S3Object is expected is now a bare key in the default storage — previously the py client silently degraded it to s3="" (auto-generated key) and both asset parsers canonicalized it without the leading slash, splitting lineage. parseS3Object moves to s3Types.ts so it is unit-testable without the generated services. The pipeline template fix from the earlier commit is superseded (bare strings are the supported spelling again); docs examples flipped to bare keys. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(sdk): enforce s3:// URIs for string S3Object params Bare strings now raise/throw with a hint pointing at the s3:///<key> spelling instead of being treated as keys (previous commit) or silently degrading to an empty key (original behavior). One string spelling everywhere: SDK calls, // on annotations, and DuckDB SQL all use s3:///<key>. TS regains the s3://-template-literal type; the asset parsers record no asset for a bare string (the call can only error); templates emit the URI form. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(pipelines): move ingestion (EL) guide to windmilldocs, keep design constraints User-facing how-to (engine choice, cursor recipes, schema drift, worked examples) moves to windmilldocs core_concepts/63_pipelines (windmilldocs#1462); the repo keeps only the design constraints future feature work must not break, as a section of ducklake-materialization.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: regenerate system prompts after parse_s3_object docstring change Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(sdk): reject empty-key s3 URIs; align asset parsers with the runtime rule Addresses CI review: s3:/// and s3://bucket/ now raise (an empty key would fall back to the auto-generated-key path the strict contract exists to prevent); the asset parsers' string branch applies the same valid-URI-with-non-empty-key rule so no R/W edge is recorded for a call that can only error (the generic URI-literal scan still records ambiguous access-None assets, by design); comments rephrased as current constraints per AGENTS.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
dce247c6d2 |
feat(pipeline): write-audit-publish for materialization data tests (#9911)
* feat(pipeline): write-audit-publish for materialization data tests (EE) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: EE worktree E0583 troubleshooting + duckdb feature check row Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: clarify EE symlink example (absolute target, EE repo layout) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(pipeline): move bootstrap DDL inside guarded WAP transaction Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(pipeline): move WAP guard SQL builder into EE, OSS keeps placement only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump ee-repo-ref to EE branch rebased on EE main Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * style: reword test comment as current invariant per AGENTS.md Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump ee-repo-ref (EE module doc update) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(pipeline): OSS emits typed materialize plan, EE owns WAP transform Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: make rewrite assertion build-aware; refresh oss module doc Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: update ee-repo-ref to 7be0bad1a6d6b5c3a107c0a2cd4bf003c36ec34c This commit updates the EE repository reference after PR #644 was merged in windmill-ee-private. Previous ee-repo-ref: 63cabae75329429f647e01083936d70f8197dc9e New ee-repo-ref: 7be0bad1a6d6b5c3a107c0a2cd4bf003c36ec34c Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> |
||
|
Ruben Fiszel
|
42e11c6570 |
feat(pipelines): schema contracts — save-time consumer checks vs captured schemas (#9917)
* feat(pipelines): schema contracts — save-time consumer checks vs captured schemas Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: move schemaContractContext above schemaCanEvolve doc comment Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: emit scd2/on_schema_change in CLI local graph, address review notes Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: gate editor _current ignore-suppression on scd2, matching backend Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
af36498432 |
feat(pipelines): record upstream snapshot ids on cascade-dispatched jobs (#9910)
* feat(pipelines): record upstream snapshot ids on cascade-dispatched jobs Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: batch upstream-snapshot lookup and memoize per subscriber Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
84141add1d |
feat(pipelines): workspace duckdb macro libraries (// macros / // use) (#9890)
* feat(pipelines): parse duckdb macro-library annotations (// macros, // use) * feat(pipelines): duckdb macro registry tables + deploy-path validation and writes * feat(pipelines): inject workspace duckdb macros into consumer jobs at run time * feat(pipelines): surface macro libraries and lib-consumer edges in asset graph api * feat(frontend): macro-library nodes, lib-consumer edges and scaffold in pipeline graph * docs: mark dbt gap #7 (packages/macros) shipped via workspace macro libraries * fix(pipelines): review fixes - char-safe parsing, local macros win, fork clone, trust-model docs * feat(frontend): duckdb macro autocomplete + workspace macro explorer drawer * fix(pipelines): address CI review - use-setup retention, splice past local defs, orphan filter, full consumer rescan, index-keyed strip * fix(pipelines): inject provider library setup for implicitly-called macros too * fix(pipelines): rls-gate macro listing + honor library-level // use transitively * fix(pipelines): weave injected macros around local definitions by bind order * fix(pipelines): injected library setup always runs before user blocks * perf(pipelines): cache macro registry per workspace with notify-event invalidation * perf(pipelines): disable macro registry cache on cloud |
||
|
Ruben Fiszel
|
d65f58c388 |
fix: pipeline dogfooding fixes — SCD2 data-test scope, --partition, s3object upload binding (#9875)
* fix: scope SCD2 built-in data tests to current rows Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: add --partition to pipeline run and fix duckdb s3object upload binding Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: note filesystem storage type is dev-only in storage settings Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: use ISO week for weekly partition default in pipeline run Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
659642e488 | fix(parsers): infer py s3 assets from S3Object constructor and dict forms (#9877) | ||
|
Ruben Fiszel
|
74f579e6d9 |
feat(pipeline): local development for data pipelines (CLI --local + pipeline dev preview) (#9840)
* feat(pipeline): local development for data pipelines (CLI --local + pipeline dev preview) Add the local edit→preview→run loop for data pipelines (folders of `// pipeline` scripts), the analog of `wmill dev` / `wmill app dev`, usable from a code editor or an agentic loop — without deploying. No backend changes: full body inference comes from the same wasm the frontend uses (windmill-parser-wasm-asset), which returns assets + pipeline annotations in one call; local runs reuse runScriptPreview with _wmill_skip_asset_dispatch. - localGraph.ts: wasm-backed working-tree → asset-graph builder (the enabler) - pipeline show/run --local; new pipeline docs (PIPELINE.md/AGENTS.md) subcommand - pipeline dev watcher + /pipeline_dev page (PipelineDevView) rendering the same PipelineGraphEditor from the pushed local graph, run via preview - cascadeRun.ts: reusable run primitives extracted from the route page - regenerated CLI agent docs See docs/pipeline-local-dev.md for the full design, test steps, and handoff TODOs. The live `pipeline dev` browser preview is implemented but not yet stack-verified. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): improve local dev preview (run, activity, responsive) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): dev-preview args, multi-root run, ws auto-reconnect Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): connect managed-materialize producer in local dev graph The CLI pinned windmill-parser-wasm-asset ^1.728.1, which predates managed-materialize support (added in 1.733.1); the frontend already pins 1.740.0. The CLI's wasm therefore never emitted `// materialize`, so the producer had no output edge and showed disconnected from its `// on` consumers. Bump the CLI to 1.740.0 (matching the frontend) and translate the parsed materialize target into the producer's write edge + materialize_target, mirroring frontend resolveGraph.ts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): harden local-dev CLI (bare-.sql crash, defaultTs, docs clobber) Review fixes, complementary to the dev-preview/materialize/multi-root work already on the branch (none overlap those commits): - localGraph: a bare `.sql` (no dialect) made inferContentTypeFromFilePath throw and abort the whole graph build — and wedge `pipeline dev` at startup. Skip the unclassifiable file instead. Also map `bunnative` → parse_assets_ts and add ruby/rlang/nu/powershell to the `#`-comment fallback. - show/run/docs/dev: thread the resolved `wmill.yaml` defaultTs into the graph builder so `.ts` infers under the workspace's runtime (bun vs deno) instead of always bun — `opts.defaultTs` was always undefined (no such CLI flag). - dev: wrap the startup graph build so a half-written file can't abort the watcher. - docs: don't clobber a user-authored AGENTS.md/CLAUDE.md — only (over)write the pointer when absent or already a generated `@PIPELINE.md` pointer. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): bind dev WS to loopback + local-graph regression tests - pipeline dev WS broadcast the folder's full script source (scripts[].content + temp_script_refs) unauthenticated on 0.0.0.0:3201 — bind 127.0.0.1 so it's not LAN-reachable (webview localhost + SSH/devbox port-forward still work). - Add regression tests for the just-landed local-graph fixes: bare .sql is skipped (was a build/dev-startup crash), defaultTs threads into .ts runtime inference (bun vs deno), and #-comment languages (ruby) use the # annotation fallback. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): --frontend flag for pipeline dev page origin wmill pipeline dev opens <remote>/pipeline_dev, but that route only exists in this build's frontend, so it 404s against a remote whose deployed frontend predates it. --frontend <origin> points the page at a locally-run frontend (REMOTE=<remote> npm run dev) while the API/token still target the remote — enabling the live preview against a real backend before the PR is deployed. No behavior change when omitted. Regenerated CLI agent docs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): WS session token + details-pane live-reload refresh Addresses CI review (Codex/Pi/Claude): - dev WS: a browser tab could open ws://localhost:<port>/ws and receive the folder's full source (browsers don't enforce same-origin on WS, loopback bind alone doesn't help). Gate the upgrade on an unguessable per-session token carried in the dev-page URL (verifyClient → 401 without it). Verified: no-token/bad-token connections get 401 with no bundle. - details pane: scriptRes keyed on [workspace, selection, draftScript] didn't re-run on a pipeline dev live-reload (same selection), so the open pane showed stale source. Thread a localScriptsVersion (the pushed bundle) into the key. Verified: editing a selected node's file updates the pane source without reselect. - docs/pipeline-local-dev.md: refresh the stale 'not yet exercised' status + done TODOs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): emit volume: annotation assets in local dev graph Addresses CI review (Codex P1 / Pi P1): the wasm body parser doesn't surface `// volume: <name>` annotations — the frontend (infer.ts:parseVolumeAnnotations) and backend (asset_inference.rs) parse them separately and merge as rw volume assets. localGraph didn't, so a `# volume: cache` producer had no write edge and showed disconnected from its `// on volume://cache` consumer (and pipeline run --local wouldn't schedule downstream). Mirror the leading-comment-block scan (SQL excluded, matching both reference parsers) and merge into inferScriptAssets. Regression test added; verified producer -> volume://cache -> consumer connects. Also (Codex P2): docs/pipeline-local-dev.md manual browser URL omitted the new ws_token param — without it the WS upgrade is rejected and the page sits disconnected. Doc now says to copy the URL the CLI prints (carries wm_token + ws_token) and recommends --frontend. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): runAll excludes event roots + review polish Addresses CI review (Codex P1, Claude P2/P3): - pipeline run runAll: derive the whole-pipeline selection from validStarts + descendants instead of all runnables, so an unqualified 'pipeline run <folder>' no longer fires event-trigger roots (kafka/mqtt/…) with empty args/side effects. Verified: a kafka root is excluded from the plan. - cascadeRun.ts runBoundedCascade: use buildLineageDownstreamMap (read-aware) so a pure-reader runs after its producer, and return cyclic — parity with the route page's bounded run (the file is meant to be THE shared correct primitive). - PipelineGraphEditor: storedRightPaneSize starts at 0 so the orientation-aware default (55% stacked / 40% side-by-side) actually applies on first open. - localGraph fallbackParse (go/bash): scan only the leading comment header (no body-comment phantom triggers) and strip key=value options from the asset URI; regression test added. - docs: reject '..' in the folder arg (it writes files under f/<folder>). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): route local previews to the // tag worker Addresses CI review P1: the local graph/bundle dropped the parsed `// tag`, so a node annotated `// tag gpu` ran on the default worker in both `pipeline run --local` and `/pipeline_dev`, while the deployed pipeline routes it to that worker tag. Carry the tag through LocalScript / the pushed bundle / LocalScriptContent and pass it to runScriptPreview at all three launch sites. Verified: a duckdb node tagged `bash` produces a job tagged `bash`; regression test added. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): add asset partitions/schemas routes to OpenAPI, use generated client The ducklake asset panels (PartitionStatusGrid, SchemaHistoryPanel) hit /assets/partitions and /assets/asset_schemas via raw fetch with cookie-only auth, because those backend routes were never added to openapi.yaml so the generated client had no methods for them. On /pipeline_dev (token-via-URL, no session cookie) the raw fetches 401'd. Add both GET routes + MaterializedPartition/AssetSchemaVersion schemas to openapi.yaml and call them through AssetService, which injects the bearer token, types, and cancellation automatically. Verified: Partitions + Schema tabs load in /pipeline_dev. (backfill stays a raw fetch — it's an EE-only route not in the OSS spec — with the token added inline.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(cli): regenerate bun.lock for windmill-parser-wasm-asset package.json / package-lock.json carry windmill-parser-wasm-asset@1.740.0 but the tracked bun.lock (the CLI installs/builds/tests via bun) was stale, so fresh bun installs would resolve a different graph than the committed lock. Regenerated. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): show asset producer + its runs in the dev-preview panel Selecting a ducklake/asset node in /pipeline_dev showed 'No producer for this asset' because selectionProducers wasn't passed (it's derived from the deployed graph on the route page, absent here). Compute it from the local graph's w/rw write-edges (incl. the // materialize target) and pass it through, mirroring the route page — so the panel shows the producing script and its (preview) runs, including data-test failures. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): carry annotation metadata onto local-graph runnables The local graph emitted only path/usage_kind/in_pipeline/materialize_target per runnable, so /pipeline_dev and pipeline show --local weren't the same surface as the deployed graph for annotated scripts — missing the badges/lineage the shared canvas renders. Map the wasm-parsed partition_kind, freshness, tag, retry, data_tests, column_lineage, and materialize_strategy (derived append/merge/replace) onto each runnable, mirroring the deployed AssetGraphRunnableNode. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): exclude event handlers that are lineage descendants from runAll The runAll guarantee ('never fires an event handler with empty args') only held for event ROOTS — validStarts excludes them, but runAll then unions in descendants(dag, start), so a kafka/mqtt/... handler that also reads an upstream pipeline asset (a lineage descendant of a valid start) still landed in the plan. Add eventTriggerScripts() and subtract it from the selection after the descendant union. +unit test. Also: docs/pipeline-local-dev.md recipe used 'pipeline docs demo_pipeline' without --local (default queries the deployed graph → hits the empty hint); add --local. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): whole-pipeline run cuts at event handlers (drop their downstream too) The prior runAll fix subtracted event handlers from the selection but left their downstream: for manual_root → asset_x → kafka_handler → asset_y → consumer, deleting only kafka_handler left consumer selected, and topoOrder then ran it as a root with missing/stale event-derived inputs. Replace the descendant-union+delete with reachableCutting(dag, validStarts, eventHandlers): traverse from valid starts but treat event handlers as cut points, so a node reachable ONLY through an event handler is dropped while one reachable via a non-event path stays. +unit test. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): recover // tag in the go/bash annotation fallback The wasm path carries out.tag, but the go/bash fallback (and the wasm-error degradation path) only recovered pipeline + on, so a // tag gpu on a bash/go node — or a temporarily-unparseable ts/py/sql node — silently routed the local preview to the default worker while the deployed pipeline routes to the tag. Scan for // tag in fallbackParse too. +test. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(pipeline): extract shared assetProducers helper The 'who writes this asset' write-edge derivation was copied verbatim in PipelineDevView and the pipeline route page — two copies that would drift. Extract assetProducers(graph, selection) into graphTraversal.ts and use it from both, keeping the dev view and route page in lockstep. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): only overwrite AGENTS.md/CLAUDE.md when it's the exact generated pointer Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): wire local-dev runs into the selected-node runs pane Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): exclude data_upload/webhook entrypoints from auto CLI runs Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): --upload binds an object to a data_upload/webhook entry point Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): add "Run + downstream" to the dev preview detail form Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): cut non-autorun triggers on all run paths; multi-binding --upload Address CI review: apply the data_upload/webhook/event barrier cut to the single-root and bounded (--from/--to) paths, not just whole-pipeline; accumulate repeatable --upload bindings per script (were overwritten); scope dev upload keys by script+param to avoid basename clobbering; drop <script> from help text. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): reseed dev run form when a local edit changes the script's args The read-only pane is keyed on script.path only, so in /pipeline_dev the selected node re-resolves on every WS bundle without remounting; PipelineScriptView cloned script.schema once, so adding/removing args left the run form on a stale schema (could run with missing inputs). Extract PipelineRunForm (owns the SchemaForm clone) and key it on the serialized schema: a real arg change reseeds the form, an unchanged re-resolve keeps in-progress input. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): don't cut a scheduled/manual root that also has a non-autorun trigger Address Codex P1: the barrier set subtracted only --upload-bound scripts, so a script with both `// on schedule` and `// on data_upload` resolved as the start yet was also a barrier — reachableCutting skipped it, giving an empty run plan. Subtract all valid starts (schedule/manual roots + bound handlers) from barriers: a legitimately-scheduled root runs on its schedule path even if it also carries a caller-input trigger; pure input-only roots stay cut. Adds a regression test. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): deployed non-autorun enrichment, s3:// storage, --to cut accounting, tag regex Address CI review (Codex P1/P1/P2, Pi P2): - Deployed `pipeline run` recovers marker-only data_upload/webhook/email triggers from script bodies (like the `show` path) so input-only entrypoints are cut instead of auto-run empty on the deployed graph. - `--upload s3://<storage>/<key>` keeps the named storage (authority) instead of folding it into the key, matching the S3Object round-trip convention. - Bounded `--to` targets cut by a barrier are reported in droppedEnds (+warning), not reachableEnds. - fallbackParse `// tag` matches a single token (\S+), rejecting multi-word prose. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): header-only deployed marker scan, fail-closed enrichment, default-storage s3 keys Address CI review (Codex P2, cubic P1/P1/P2): - Deployed marker recovery scans the LEADING comment header only (shared recoverHeaderMarkers helper, reused by the show enrichment too) so a body comment `// on data_upload` can't inject a phantom trigger and over-cut. - Deployed run enrichment fails CLOSED: a script-body fetch error aborts the run instead of silently letting an input-only entrypoint run with empty args. - Revert `--upload s3://` to default-storage whole-path keys (matching pipeline `s3://` asset-URI semantics); named-storage authority-splitting broke nested default keys like `s3://raw/2026/events.csv`. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): reject trailing content on fallback native markers; trim s3:/// key Address CI review (Codex P2, cubic P3): - fallbackParse now requires a native marker (`// on data_upload`) to stand alone; a line with trailing content (`// on data_upload f/foo`, `# on kafka topic`) is rejected, matching the canonical parser and keeping local/deployed parity. - s3UriKey trims a leading slash so the canonical empty-authority default form `s3:///key` doesn't leak a leading slash into the object key. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): persist dev WS token per-port so reconnect survives a CLI restart Address Codex P2: the /pipeline_dev auto-reconnect reuses the ws_token from the page URL, but `pipeline dev` minted a fresh random token each start, so a restart on the same port left the open page rejected by verifyClient forever. Persist the token per-port under the user-private config dir (0600) and reuse it on restart, so an already-open page reconnects — matching the reconnect behavior's intent. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): scope persisted dev WS token by workspace+folder+port Address cubic P2: keying the persisted token by port alone let a stale browser tab from a previous folder's session on the same port reconnect and receive a different folder's source. Scope the token file by workspace+folder+port so a same-session restart still reconnects, but a different folder on the same port gets a distinct token that rejects stale cross-folder tabs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): caller args can't override skip-dispatch guard; hash the dev token key Address CI review (Codex P1, cubic P2): - makeLaunch / CLI run build args with `_wmill_skip_asset_dispatch` LAST (and drop any caller-supplied copy) so a run-form/`--upload` arg can't re-enable backend asset dispatch while the client orchestrates the cascade (double-run / running deployed subscribers from a local preview). Adds a cascadeRun guard test. - Dev WS token file key is a sha256 of NUL-delimited workspace+folder+port, so different folders (`a/b` vs `a_b`) can't collide onto the same token file. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipeline): canonical s3://storage/key --upload parsing; scope dev token by remote+root Address Codex P1/P1: - Restore canonical S3Object URI parsing for `--upload` s3 sources, matching the frontend's `parseS3Object` (`s3://<storage>/<key>`, empty authority ⇒ default, `s3:///key`/`s3:///nested/key` for the default store). `s3://secondary/k.csv` → `{ s3: "k.csv", storage: "secondary" }` so a named-storage object is read from the right store. (This is the canonical convention; the default-storage nested key is served by the `s3:///` form.) - Scope the persisted dev WS token by remote+workspace+root+folder+port (was workspace+folder+port), so two profiles on different remotes (or local checkouts) with the same workspace/folder/port don't share a token — a stale tab can't reconnect across a workspace/remote boundary. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
5a661279a3 |
feat(pipelines): add managed SCD2 history materialize strategy (#9850)
* feat(pipelines): add managed SCD2 history materialize strategy `// materialize ducklake://... key=<col> history [track=...]` (alias: `scd2`) upgrades the keyed merge to SCD type 2: diff the current snapshot against live rows, close changed versions (valid_to/is_current) and open new ones in one transaction, keeping full history. Adds a consumer-convenience <dim>_current view; effective-dated joins via native ASOF JOIN >= valid_from. Managed, so // data_test and schema capture work (unlike manual mode). Non-partitioned v1, soft-delete on absence. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(pipelines): document scd2 track= spacing, reserved _current suffix, schema-freeze Addresses non-blocking CI-review nits on the new SCD2 public surface. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): null-safe scd2 key matching + create _current view inside txn Addresses CI review: (1) Codex P1 — NULL natural keys were flagged as changed but silently dropped because `key IN (...)` never matches NULL; close/open now match with `IS NOT DISTINCT FROM` via correlated EXISTS. (2) cubic P2 — the `<dim>_current` view was created after COMMIT and CREATE VIEW advances the DuckLake snapshot, so the summary recorded the view's snapshot instead of the data write; the view is now created inside the write transaction. Validated both against a real DuckLake (NULL key materialized; one snapshot per run). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): create scd2 _current view with IF NOT EXISTS to keep no-change runs no-op Addresses CI review (Codex P2): CREATE OR REPLACE VIEW advances the DuckLake snapshot every run, so an unchanged rerun still minted/recorded a snapshot. The view definition is static, so IF NOT EXISTS creates it once (folded into the first data-write snapshot) and is a true no-op thereafter — verified an unchanged rerun keeps max(snapshot_id) constant. Also softens the reserved-name collision: IF NOT EXISTS skips silently instead of erroring. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipelines): add scd2 deletes=close (hard-delete-close) Opt-in `deletes=close` closes the current version of a key that disappears from the snapshot (dbt's hard_deletes=close); default stays soft-delete. Codegen adds a vanished-key temp set (current keys EXCEPT snapshot keys) + a second null-safe close UPDATE with no reopen; a reappearing key opens a fresh version (validity gap = correct SCD2). Wired through both parsers with parity fixtures/tests, worker derivation, unit + codegen tests, and docs. Verified end-to-end against a real DuckLake incl. delete-close + reactivation. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): align materialize deploy precedence warning with runtime (scd2>append>merge) The deploy-time conflict warning only knew append>key, so warned 'append wins' while the runtime (duckdb_executor) runs SCD2 (history wins). Warn for history+append (history wins, append ignored) before the append+key case, mirroring the runtime strategy precedence. (Pi review P2.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): register scd2 _current view as a produced asset for cascade dispatch The docs present the companion <dim>_current view as a subscribable produced asset (// on ducklake://.../<dim>_current), but deploy registered only the base table as a write asset, so a subscriber on the view would never be dispatched (the cascade fans out from deploy-time asset rows). Register <dim>_current as a produced write asset when scd2 so those subscribers fire. (Codex review P1.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(pipelines): don't register _current asset for manual+history (no view created) Manual mode short-circuits before the scd2 codegen, so no <dim>_current view is created; gate the produced-asset registration on !manual so a contradictory // materialize manual ... history doesn't leave a false write edge dispatching subscribers on a nonexistent view. (Codex review P2.) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
003a262a4e |
feat: column-level lineage for DuckLake pipelines (SQL-AST inferred + traceable) (#9814)
* feat: column-level lineage for ducklake pipelines via // column annotation Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat: auto-derive column lineage from DuckDB SQL AST (annotation as override) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * docs: clarify column-lineage inference is server-side; drafts use annotations Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(frontend): surface inferred column lineage in live pipeline drafts Threads the DuckDB SQL-AST column lineage (from the WASM asset parser) through ScriptEditor -> details pane -> page -> resolveGraph, merged with // column annotations (annotation wins) so the live preview matches the deployed graph. Takes effect once windmill-parser-wasm-asset is republished with the inference. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(frontend): bump windmill-parser-wasm-asset to 1.740.0 for SQL column-lineage inference Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * docs: column-lineage inference now runs live (WASM) too, merged with annotations Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(frontend): transitive column-lineage trace (impact analysis) Stitches every producer's column_lineage into a pipeline-wide column graph (columnLineageGraph.ts) and replaces the single-hop diagram with an interactive ColumnLineageTrace: select an asset to see its columns' full upstream/downstream lineage across scripts; click any column to highlight its complete transitive impact set (forward + backward) and dim the rest. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: address CI review on column lineage (parse-fallback, node-id, perf, leak) - backend: DuckDB SQL parse failure now falls back to `// column` annotation lineage instead of dropping it (Codex P1) - columnLineageGraph: collision-proof JSON node ids; deterministic first-write output anchoring when a producer has multiple ducklake writes (cubic P2 ×2) - pipeline page: gate buildColumnGraph to a ducklake-asset selection so it doesn't rebuild on every editor keystroke (cubic P2) - ScriptEditor: clear inferredColumnLineage on parse error so it can't leak across a script switch (cubic P2) - AssetGraphEdge: widen badge stacking offset 12px->18px to fully clear (cubic P3) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: resolve JOIN inputs + anchor column lineage to // materialize target Addresses the second Codex review pass (two P1s): - SQL inference now walks JOINed tables: build_from_maps maps every FROM entry AND its joins into the alias map, and single-table attribution requires no joins. `SELECT o.x, c.y FROM a o JOIN b c` now resolves c.y (was dropped). - The column graph anchors a producer's lineage to its declared // materialize target (surfaced on the runnable node) instead of guessing a ducklake write-edge, which is unordered for deployed graphs and ambiguous for multi-output scripts. Falls back to a write-edge when no materialize target. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: gate column-lineage badge to the // materialize target write-edge The canvas badge keyed on `e.asset_kind === 'ducklake'`, so a multi-output producer showed the same column mapping on every ducklake write-edge. Use the same materialize-target anchor as buildColumnGraph: the badge lands only on the declared output's edge, falling back to the ducklake write-edge when there's no materialize annotation. (Codex P1) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: build column trace from displayGraph so View hides draft lineage The transitive column trace was built from graphWithDraft regardless of mode, so in View with drafts hidden it could surface draft `// column` lineage the deployed canvas doesn't show. Build it from `displayGraph` (the graph the canvas actually renders) so the trace matches: draft overlays in edit / show-drafts, deployed-only in plain View. (Codex P2) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: don't infer column lineage for local/temp staging CTAS A CTAS into a local/temp staging table isn't the materialized output, but its projection was inferred and (flat) column_lineage anchored to the script's // materialize target — so staging columns showed up as the final asset's. Gate inference to the actual output: a top-level managed-materialize SELECT, or a CTAS/CREATE VIEW whose target resolves to a real asset. (Codex P1) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: scope inferred column lineage to one output asset Inference accumulated columns from every output-producing query into one flat list, all anchored (frontend) to the script's // materialize target — so an auxiliary CTAS into a different asset showed its columns on the materialized one. Tag each inferred entry with its output asset and, in parse_assets, scope the list to the // materialize target (keeping untagged top-level-SELECT entries); with no declared target, drop inference when entries span multiple output assets rather than attribute them to an arbitrary one. Parser-internal — no wire change. (Codex P1) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: treat CREATE TEMP TABLE/VIEW as local even under an active USE A one-part temp name under `USE dl` resolved to an asset (ducklake://…/tmp) before being registered local, so a final SELECT reading it invented `final.total <- warehouse/tmp.amt` (a phantom DuckLake column) and recorded a phantom asset. track_table_definition now registers any temporary table/view as local up front, bypassing active-asset resolution; CreateTable/CreateView pass their `temporary` flag. (Codex P1) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
f6998ec54c |
feat: data tests for ducklake pipeline materialization (#9708)
* feat: data tests for ducklake pipeline materialization Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(frontend): data_test count badge on pipeline graph nodes Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: surface annotation badges (incl. data_test) on deployed pipeline nodes Backend graph endpoint now parses each pipeline member's deployed body and returns partition/freshness/tag/retry/data_test, so badges render on deployed nodes, not only live drafts. Aligns the TS DataTest.relationships fields to snake_case to match the Rust serde wire shape (the type is now populated from both the parser and the backend JSON). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(frontend): keep materialize output edge when editing the producer in the pipeline graph The live-edit overlay re-derived a selected/edited script's lineage from // on inputs + body-inferred assets only, so the // materialize <asset> output (an annotation, not body SQL) was judged stale and its write-edge dropped on select — leaving the materialized asset unlinked (and the node's annotation badges hidden). Include the parsed materialize target in liveRefKeys and the draft writeOuts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: run all data tests in one pass with a structured per-test result Replace the raise-on-first-violation probes with a single materialize summary that embeds every test's violating-row count in a data_tests column (computed in a CTE, since DuckDB rejects subqueries inside struct literals). The worker reads the breakdown and decides pass/fail: a clean run returns the per-test summary in the result; a failing run errors with the FULL list (every test, ✓/✗ + counts), not just the first failure. Verified live (EE) for built-ins + custom, pass and multi-failure. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(frontend): data-test pass/fail checklist in the job result DisplayResult renders a per-test checklist (✓/✗ + violation counts) above the raw result for managed materialize runs — from the structured data_tests on success, and parsed from the worker's breakdown message on failure. Shows in the script editor Test panel, the runs page, and the pipeline asset run pane. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(frontend): move data-test badge onto the producer→asset edge with run status The test badge now sits on the write-edge (the transformation link) rather than the producer node, since the tests assert on what the transformation produces. It's tinted by the producer's last-run status (green = passed, red = a test failed) and its hover title lists every declared test. Removes the now-redundant node badge. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(frontend): render custom data-test scripts as their own clickable graph nodes A // data_test <script_path> custom test now appears as its own node below the asset it validates, joined by a dashed 'tests' edge. Clicking it opens the test script in the detail pane (dispatched like any runnable). Built-in tests stay folded into the edge badge; only script-backed tests become nodes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(frontend): type data-test edge field via AssetGraphResponse, not in-scope g BuiltEdge is declared at component scope, outside build(g), so referencing typeof g.runnables in its type failed CI's svelte-check (Cannot find name 'g'). Use the imported AssetGraphResponse type instead. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(frontend): anchor edge badge on routed path + a11y text on test icons Address review: the data-test edge badge anchored on the straight-line midpoint, floating off detoured edges — anchor it at detourX when the edge is routed through a gutter lane. Add sr-only pass/fail text so the checklist icons are distinguishable to screen readers. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: close data-test enforcement bypass + gate badges to scripts + reject multi-stmt custom tests Address review (cubic) findings: - P1: managed materialize generates its own summary row carrying data_tests, and enforcement reads that column — but a // result_collection annotation (e.g. a scalar mode) could reshape the row and drop data_tests, silently bypassing a failing test. Force LastStatementAllRows for managed materialize runs so the summary row is always intact. - P2: asset-graph annotation badges were keyed by path only, so a flow sharing a path with a pipeline script inherited its badges. Gate the lookup on usage_kind == Script. - P2: a custom test body is embedded as a subquery, so a multi-statement body produced invalid SQL with an opaque DuckDB error. Validate single-statement up front with an actionable error; align docs/comments. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: fail loud if fewer data-test outcomes recovered than declared Defense-in-depth from the fresh-context review: enforcement reads per-test outcomes off the materialize summary row, but if the data_tests column were ever dropped/reshaped at the FFI boundary, extract_data_tests would return fewer (or zero) outcomes and the run would silently pass unverified tests. Track the embedded test count on MaterializeExec and abort with a clear error when recovered < declared. Verified: normal run (4==4) unaffected; the scalar-result_collection bypass already fails. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: relationships data test same-lake reuse + schema-qualified target quoting Address Codex/Pi review (two P1s in the relationships codegen): - A relationship into the same ducklake as the materialize target minted a second ATTACH of that lake under _wm_ref_N while _wm_target already held it — DuckDB forbids attaching one database twice, so the test failed before it could run. Reuse _wm_target for same-lake references. - A schema-qualified target (ducklake://warehouse/main.dim_products.sku) emitted FROM _wm_ref_0."main.dim_products" — one quoted identifier with a literal dot — silently querying a nonexistent table. Quote each dotted segment so the dot stays a schema separator. Adds tests for both. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(frontend): refresh data_test badge on deployed-script drafts + scope to materialize target Address Codex review nits (both P2): - resolveGraph: the existing-runnable draft-overlay branch kept the deployed data_tests, so adding/removing // data_test lines on an already-deployed script left the badge stale until redeploy. Refresh it from the live parse like the new-runnable branch. - AssetGraphCanvas: data tests were attached to every write-edge from a producer. They assert on the // materialize target (always a ducklake asset in v1), so only the ducklake write-edge now carries the badge and custom-test nodes — a producer's other (S3/datatable) outputs no longer show them. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
d131d754e1 |
feat: ducklake time-travel UX (snapshot history + AT VERSION reads) (#9709)
* feat: ducklake time-travel UX (snapshot history + AT VERSION reads) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: catalog-qualify ducklake time-travel FROM hints (lake. prefix) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: render ducklake snapshot_time (microseconds since epoch) correctly Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor: merge ducklake History + Query into one master-detail tab Snapshot list (left) selects the version previewed in the read-only grid (right); newest auto-selected. Copy-clause moved to the preview's SQL line. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: scope ducklake snapshot history to the table's versions Catalog-wide snapshots predate a table's creation; previewing AT a version before the table existed errored ("Table ... does not exist at version N"). The DUCKLAKE_SNAPSHOTS marker now takes the table and lists only snapshots from its first creation onward. Also: narrower snapshot-list pane on large screens (target a fixed width, not a fixed fraction). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: load ducklake preview columns at the pinned version + reset on asset switch Addresses CI review (codex/pi P1, cubic P2): - Historical previews loaded current-schema columns, so an AT(VERSION) read enumerating a column added in a later snapshot failed. Now DESCRIBE-loads the column set at the pinned version; the read is gated on columns matching the current version to avoid a stale-colDefs race on version switch. - selectedVersion no longer sticks across assets: the panel is keyed on path (remounts per asset) and effectiveVersion falls back to newest when the pick isn't in the current list. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: match History tab UI (master-detail, full-FROM copy) after merge Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: handle catalog-only ducklake asset paths (no table segment) parseDbInputFromAssetSyntax threw on a catalog-only path like 'ducklake://main' (undefined.split('.')) — a real graph node (e.g. a consumer of the whole catalog). It now returns a table-less input instead of throwing, and DucklakeAssetPanel renders only the partition grid (no per-table history/time-travel) for table-less nodes. Adds parser unit tests. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: escape ducklake catalog name in client-built time-travel DESCRIBE fetchDucklakeColumnsAtVersion interpolated the catalog name into an ATTACH string literal without escaping; double single-quotes (mirrors backend escape_sql_literal) so a quote-containing catalog name can't break out. Also fixed the v1.x docs checklist line to match the shipped full-FROM copy affordance. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
3ebf24359d | feat: ducklake materialization for data pipelines (#9689) | ||
|
Ruben Fiszel
|
7155a0bb96 |
feat: Data Pipelines alpha (#9193)
* feat: add workspace asset graph view Workspace-wide canvas of assets and their producer/consumer scripts, reachable from the assets page. Left-to-right layered layout via d3-dag sugiyama, rendered with @xyflow/svelte (same stack as the flow editor). GET /w/:ws/assets/graph returns deduped nodes + edges. Follow-ups: filters (kind/folder/search), node detail drawer, inline script edit from a clicked node. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * all * all * all * update * all * all * all * feat(pipeline): output-kind picker and per-(lang, output) templates Add a third stage to PipelineInsertMenu that asks what kind of asset the new script will produce (datatable / ducklake / s3 parquet / s3 object / none). The picked kind drives a real wmill SDK skeleton — typed datatable inserts, ducklake CREATE+INSERT, s3 parquet COPY, etc. — with the upstream asset auto-wired as the input source when added from an asset node. Reorder languages to bun → duckdb → python → sql so data-shaped languages surface first. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * all * chore(main): release 1.693.4 (#8994) * chore(main): release 1.693.4 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * feat: ansible delegate_to_git_repo install_requirements, dynamic fields, --limit (#8997) * feat: ansible delegate_to_git_repo install_requirements, dynamic fields, --limit Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: include .yaml variants in collections/roles requirements lookup Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): only preserve case for raw-app runnableIds, not app/flow summaries (#9000) * fix(cli): only preserve case for raw-app runnableIds, not app/flow summaries PR #8940 stopped lowercasing in sanitizeForFilesystem to fix #8939, where a raw-app runnableId like CamelCaseTSRunnable produced a CamelCase YAML metadata file but a lowercased code file, making them desync and register as duplicate runnables on push. That fix overshot. sanitizeForFilesystem is also reached by newPathAssigner, which serves normal apps and flows where the input is the script's human summary ("Get Users Data") rather than an identifier. There the on-disk filename is the only artifact — there's no companion YAML to keep in sync — so lowercasing was the right behavior. Removing it changed both the on-disk filename and the !inline reference in app.yaml / flow.yaml from get_users_data.inline_script.ts to Get_Users_Data.inline_script.ts on the next pull, surfacing as unwanted case churn for users updating to 1.693.x. Add a preserveCase option to sanitizeForFilesystem (default false → lowercase). newRawAppPathAssigner opts in; newPathAssigner stays on the default. Update unit tests accordingly and add an end-to-end raw-app round-trip in raw_app_sync.test.ts that pushes a CamelCase backend runnable, pulls it back, and asserts both YAML and code file preserve case with no lowercase orphan. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(cli): use readdir for exact-case orphan check on Windows The CamelCase round-trip test used fileExists("camelcasetsrunnable.ts") to assert no lowercase orphan was produced, which false-positives on Windows since the filesystem is case-insensitive and resolves the lookup to the existing CamelCaseTSRunnable.ts. Switch to readdir + toContain so the exact on-disk casing is compared identically on Linux and Windows. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(cli): wmill-lock.yaml auto-fill + --rehash-only + path-prefix dedup (#8978) * fix(cli): canonical lockfile hashes + lock upgrade migration to v3 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): use __app_hash subpath in rehash missing-entry check Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): run sync pull lockfile auto-fill regardless of changes Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: regenerate system prompts for new lock and rehash-only commands Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): address review feedback on lock upgrade Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): drop v3 marker; always run fallback; fail-fast on unknown lockfile version Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): drop yaml-round-trip legacy hash variant; recover via --rehash-only Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): include legacy hash in script push staleness warning check Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * revert(cli): drop canonical hash formula; keep raw-bytes hashing Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * perf(cli): reuse change-tracker map for sync pull lockfile auto-fill Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): address review feedback on rehash-only Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(cli): pin lockfile hash + yaml format and cover regression cases Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(cli): byte-stable snapshot tests for flow.yaml format Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(cli): add app and script-metadata yaml snapshot fixtures Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): address claude review on rehash-only Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * refactor(cli): factorize script-path to remote-path derivation Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): address claude + cubic review (dry-run mutation, rehash short-circuit) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * refactor(cli): make rehash a subcommand and factorize fs walks Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): normalize line endings in yaml snapshot tests for windows ci Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(cli): address review feedback on rehash + auto-fill - Flat-layout scripts now clearGlobalLock before rehash write so legacy ./-prefixed duplicates get cleaned up (matches flow/app behavior). - Add MalformedLockfileError; sync pull auto-fill re-throws it alongside UnknownLockVersionError instead of silently warning + continuing. - Document the legacy step-removal false-negative in isFlowDirectlyStale / isAppDirectlyStale and the categorizeLocalFiles ignore-filter invariant. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * fix: use otel.status_message for OTLP Status.message on failed jobs (#8995) tracing-opentelemetry only recognizes otel.status_code and otel.status_message as fields that map to the OTLP Status proto. The previously-used otel.status_description fell through to the generic attribute recorder, leaving Status.message unset and preventing OTLP consumers from filtering spans on error status. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: route email trigger path through standard info channel (#8996) * docs(skill): document email triggers and S3 attachments Add an "Email triggers" section to the triggers skill covering the local-part config, the parsed_email/raw_email/email_extra_args payload, the URL-style extras convention, where to find trigger_path (only with a preprocessor, at event.trigger_path), and — most importantly — that binary attachments are uploaded to the workspace S3 bucket and surface as `{ s3: "windmill_emails/<job_id>/attachments/<filename>" }`. Scripts must use wmill.loadS3File / wmill.load_s3_file to read them. Also pulls EmailTrigger into the schema mappings so a real `email_trigger.schema.yaml` is generated, and adds Email/Azure to the trigger kinds list in the CLI agent guidance. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref for email trigger path fix Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref to 26184ab7a4aadfc529dcedf038aa08d36c7ad381 This commit updates the EE repository reference after PR #553 was merged in windmill-ee-private. Previous ee-repo-ref: 318a46897a605dc9be3817901f35ba5a99a0a525 New ee-repo-ref: 26184ab7a4aadfc529dcedf038aa08d36c7ad381 Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * update git sync version to 1.693.5 * fix: pair PG arg type with actual Rust binding to keep query_typed_raw safe (#8999) * fix: pair PG arg type with actual Rust binding to keep query_typed_raw safe Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(pg): wrap encoder errors with arg context, add fallback test Followups on #8999 review: - Wrap rust-postgres "error serializing parameter N" failures with the arg name, JSON value kind, and asserted Postgres type plus a hint about an explicit cast — so users see actionable context instead of an opaque WrongType. - Drift-prevention meta-test: assert otyp_to_pg_type and convert_val agree on the Type for every recognised arg_t when the JSON value matches its natural Rust kind. Catches future drift if either side changes. - Integration test for the prepare + query_raw fallback path: confirms unrecognised arg_t (custom enum) is routed through prepare and the server-resolved type appears in the failure surface — flips into a test failure if a regression accidentally routes unrecognised types through query_typed_raw. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): add otyp_inferred flag + regex-based placeholder renumbering Two follow-ups from the review of #8999: 1. **Issue #1 (Number/Bool + explicit text decl in WHERE)** Add `Arg::otyp_inferred: bool` to the parser. The PG SQL parser sets it `true` only at the "no info → fall back to text" site (bare `$N`, no inline cast, no `-- $N (TYPE)` decl). All other arg sources keep it `false`. In `convert_val` this flag distinguishes: - explicit text-like target (`-- $1 (text)` or `$1::text`) — coerce `Bool`/`Number` → `Box<String>` so `WHERE text_col = $1` works (`text = text` operator). Pre-#8988 behaviour, restored. - parser-default text (bare `$N`) — bind the value's natural Rust type so the regression case (`Value::Bool` against a real `bool` column via `CAST AS bool`) keeps working. `Arg` is in `windmill-parser`; the new field has `#[serde(default)]` so persisted signatures stay backward-compatible. 2. **Issue #4 ($5/$50 substring rewrite collision)** Replace the per-index `String::replace` chain (which turned `$50` into `$10` when oidx=5 was processed first) with a single regex pass. `\d+` is greedy, so `$5` and `$50` match as distinct units; indices outside the mapping are left intact. 3. Tests: - parser: `test_parse_pgsql_otyp_inferred_flag` covers bare/inline- cast/decl/mixed shapes. - executor unit: `convert_val_bool_against_every_arg_t` and `convert_val_*_number_*` split each text-like target into explicit vs inferred expectations. - executor unit: `renumber_sparse_placeholders_no_collision`. - integration: `test_postgresql_arg_type_combinations` adds 4 cases covering decl(text)+Number/Bool in WHERE, bare $1+Bool, and sparse positional args ($5/$50). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg+sdk): enum support, extended String arms, position-aware $N rewrite, SDK quality Backend: 1. **`AnyTextValue` ToSql/FromSql wrapper**: vanilla `tokio_postgres`'s `ToSql for String` / `FromSql for String` reject `Kind::Enum` and `Kind::Domain` even though the wire format is plain UTF-8. The wrapper accepts those kinds in both directions. End result: explicit `$1::my_enum` / `CAST($1 AS my_enum)` casts now round-trip without the ugly `CAST($1::text AS my_enum)` workaround, AND `SELECT enum_col` results come back as JSON strings instead of erroring at the FromSql layer. 2. **#10 — Value::String → numeric/real/double/oid/bool**. Without these arms, a string-encoded value (`"3.14"`, `"true"`) for a non-text / non-temporal arg_t fell through to `Box<String> + TEXT`, which then failed at the server (no implicit cast text→numeric in expression context). Now strings are parsed into the matching native type with clear error messages on parse failure. 3. **Position-aware `$N` rewrite**: replaces the regex-based renumbering (which fixed the `$5/$50` substring collision but still walked through string literals and comments, mangling `'price: $5'` etc.) with a walk over `parse_pg_statement_arg_positions` — the same string/comment/dollar-quote-aware tokenizer used for index discovery. Adds `parse_pg_statement_arg_positions` to the parser's public API. SDK: 4. **BigInt support**: `JSON.stringify(BigInt)` throws. The SDK now stringifies bigints before serialisation; the executor accepts numeric strings into BIGINT arg slots via the existing `Value::String → INT8` parsing arm. SDK-side `inferSqlType` is split so `BigInt` always resolves to `BIGINT` (was reaching `Number.isInteger(BigInt)` which returns false → wrong default). 5. **Homogeneous array auto-tag**: `${[1,2,3]}` against an `int[]` column now emits `$1::BIGINT[]` instead of `$1::JSON`. Detection covers primitive types only (number / bigint / string / boolean); mixed or nested arrays still fall back to JSON. Mixed int/float widens to `DOUBLE PRECISION[]`. 6. **`.query()` positional bug**: previously the `.query()` method abused the template-tag builder, which appended `$N::TYPE` after the user's literal SQL string instead of binding by position (`SELECT $1, $2` became `SELECT $1, $2$1::BIGINT`). Now `.query()` builds the executor-shaped content directly: a `-- $N argN (TYPE)` declaration block followed by the user's SQL verbatim. Tests: - Parser: `test_parse_pg_statement_arg_positions_skips_strings_and_comments` asserts string literals, comments, and dollar-quoted blocks don't produce positions (so renumbering doesn't mangle them). - Executor unit: `renumber_sparse_placeholders_no_collision_no_string_mangling` uses the new position-aware path and includes string-literal + comment + `$$…$$` cases. Existing convert_val tests grow to cover new String→numeric/real/double/oid/bool arms. - Integration: `test_postgresql_arg_type_combinations` adds 13 cases (enum round-trip both directions, string→numeric/real/double/bool/oid, string-literal `$N` non-mangling). The prepare-fallback test now asserts SUCCESS (not failure) for enum encoding via AnyTextValue. - SDK: new `typescript-client/tests/sqlUtils.test.ts` (42 tests) exhaustively covering inferSqlType primitives + arrays, parseTypeAnnotation, datatable() template tag (with all the new shapes — BigInt, homogeneous arrays, RawSql, schema preamble), datatable().query() positional, and ducklake() shape. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): replace DISCARD ALL with curated reset (preserves typeinfo cache) Found while exhaustively probing custom-type DX: every cached-connection reuse was running `DISCARD ALL`, whose included `DEALLOCATE ALL` deallocates *all* prepared statements server-side — including the typeinfo statements that tokio_postgres caches per-Client to resolve custom enum / domain Oids. tokio_postgres still held `Statement` objects whose names the server had forgotten, so the next custom-type query failed with intermittent "prepared statement \"sN\" does not exist" errors. The failure was easy to reproduce: any sequence that forced typeinfo lookup for two different custom-type kinds on the same cached connection (e.g. enum followed by domain) would hit it. Replace `DISCARD ALL` with a curated reset that explicitly targets the state we actually care about, *without* touching prepared statements: RESET ALL — GUC parameters (search_path, application _name, statement_timeout, …) RESET SESSION AUTHORIZATION — undoes both `SET SESSION AUTHORIZATION` and `SET ROLE` (RESET ALL does NOT — these aren't GUC parameters, so without this an elevated role from a previous job would silently leak) UNLISTEN * — drops LISTEN registrations CLOSE ALL — closes open cursors Trade-off: temp tables, advisory locks (session-scoped), and user-created PREPARE statements may persist across cached-connection reuse — rare in datatable / PG-script workloads. tokio_postgres's typeinfo cache survives intact, so custom enum / domain queries are fast on subsequent reuse. Tests: - `test_postgresql_custom_types_on_cached_connection` — runs 10× alternating enum + domain queries on a cached connection. Pre-fix this failed with `prepared statement "sN" does not exist` after the first reuse; post-fix passes. - `test_postgresql_set_role_does_not_leak_across_cached_connection` — switches `SET ROLE` and `SET SESSION AUTHORIZATION` to a non-postgres role, then runs a follow-up job and asserts current_user/session_user are restored. Specifically catches the case where someone might switch back to `RESET ALL` alone (which doesn't cover SET ROLE / SESSION AUTHORIZATION) and silently introduce a permission-leak vector. - All existing session-isolation tests (`test_postgresql_cached_connection_resets_session`, `test_postgresql_single_worker_session_isolation`, `test_postgresql_100_jobs_cached`) continue to pass. Found via end-to-end probing of datatable / PG-script DX, not previously covered: the existing isolation tests only did `SET ROLE postgres`, the connecting user, so the leak was invisible. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): address PR #8999 review (cubic + claude) cubic (P1, real bug): - `convert_vec_val` for `timetz` array asserted `Type::TIMETZ_ARRAY`, but chrono `NaiveTime` only encodes for TIME (same caveat as the scalar arm). Switch to `Type::TIME_ARRAY`; rely on PG's implicit `time→timetz` assignment cast at the column site. Add an explicit unit test. claude (#1, silent failure → explicit error): - `Bool` + explicit `(char)` / `(character)` decl previously silently bound BOOL, hoping the server would cast at the use site — but PG has no implicit `bool→char` and the resulting error ("operator does not exist: bool = char") was opaque. Now error at bind time with an actionable hint to use `bool` decl or pass the value as a "t"/"f" string. claude (#2, asymmetry doc): - Object/Array still coerce to text on `matches!(typ, Typ::Str(_))` (covers both explicit AND inferred-default text), unlike Bool/Number which key on `explicit_text_target`. The asymmetry is intentional (no implicit `jsonb → text` cast in expression context vs PG having implicit `bool/int → text` casts) — added a body comment so future maintainers don't try to "align" them. claude (#3, perf): - `parse_pg_statement_arg_indices` and `parse_pg_statement_arg_positions` walked the SQL tokenizer twice. Fold into a single pass that derives the index set from the position list. claude (#4, fmt drift): - `cargo fmt` over the parser crates I touched with perl scripts in the earlier commit (windmill-parser-{sql,bash,ts,go,php,java,csharp,nu,py, rust,graphql,yaml,r}). Net cosmetic. claude (#5, parseTypeAnnotation): - One-line caveat in the SDK's `parseTypeAnnotation` that the returned string is presence-only (e.g. `${x}::DOUBLE PRECISION` returns `"DOUBLE"`, `CAST(${x} AS int)` returns `"int)"` — neither matches a real PG type, but the only consumer just checks `!== undefined`). While here — discovered + fixed independently while exhaustively probing DX: - **Replace `DISCARD ALL` with curated reset** (`RESET ALL; RESET SESSION AUTHORIZATION; UNLISTEN *; CLOSE ALL;`). DISCARD's `DEALLOCATE ALL` killed tokio_postgres' typeinfo cache, producing intermittent `prepared statement "sN" does not exist` errors on custom-type queries after cached-conn reuse. New regression tests: `test_postgresql_custom_types_on_cached_connection` and `test_postgresql_set_role_does_not_leak_across_cached_connection` (the latter catches the case where someone might switch back to `RESET ALL` alone and silently introduce a permission-leak vector — RESET ALL doesn't cover SET ROLE / SET SESSION AUTHORIZATION). - **ISO-8601 timestamp results** (`pg_cell_to_json_value`). Pre-fix `TIMESTAMP` was rendered with a space separator ("2024-01-15 10:30:00") and `TIMESTAMPTZ` with " UTC" suffix ("2024-01-15 10:30:00 UTC") — neither parseable by `date-fns parseISO`, JavaScript `new Date()` is lenient enough to handle them but several frontend `App*Input.svelte` components use parseISO and fail silently. Switched to ISO-8601 with `T` separator and `+00:00` offset; arg-parsing path still accepts the legacy " UTC" suffix for back-compat. Test coverage: - 17/17 unit (`pg_executor::tests`) - 9/9 integration (`backend/tests/worker.rs`, `test_postgresql_*`) - 27/27 parser (`windmill-parser-sql`) - 42/42 SDK (`typescript-client/tests/sqlUtils.test.ts`) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): bounded one-shot warning on numeric precision loss + ISO-8601 + NaN handling Found while probing PG-script DX with millions of numeric cells: 1. **Numeric precision-loss warning**: `numeric` results are still serialised as JSON Number (back-compat — switching to JSON String would silently break user code doing arithmetic on results), but we now detect `Decimal -> f64 -> Decimal` round-trip failure and emit a single job-log warning recommending a `::text` cast in the SQL. Bounded by `NUMERIC_PRECISION_CHECK_BUDGET = 256` cells per query (one atomic load + one fetch_sub on the hot path; first lossy value short-circuits to a single load thereafter). Worst-case overhead on a 1M-cell numeric-heavy query: ~25µs of checks + 5ns × N atomic loads (vs. ~100ms unbounded). 2. **ISO-8601 timestamps**: `pg_cell_to_json_value` previously returned `"2024-01-15 10:30:00"` (TIMESTAMP) and `"2024-01-15 10:30:00 UTC"` (TIMESTAMPTZ) — neither parseable by date-fns `parseISO`, which is what the apps `App*Input.svelte` components use, so timestamp values silently failed to round-trip into date pickers. Switch to ISO-8601 (`T` separator + `+00:00` offset) on the result side; arg-parser continues to accept the legacy `" UTC"`-suffixed format for back-compat. 3. **Float NaN / Infinity results**: `Number::from_f64` returns None for NaN / ±Inf, which `pg_cell_to_json_value` was raising as "invalid json-float" — failing the *entire* query if any cell held one of these special values. Now serialise them as JSON strings ("NaN", "Infinity", "-Infinity") and let the rest of the row come through. Arg-side: `s.parse::<f64>()` already accepts the same strings. Tests: - `decimal_fits_f64_losslessly_predicate` — covers fits / doesn't-fit cases for the precision-loss predicate. - `precision_check_budget_caps_per_query_overhead` — locks in the budget cap and the loss-flag short-circuit. - All 9 PG integration tests + 17 unit tests pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): add pg_advisory_unlock_all to reset; warn on missing args; honor decl defaults While probing PG-script DX further found three more frictions: 1. **Advisory lock leak** (cubic P2): switching from `DISCARD ALL` to `RESET ALL; RESET SESSION AUTHORIZATION; UNLISTEN *; CLOSE ALL;` meant session-scoped advisory locks (`pg_advisory_lock`) leaked across cached-connection reuse. Add `SELECT pg_advisory_unlock_all()` to the chain — `DISCARD ALL` covered this implicitly via `DISCARD PLANS / DEALLOCATE / pg_advisory_unlock_all` and we lost it in the switch. 2. **Missing-arg silent NULL**: an arg declared in the SQL (e.g. `-- $1 amount (numeric)`) but not provided in the args object was bound as NULL with no error / warning. Misspelling the key in the args object silently produced a row of NULLs — a notorious DX debugging trap. Now: collect the names of declared-but-missing args during dispatch and emit a single one-shot warning to the job logs at end-of-query naming each one. Bound NULL is preserved for back-compat. 3. **Declaration defaults ignored**: `-- $1 a (int) = 5` carries `arg.default = Some(Number(5))`, but the dispatch fell straight to NULL when the arg was missing. Now: respect the default — user-supplied value > declaration default > NULL. Also fixes the warning logic above (only warn for args that *don't* have a default). Tests: existing 19 unit + 9 integration pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(pg): multi-word PG types with [] suffix lost the array-ness; array arms accept stringified values Two more frictions found while probing SDK end-to-end against a real datatable resource: 1. **Multi-word array types lose the [] suffix in the parser**. `transform_types_with_spaces` recognises aliases for "double precision", "character varying", "timestamp with time zone", etc. but its return type was `&'a str` — only the bare alias, never with a trailing `[]`. The `RE_CODE_PGSQL` regex's `\w+` captures stop at the first space, so the regex's own `(?:\[\])?` array-suffix branch sees only `"double"` (not `"double precision[]"`); the `[]` was silently lost. Result: `$1::double precision[]` (which the SDK now emits for homogeneous float arrays via the new auto-tag) routed through `Value::Array → Type::JSONB` and the server failed with "cannot cast type jsonb to double precision[]". Fix: switch `transform_types_with_spaces` to return `Cow<'a, str>` and re-check the trailing bytes after a multi-word match. If they start with `[]`, return `format!("{alias}[]")` — Owned. Single-word types and the no-match path keep returning Borrowed slices, so no allocation in the hot path. 2. **Array arms in `convert_vec_val` rejected stringified values for numeric / int* / bool / oid / real / double**. The scalar `convert_val` already parses strings into the matching native type for these arg_ts, but the array variant only accepted JSON-native counterparts. Sending `["1.5", "2.5", "3.5"]` against `$1::numeric[]` (e.g. via `unnest` for bulk loading, or `JSON.stringify(BigInt[])` round-trip) failed with "Mixed types in array". Now the array arms mirror the scalar ones — `as_<native>().or_else(|| as_str().and_then(parse))` — so both shapes round-trip cleanly. Tests: 19 unit + 9 integration pass; existing parser tests cover the multi-word array forms (the regex-cap behaviour didn't break for single-word types, and Cow plumbing is transparent to all callers). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(parsers): add otyp_inferred field to Arg literals in tests + 3 missed src files CI failures: the perl-driven sweep that added `otyp_inferred: false` to every `Arg { ... }` literal when I introduced the field in the parser schema covered `src/lib.rs` files but missed: - parsers/windmill-parser-bash/src/lib.rs (mass-edited but a later format pass un-applied a few sites) - parsers/windmill-parser-go/src/lib.rs (same) - parsers/windmill-parser-graphql/src/lib.rs (same) - parsers/windmill-parser-nu/tests/tests.rs (test file — not swept the first time) - parsers/windmill-parser-ts/tests/tests.rs (test file — same) Also tightened the regex to handle `oidx: None` without the trailing comma (some test files had the field as the last initialiser line). `cargo build --features <CI feature combo> --workspace --all-targets` is clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(sdk): Date → TIMESTAMPTZ; NaN / ±Infinity → string Two more frictions found while running the actual SDK end-to-end against a live datatable resource: 1. **JS `Date`** fell into the typeof "object" branch and was tagged `::JSON`. It worked accidentally for `${date}::timestamptz` via PG's `json → text → timestamptz` implicit cast chain, but `${date}` against a `timestamptz` column without a user-supplied cast bound the value as a JSON string and the comparison `timestamptz = json` failed. Now: `inferSqlType` recognises `Date` and tags `::TIMESTAMPTZ`; `serializeArgValue` emits `Date.toISOString()` so the executor's `Value::String → TIMESTAMPTZ` arm parses it cleanly. 2. **JS `NaN` / `±Infinity`** silently became NULL. `JSON.stringify(NaN)` returns `"null"` per the JS spec, so the value reached the executor as JSON null — the SDK's `::DOUBLE PRECISION` tag then bound a NULL double. Fix: detect non-finite numbers in `serializeArgValue` and stringify them as `"NaN" / "Infinity" / "-Infinity"`. The executor's `Value::String → FLOAT8` arm (`f64::from_str`) accepts these literals directly, and the result-side already renders the values as JSON strings (matching round-trip). SDK unit tests grow from 42 → 44 passing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(pg): integration coverage for multi-word arrays + stringified array elements Locks in the two array fixes from the previous commit (`fix(pg): multi-word PG types with [] suffix lost the array-ness`) with end-to-end cases in `test_postgresql_arg_type_combinations`: - `double precision[]`, `character varying[]`, `timestamp without time zone[]` — verifies the parser keeps the `[]` suffix after multi-word alias resolution. - `numeric[]` / `int[]` / `bool[]` from stringified primitives — verifies the array arms of `convert_vec_val` apply the same string-coercion the scalar arms do. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style: fix indentation drift on otyp_inferred lines cargo fmt cleanup of leftover indentation where the perl-driven sweep that introduced the otyp_inferred field landed at the wrong column. No behaviour change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * feat: support assigning a worker tag to app inline scripts (#9002) * feat: support assigning a worker tag to app/raw-app inline scripts Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix: omit empty tag field from inline script raw_code payload Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * style: shrink tag popover width --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> * feat(pipeline): 2-col picker, draft path edit, save-all + leave guard Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * all * all * update * fix(cli): forward HEADERS env var on every backend fetch call (#9075) Several `fetch()` callers in the CLI bypassed `OpenAPI.HEADERS` and skipped the `HEADERS` env var, causing requests to fail behind auth gateways like Cloudflare Access (same shape as #6421): - `pushScript()` `/scripts/create` and `/scripts/create_snapshot` — regressed in #8936 when the call switched from `wmill.createScript()` (SDK) to a raw `fetch` for the `skip_if_noop` query param. - Script preview `/jobs/run/preview_bundle`. - App dev `/jobs_u/getupdate_sse` SSE stream. - `wmill docs` `/api/inkeep`. All four now spread `getHeaders()` and call `detectAuthGatewayChallenge()` so a Cloudflare/SSO challenge surfaces a clear error instead of an opaque JSON parse failure. Adds `test/headers_env_var.test.ts`: spins up an auth-gateway proxy that 403s requests missing `CF-Access-Client-Id` / `CF-Access-Client-Secret` and otherwise reverse-proxies to the test backend, then runs `wmill sync push` of a fresh script through the proxy. Negative case (no `HEADERS` env) verifies the proxy actually gates; positive case asserts every request including `/scripts/create` reaches the backend with the headers attached. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(cli): add --parallel flag to generate-metadata (#9074) * feat(cli): add --parallel flag to generate-metadata * fix(cli): validate --parallel input and harden flush ordering * perf(flows): skip flow_env DB+transform work when no resolution is needed (#9078) * fix(cli-tests): stabilize flow lock-gen race + Windows path (#9080) * fix(cli-tests): stabilize flow lock-gen race + Windows path Three CLI test failures on the latest main, all flaky on CI: 1. `Mixed Case Paths: pull and push flow with capitalized folder` and `Integration: Mixed scripts and flows with nonDottedPaths are idempotent`: flow create/update queues an async FlowDependencies job that fills inline-script lockfiles and rewrites flow.value. The tests pulled/pushed before the worker finished, so dry-run idempotency saw phantom `*.inline_script.lock` adds and `flow.yaml` edits. Added a `waitForFlowDependencyJob` helper that polls `/flows/get` for the latest `dependency_job` and `/jobs_u/completed/get` until it lands, and called it after each API/CLI flow write in both tests. 2. `HEADERS env var is forwarded on every CLI fetch` (Windows-only, added in #9075): the new test built the CLI entrypoint via `new URL("..", import.meta.url).pathname`, which yields `/C:/...` on Windows and `Bun.spawn` rejected before reaching the proxy, leaving `rejectedRequests.length` at 0. Switched to `fileURLToPath` + `node:path.join` to match `cargo_backend.ts`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(cli-tests): use /flows/deployment_status to actually wait for dep job CI reviewers (Claude, Codex) flagged the prior `waitForFlowDependencyJob` as a no-op: it read `flow.dependency_job` from `/api/w/{ws}/flows/get`, but `Flow` / `FlowWithStarred` (backend/windmill-types/src/flows.rs:20-60) do not include that field. The helper exited on the first iteration without polling. Switch to `/api/w/{ws}/flows/deployment_status/p/{path}`, which returns `{ lock_error_logs, job_id }`. `job_id` is the FlowDependencies UUID written into `deployment_metadata` in the same tx as the dep-job push (backend/windmill-api-flows/src/flows.rs:660-672 and :1275-1292), so by the time the create/update API call returns, the response carries the latest dep-job UUID. Then poll `/jobs_u/completed/get/{job_id}` as before. Local runtime for `mixed_case_paths.test.ts` jumps from ~9s to ~32s, confirming the helper now actually waits instead of returning immediately. The 404 short-circuit in `sync_pull_push.test.ts` still works — `get_deployment_status` returns 404 when the flow is absent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * perf(flows): cache resolved flow_env per flow execution (#9079) * perf(flows): cache resolved flow_env per flow execution * perf(flows): tighten flow_env cache cap to 1024 and clarify memory note * perf(flows): don't cache transient flow_env resolution failures * chore(main): release 1.698.0 (#9076) * chore(main): release 1.698.0 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * fix: reject root-rooted paths in ansible playbook validator on windows (#9081) * fix(native-triggers): serialize Google channel renewal across replicas (#9060) * fix(native-triggers): serialize Google channel renewal across replicas `sync_all_triggers` runs every 5 minutes on every windmill-app replica with no leader election. Multiple replicas were each rotating the webhook token, creating a new Google watch channel, and racing the trigger UPDATE — leaving the loser's new token (in `token`) and channel (in Google) orphaned. Cloud was accumulating ~5 leaked tokens/week without the silent best-effort `delete_token_by_hash` ever logging a warning. Wrap each per-trigger renewal in a transaction and acquire the row with `SELECT … FOR UPDATE SKIP LOCKED`. Contending replicas skip the row instead of duplicating the work. The lock spans `rotate_webhook_token` → Google API call → `update_native_trigger_service_config` and is only released on commit. Re-checks `should_renew_channel` after acquiring the lock so a replica that committed seconds earlier doesn't trigger a duplicate renewal. The pattern matches existing batch-cleanup paths in `monitor.rs` (job-retention sweep) and other `FOR UPDATE SKIP LOCKED` call sites. Also logs at `debug!` when `delete_token_by_hash` finds no matching row, so future investigations can distinguish "deleted" from "not found" without changing the `Ok(false)` contract. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fixup! fix(native-triggers): serialize Google channel renewal across replicas * fixup! fix(native-triggers): serialize Google channel renewal across replicas fixup! fix(native-triggers): serialize Google channel renewal across replicas Address claude review: - #5: per-skip log info -> debug (expected outcome under SKIP LOCKED) - #2: warn moved out of delete_token_by_hash to the call site that knows the expected state (try_renew_channel_locked); other callers are race-prone and shouldn't warn - #3: NULL service_config now warns (anomalous case) - #4: post-Google-API DB-update + commit failures log distinctly so the channel-orphan case is grep-able Plus: add 14d expiry to Google webhook tokens via ServiceName::webhook_token_expiration, mint fresh ephemeral-webhook-{service}-{rd5} labels at create + rotate so the existing 'ephemeral-' filter excludes them from user-token email/critical-alert paths (no filter changes in 3 places). Orphans now self-clean via the existing expiry sweep in monitor.rs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fixup! fix(native-triggers): serialize Google channel renewal across replicas fixup! fix(native-triggers): serialize Google channel renewal across replicas Address second-round review: - Claude #1 (P2): username_override_from_label now strips the 'ephemeral-' prefix for ephemeral-webhook-* labels, so created_by stays webhook-{service}-{rd5} instead of changing to label-ephemeral-webhook-... (preserves audit/job-list filter compatibility) - Codex (P2): updated renew_channel doc — labels are no longer copied; rotate mints fresh ephemeral-webhook-google-{rd5} with 14d expiration - Claude #3 (optional): test_rotate_webhook_token now asserts the rotated Google token has an ephemeral-webhook-google-* label and a populated expiration Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fixup! fix(native-triggers): serialize Google channel renewal across replicas fixup! fix(native-triggers): serialize Google channel renewal across replicas Reconsider the previous fixup: stripping the 'ephemeral-' prefix made created_by no longer match token.label exactly, defeating the linking purpose. Just allowlist 'ephemeral-webhook-' alongside the other recognized webhook/email/ws prefixes — created_by becomes ephemeral-webhook-google-XXXXX, matching token.label exactly. The 'ephemeral-' substring also informs operators that this is a system-managed auto-expiring token vs a user-managed webhook trigger. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(cli): bump svelte version in `wmill app new` template (#9084) * fix(cli): bump svelte version in `wmill app new` template The svelte5 template pinned `svelte` to `5.45.2`, but the Svelte compiler bundled in `wmill app dev` emits `$.delegated('click', ...)` calls. The `delegated` export was added later, so 5.45.2 doesn't have it — esbuild warns `Import "delegated" will always be undefined`, replaces the call with `void 0`, and the page crashes at first event-handler bind (white screen). Bump to `^5.55.5` so the compiler and runtime stay in sync. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(frontend): bump svelte version in raw_apps UI template Mirror the CLI fix: the UI's `Add raw app` flow scaffolds a package.json with `svelte: "5.45.2"`. That works today only because the bundled rolldown worker also pins 5.45.2 — when the worker is upgraded past 5.51.1, the compiler will emit `$.delegated()` and the runtime won't have it, producing the same white-page crash that hit the CLI. 5.55.5 still exports `event` (used by the current bundled compiler), so this is forward-compatible: it works with the 5.45.2 compiler now and won't break when the worker is upgraded. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * perf(flows): gate flow_env resolve on expr text and share cache with handle_flow (#9085) * feat: parse windmill_failure field to tag run as failure (#9073) * feat: parse windmill_failure field in job result to tag run as failure * feat: preserve top-level fields when windmill_failure tags a run as failure * fix: address review findings on windmill_manual_failure * refactor: rename windmill_manual_failure to wm_failure and add wm_* aliases * fix: prefer injected ManualFailure error over sibling name/message in OTel * fix: hide _ENTRYPOINT_OVERRIDE jobs from script/flow history panel (#9088) * fix(flows): populate error handler input args from failure picker (#9087) * fix(flows): populate error handler input args from failure picker * style(flows): fix indentation in failure-step branch * fix(python): verify wheel RECORD on cache pull/install, finalize piptar (#9090) The Python per-package dependency cache could persist an incomplete wheel extraction with `.valid.windmill` set, then propagate that broken artifact to every worker through the object store. Customer hit this on argon2-cffi==25.1.0 (missing argon2/_utils.py), and previously on botocore/httpx (truncated tars). Symptom is a runtime ImportError that looks like a missing dependency declaration rather than a Windmill bug. Three changes that together stop the propagation: 1. After `pull_from_tar`, parse the wheel's `<dist-info>/RECORD` and confirm every listed path exists on disk before writing `.valid.windmill`. On failure, wipe the directory and fall through to a fresh local install — the next install also self-heals the broken object-store entry by pushing a fresh tar. 2. After `uv pip install` succeeds, run the same RECORD check before queuing the piptar upload or writing `.valid.windmill`. A bad install never becomes the source of a broken tar in the object store. 3. Finalize the tar (`drop(tar.into_inner()?)`) before reading its bytes for upload, so we never push an unfinalized archive (no end-of-archive marker) to the object store. Verified with a 60-package end-to-end integration test (first-fill → clear-local-cache → re-pull-from-objectstore → corrupt-objectstore-tar → detect-and-self-heal). All 27 packages on the live test pulled cleanly, and the deliberately corrupted argon2-cffi tar was caught with the exact expected log line ("wheel RECORD lists files missing on disk: argon2/_utils.py") and replaced with a fresh tar. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(main): release 1.699.0 (#9082) * chore(main): release 1.699.0 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * feat(cli): auto-infer args for `wmill app push` (#9091) Run `wmill app push` from inside an app folder (e.g. `f/foo/my_app.app/`) with no args. The local path defaults to CWD, and the remote path is derived from CWD relative to `wmill.yaml`, with `.app`/`.raw_app`/ `__app`/`__raw_app` suffixes stripped. Either, both, or neither positional argument can be passed. Also resolves `file_path` against the user's original CWD before `resolveWorkspace` may chdir to the wmill.yaml root, so a relative `file_path` argument is interpreted from where the user invoked the command (previously it could resolve against the wrong directory). Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * all * fix(pipeline): live-update graph for annotations and body assets * fix(pipeline): persist draft body edits across node switches * fix(pipeline): persist live writes per draft to keep output node fresh after switch * feat(pipeline): animate graph edges only while a runnable is executing * feat(pipeline): add run button on script nodes + recomputing hint on preview * feat(pipeline): compact preview layout, two-way Test/Run sync * fix(pipeline): test button cross-browser placement (no overflow trick) * style(log-viewer): replace took/mem-peak labels with timer/cpu icons * style(log-viewer): hyphenate Auto-scroll label and prevent wrapping * style(log-viewer): lowercase auto-scroll label, force vertical scrollbar * style(log-viewer): force horizontal scrollbar instead of vertical * fix(log-viewer): scope overflow-x to top bar so pre doesn't drive panel width * fix(pipeline): overlay live body-asset writes for persisted scripts too * fix(pipeline): persist inferred body assets at save so edges survive page reload * fix(pipeline): snapshot live draft writes at persist time so they survive reload * fix(pipeline): keep inferred body writes on the canvas across selection changes * fix(pipeline): untrack inferredWrites cache mutation to break effect loop * fix(pipeline): refetch asset graph after persisted-script save * feat(pipeline): optional AI prompt when creating a pipeline script * all * all * test: cover asset-trigger dispatch end-to-end through worker * feat(pipeline): split-button Test with optional downstream cascade * feat(pipeline): cascade option on graph Run + match button heights * style(pipeline): match caret bg/text to Test button's accent-secondary * feat(pipeline): split Run pill on graph node exposes cascade option * feat: live run activity + status badges in pipeline asset graph - folder-scoped queue poll lights up the downstream asset-trigger cascade (not just the launched script); zero requests at rest, catch-up for fast hops, auto-disarm when idle - per-runnable node badge: last-run status + session run count - animate unsaved/live-parsed edges (was unconditionally suppressed) - background-pane click no longer clears selection - run-bridge guarded so node selection/save no longer triggers a test Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: live activity log, optimistic badges, node-avoiding graph edges - collapsible folder activity log (PipelineEventLog): live job feed, polls only while open/active, slow idle cadence, capped + pruned - composable: observe mode + events list + run-count anchored to graph-open time (pre-existing history excluded) - optimistic node badge: launched script shows running instantly via the zero-latency activeRunnable hint, keeps the polled run count - activity pane height capped (min(18rem,40vh)) then scrolls - route asset-graph edges through sugiyama-computed waypoints so they go around nodes instead of under them; bezier fallback for adjacent-layer / draft-overlay edges Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: prefetch all folder script assets so graph is stable on load On pipeline load, eagerly infer body assets for every persisted folder script and seed the existing inferredWritesByPath overlay, instead of only filling it when a node is selected. Scripts whose persisted asset rows are missing (e.g. object-form writeS3File) now have their edges from first paint, so clicking a node no longer re-layouts the graph. One-shot per (workspace, base-graph) load, untracked map reads, generation-cancelled, pool-capped fetches. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * perf: guard no-op poll re-layout; dedupe write-asset extraction - skip reactive ids/states/events reassignment when unchanged, so an idle poll tick no longer re-runs the full sugiyama layout every 3-6s - bound countedJobIds (rebuilt from eventsById in lockstep with prune) - extract shared extractWrites() helper, replacing 4 copy-pasted write-asset filter/map blocks in the pipeline page - compute activeRunnable node-id once, reuse for the active-edge set and the optimistic badge (flattened ternary); trim narrating docs Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: live read-lineage overlay for inferred body assets Renaming e.g. duckdb read_parquet('s3://...') / loadS3File now updates the asset->reader edge live instead of only after Save re-derives the persisted asset rows. - extractReads() (+ shared refsByAccess) mirroring extractWrites - inferredReadsByPath sticky cache, filled by handleAssetsChange and the load prefetch alongside writes - replace the write-only overlay loop with one overlayLineage(map, access) helper invoked for both 'w' and 'r' (net DRY) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: detect S3 assets passed as SDK object arg in ts parser Mirrors merged PR #9181 so feat/asset-graph-view is self-contained (local origin/main is stale and lacks it). Object/{ s3, storage } form of writeS3File/loadS3File is now detected, not only the bare s3:// string literal. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: regenerate wasm Cargo.lock + frontend package-lock Lockfile churn from local wasm-pack (asset target) + npm operations during the asset-graph work. No source/dependency-intent change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: revert to bezier graph edges; add parsing-assets hint The sugiyama-waypoint routing looked worse than the original; revert AssetGraphEdge/assetGraphLayout to the pre-routing bezier logic (same as the flow editor's BaseEdge) and drop the now-unused route plumbing from the canvas. Add a small 'Parsing assets…' hint shown while the load-time prefetch sweep is still inferring folder scripts. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: extract pure resolveGraph merge + unit tests Move the ~230-line graphWithDraft precedence/merge (base < session- inferred < draft-seeded < open-script-live, +read/write/annotation overlays, +dedup) out of the 1648-line route into a pure, testable resolveGraph() module; the route's graphWithDraft is now a thin $derived. Behaviour extracted verbatim. 10 unit tests cover the precedence matrix. Phase 1 of the state/render split. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style: graph controls top-right, lift minimap, hide Save when unchanged Controls -> top-right horizontal, no lock toggle; MiniMap !mb-10 so it clears the activity bar; hide the per-script Save button when the script is already at its latest save point (drafts still show Create). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: scope runtime-asset prune by id to spare static lineage rows prune_runtime_assets deleted by (workspace_id, path, kind) tuple, so trimming surplus usage_kind='job' rows for an s3 path also wiped the static usage_kind='script'/'flow' producer rows for the same path — silently breaking the asset-trigger cascade (fetch_producer_writes found no writes; downstream never dispatched; required band-aid re-syncs). Delete the surplus job rows by id instead; the inner query is already scoped to usage_kind='job'. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: don't re-pulse already-running jobs after they finish The catch-up pulse re-added a completed job to the active set if its start was within the (lagging) lookback window — even one we'd already animated the whole time it ran — keeping its edges lit ~a poll interval past completion (~5s after a 3.5s test). Track job ids seen in-flight and skip the pulse for them; it still fires for hops whose whole lifetime fell between two polls. Bound the set in lockstep with eventsById; cleared on dispose. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: don't catch-up-pulse the runnable launched from the graph If the poll never sampled a launched run's in-flight window, the catch-up pulse re-flashed its edges one tick after it correctly stopped (the page already animated it zero-latency via activeRunnable). arm(launchedId) records the launched runnable id; catch-up skips it. Cascade hops (other ids) still pulse. launchedIds cleared on stop. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style: nudge graph controls left to clear panel toggle Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: partition value resolver + asset-cascade propagation windmill-common/partition: pure resolver — time kinds (tz/format/start anchor) + dynamic $.a.b JSONPath; 9 unit tests. asset_dispatch: read the producer's resolved partition and thread it into every cascaded subscriber's args + trigger.partition, so a chain resolves once at the top. No migration (cascade needs no spec lookup). Stage 1+3 of pipeline partition runtime; run-start resolution is Stage 2. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: show args form in compact pipeline preview when script has inputs AssetGraphDetailsPane keeps the compact (hideArgs) preview but, via a new previewPanel.argsAboveLogs flag, renders a compact SchemaForm between the floating Test button and the logs/result panel when the script declares inputs (e.g. a partitioned script needing a `partition` arg). The preview pane also grows ~18pts so the args form doesn't shrink logs/result. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: parser join-mode (`// trigger all`) + script_trigger.join_all Stage A: JoinMode{Any(default),All} + `// trigger any|all` directive in parse_pipeline_annotations; TriggerSpec::is_partition_bearing() (path contains {partition}); join_mode threaded through all 4 asset-parser crates (ts/py/sql/yaml). Stage B: reversible migration adds script_trigger.join_all; insert_script_trigger writes it; deploy path sets it from the parsed annotation. No reader yet (AND-join dispatch is the next stage) so runtime behaviour is unchanged. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: resolve pipeline partition at job execution time Stage C: in handle_code_execution_job, once the script content is loaded, parse the // partitioned annotation (free here) and resolve the concrete partition once — schedule fire-time (scheduled_for anchor, not wall-clock) for time kinds, triggering payload for dynamic. The value is injected into the in-memory args the body sees (via a shadowed job clone) and persisted back to v2_job.args so dispatch_asset_triggers propagates the same value down the cascade. Already-set (explicit/backfill/cascade) partitions are never re-resolved (run identity immutable); unresolvable partitioned runs fail with a clear error. Integration test exercises the full worker loop + cascade propagation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: AND-join barrier for partitioned pipeline subscribers Stage D: a // trigger all subscriber no longer fires on any input. New join_pending_inputs slot table keyed (workspace, subscriber, partition); fetch_subscribers now returns join_all and the dispatch loop records each partition-bearing input arrival, pushing the subscriber once only when every partition-bearing input it declares is present for that partition. Per-partition slots, cleared on fire (re-accumulate, no double-fire), skew-immune (unlike debounce). Case-3 guard: an unpartitioned producer or a reference (non-{partition}) input never fires a partitioned join. Integration test covers wait/fire/isolation/no-double-fire. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: opt-in // debounce for asset-cascade subscribers (parser + schema) Stage E1+E2. Parser: script-level // debounce <dur> + per-// on debounce=<dur> override (edge wins, else script default, else none = fan-out, unchanged); TriggerSpec::Asset carries the per-edge override; split_trailing_kv_opts separates the ref from trailing key=val opts. Schema/deploy: reversible migration adds script_trigger.debounce_s; parse_duration_secs (bare int or <n>s|m|h|d, fail-safe on garbage) resolves the effective per-edge window at deploy and writes it per row. No reader yet (dispatch wiring is E3) so runtime is unchanged. New unit tests for the parser directive and duration parsing. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: apply opt-in debounce to asset-cascade subscriber dispatch Stage E3. fetch_subscribers now also returns debounce_s; push_subscriber builds real DebouncingSettings (delay + a (subscriber, partition) key, so distinct partitions never collapse and latest-in-window falls out) instead of ::default() when the edge opted in. Default stays no-debounce (fan-out — the prior deliberate behaviour, now overridable rather than reversed). Wiring test asserts the dispatched job carries the configured window/key and an undebounced edge carries none. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix: atomic AND-join gate + preserve resolved partition; drop scratch artifacts Addresses local-review findings before PR: - P1: record_and_check_join_slot was a non-atomic check-then-act on a pooled connection; concurrent completion of a subscriber's last two partition-bearing inputs on different workers could double-dispatch. Now one transaction guarded by a tx-scoped advisory lock keyed on (workspace, subscriber, partition) so the gate fires exactly once. - P2: the preprocessed-args overwrite in result_processor replaced args wholesale, dropping a partition resolved by resolve_partition_for_job; the UPDATE now preserves an existing persisted partition key. - P2: gate resolve_partition_for_job on a cheap code.contains check so non-pipeline script jobs skip the annotation scan on the hot path. - P2: remove 40 scratch screenshot PNGs, a flicker-debug script and a local scheduler lock accidentally committed; gitignore the lock. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * test: AND-join fires once under concurrent upstream completion Regression for the check-then-act race fixed by the advisory-locked transactional gate: releases N producer dispatches simultaneously via a barrier and asserts the AND subscriber is pushed exactly once and the slot is cleared. The invariant holds for the correct gate regardless of interleaving; a non-atomic regression fails it. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * test: fuller partitioned join + multi-hop pipeline coverage Exercises a complex pipeline combining options end to end: two partitioned producers fanning into a // trigger all join, then a multi-hop downstream chain. Asserts the resolved partition propagates unchanged at every hop, chain depth increments per hop, the AND barrier fires exactly once, and a second partition opens an independent slot with no cross-partition bleed across the whole graph. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * refactor: simplify pipeline code per review (dedup, single-parse, constant) - ParseAssetsOutput::new() collapses the 6-line annotation copy-paste across the 4 asset-parser crates to one call site. - asset_dispatch: parse the cascade trigger object once and pass it to the depth/partition readers instead of deserializing it twice; add a TRIGGER_ARG constant for the previously stringly-typed key (3 sites). - scripts deploy: drop a redundant debounce_default clone. No behavior change; 29 parser + 6 dispatch integration tests green. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: reap abandoned AND-join slots after a TTL (default 60d, per-slot) join_pending_inputs slots are normally cleared when the join fires; partial slots whose inputs never all arrive (upstream removed/renamed, one-off dynamic partition key, permanent skew) would otherwise leak. windmill_queue::asset_dispatch::reap_stale_join_slots, called from the monitor's delete_expired_items loop, deletes a (workspace, subscriber, partition) slot only when its MOST RECENT row is older than JOIN_SLOT_TTL_SECS (60d) — per-slot, never per-row, so a legitimately slow join is not corrupted mid-accumulation. Conservative default; per-join configurable TTL via the annotation is a planned follow-up. Test covers stale-reaped / fresh-kept / mixed-slot-kept. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * update * feat: path-less native trigger markers + missing-trigger placeholder * feat: pipeline // tag and // retry annotations + dispatch_event log * fix: derive test-pane min from split-axis dimension (height in bottom layout) * feat: show last run logs/result when a script node is selected * fix: backfill asset rows from script.assets for pre-feature scripts * feat: job-id link + dispatch popover above script log/result * style: drop 'dispatched' label, keep just the check icon * fix: drop tag picker from pipeline script editor (set via // tag annotation) * Nicer UI * refactor: move google ai proxy handling to windmill-ai (#9260) * refactor: add ai proxy execution mode * refactor: move google ai proxy handling * refactor: share google ai request building * fix: early return should consider failure_module result (#9241) * fix(flows): flag noLogs jobs and lazily resolve them in log panel (#9099) * fix(flows): flag noLogs jobs and lazily resolve them in log panel * fix appending to flag * fix: preserve WM_LOGS_SKIPPED sentinel on SSE/replay completion pickMoreCompleteLogs resolved both sentinel and undefined to '', so the SSE completion event (whose job field is fetched .without_logs()) would clobber the sentinel placed by flagSkippedLogs. The module log panel then saw '' instead of the sentinel, defeating the lazy-resolve path. Also wire onLogsResolved on the OutputPickerInner inline LogViewer so a lazy resolve writes back to flowStateStore.previewLogs, matching ModulePreviewResultViewer and avoiding repeated fetches on remount. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(main): release 1.705.0 (#9229) * chore(main): release 1.705.0 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * chore: add playwright mcp for frontend verification (#9269) * feat: CLI datatable serve / psql (#9267) * feat(cli): add datatable list and run commands * feat(cli): render datatable query results as a table * feat(cli): serve datatables as a postgres-wire endpoint * feat(cli): add 'datatable psql' to launch psql against the proxy * feat(cli): route datatable serve by client-supplied database name * override database list + password option * fix: support extended queries in datatable serve * fix: correct cloud size threshold log and parse CLI descriptions with parens/trailing comma * refactor: extract raw_output envelope encoding into pg_raw_output module --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> * oom_adj nit * feat: add UV_PYTHON_INSTALL_MIRROR env and instance setting (#9271) * feat: add UV_PYTHON_INSTALL_MIRROR env and instance setting Allows operators to point `uv python install` at a private mirror of the python-build-standalone releases. Configurable via the `UV_PYTHON_INSTALL_MIRROR` env var or the `uv_python_install_mirror` instance setting, with the env var as the boot fallback and the instance setting taking precedence at reload. Fixes WIN-1966 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: hoist uv_python_install_mirror binding above sandboxing branch The non-sandboxed uv pip install branch referenced a binding that was only declared inside the sandboxed branch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: neutral placeholder for uv_python_install_mirror The previous placeholder was the default public URL the setting is meant to redirect away from. A neutral example mirror URL is clearer. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(indexer): tell admins when ingress routes search to wrong pod (#9274) * [ee] fix(indexer): tell admins when ingress routes search to wrong pod When the IndexReader is absent on the pod handling a search request but another pod is actively holding the indexer lock, the EE handler now returns a tailored error pointing at the ingress/load-balancer configuration instead of the generic "indexer not running" message. The indexer status endpoint reads the DB lock so it reports "running" from any pod, but search endpoints need the in-memory IndexReader that only exists on the lock holder. In multi-replica deployments this looks like the indexer is healthy but every search 404s. Companion: windmill-labs/windmill-ee-private#TBD Fixes WIN-1968. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref to eb18d7b4c0e37fea3f6e1e2cc44e0fddd74ff817 This commit updates the EE repository reference after PR #586 was merged in windmill-ee-private. Previous ee-repo-ref: 7dd43d1850813071cc18ba49ba090583e7321f4b New ee-repo-ref: eb18d7b4c0e37fea3f6e1e2cc44e0fddd74ff817 Automated by sync-ee-ref workflow. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> * feat(cli): add `wmill init prompts` and custom override slot (#9266) * feat(cli): add `wmill init prompts` and custom override slot Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(cli): replace init prompts with refresh prompts + AGENTS.md/AGENTS.cli.md split Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(cli): dedupe claude skills via @-includes and add prompts freshness check Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(cli): drop migration-choice flags from `refresh prompts` Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(cli): add 'Running and previewing local changes' section to AGENTS.cli.md Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(cli): write full skill content to .claude/, drop @-include wrapper Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(cli): reconcile CLAUDE.md the same way as AGENTS.md Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(cli): address PR review nits — argv parsing, lazy import, comment detection, error propagation Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: add yolo mode for ai chat tools (#9258) * feat: add yolo mode for ai chat tools * nit * fix: align chat footer controls * feat: add ai chat autonomy modes * feat: add autonomy mode dropdown * fix: highlight yolo autonomy icon * fix: auto accept flow edits * fix: hide unsupported autonomy modes * fix: handle auto-accept flow editor races * fix(debugger): add non-root user support to Dockerfile (#9277) Mirrors the main Windmill Dockerfile pattern: creates a windmill user (UID/GID 1000) and makes cache/work directories world-writable so the image runs cleanly under Kubernetes securityContext.runAsNonRoot or runAsUser: 1000 without permission errors on Bun, pip, or windmill cache writes. Fixes WIN-1969 Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(ai): enforce RLS and scope check on user-supplied X-Resource-Path (#9276) * fix(ai): enforce RLS and scope check on user-supplied X-Resource-Path The AI proxy handler accepts an X-Resource-Path header to override the configured workspace AI provider. When supplied, the handler loaded the resource value from the resource table using the root DB pool with no resources:read scope check, so any authenticated workspace user could point X-Resource-Path at a restricted AI resource (e.g. one in a folder they cannot read) and the proxy would use that resource's provider credentials for the outbound AI request. For user-supplied resource paths, now require resources:read:{path} scope and fetch the resource through user_db.begin(&authed) so RLS enforces the same folder/group boundary as the resource API. The RLS- scoped $var: resolution stays in place as defense in depth. The admin-configured workspace/instance ai_config path is unchanged. Fixes WIN-1971 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(ai): regression test for X-Resource-Path RLS enforcement Cover all four cases: - non-admin pointing X-Resource-Path at a restricted resource is rejected - non-admin pointing it at a resource they own still works - admin can point it at any resource - workspace-configured proxy flow (no X-Resource-Path) is unchanged Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: add userdraft listing primitives (#9268) * feat: add userdraft listing primitives * fix: cancel stale userdraft discard writes * docs: remove global ai userdraft plan * feat(nsjail): optional disk-backed /tmp via instance setting (#9272) * feat(nsjail): optional disk-backed /tmp via instance setting * test(nsjail): unit-test tmp mount resolver and narrow visibility * refactor(nsjail): switch tmp backing to select + conditional UI * ui(nsjail): make tmpfs the visible default in /tmp backing select * fix(nsjail): refuse preexisting jail_tmp to block symlink escape * fix(nsjail): allow jail_tmp reuse on sequential nsjail calls Codex flagged that python/ruby/rust executors invoke nsjail twice per job_dir (install then run). The previous resolver treated any preexisting jail_tmp as hostile and silently fell back to tmpfs on the second call, so disk-backed mode never reached the main script run for those langs. Use symlink_metadata().is_dir() to distinguish a real directory left by an earlier call in the same job_dir (safe to reuse) from a symlink or other entity (still refused, as the codebase-tar escape requires). Also loosen the frontend visibility predicate: only hide nsjail settings when job_isolation is explicitly 'none' or 'unshare', so deployments that enable nsjail via DISABLE_NSJAIL=false with no DB setting can still see the controls. * chore(main): release 1.706.0 (#9270) * chore(main): release 1.706.0 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * fix(nsjail): gate unix-symlink test behind cfg(unix) for Windows build (#9280) The disk_backed_refuses_preexisting_symlink_at_jail_tmp test calls std::os::unix::fs::symlink directly, which doesn't exist on Windows targets. Without a cfg gate, `cargo check --tests` fails on Windows with E0433. Other symlink call sites in this crate (php_executor, bun_executor, rust_executor, etc.) already follow this pattern. Fixes WIN-1972 Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Reduce slim image vulnerability surface (#9279) * Reduce slim image vulnerability surface * chore(docker): drop apt-get upgrade -y from slim images apt-get upgrade hurts build reproducibility (same Dockerfile + same commit at different times produces divergent images) and trips hadolint DL3005. The freshness it buys is dominated by simply rebuilding against the periodically-refreshed debian:bookworm-slim base image. The --no-install-recommends and apt-list cleanup wins are kept. --------- Co-authored-by: Ruben Fiszel <ruben@windmill.dev> * fix(git-sync): bump to hub/28234 with stateless gpg.program wrapper (WIN-1974) (#9282) * fix(git-sync): revert LATEST_GIT_SYNC_SCRIPT_PATH to hub/28230 to restore GPG-signed deploys (WIN-1974) hub/28231 (PR #9230) is the "thin" script that hands the actual `git commit` to the CLI's hidden `sync git-deploy`. The hub script still does the GPG setup (import key into a fresh GNUPGHOME, dummy `gpg -bsau` to warm the agent passphrase cache, then `git config user.signingkey` + `commit.gpgsign` locally), but the commit no longer runs in the same `git_push` flow — it runs minutes later inside the CLI after workspace API resolution, zip pull, file extraction, and lockfile autofill. By the time the spawned `git commit` asks gpg-agent for the cached passphrase, the cache state is no longer reliable (or the spawned `gpg` ends up talking to a fresh agent), so signing fails non-interactively with `gpg failed to sign the data`. hub/28230 is hub/28217's in-script logic rebuilt with windmill-cli@1.703.3: the GPG setup and the in-script `sh_run("git commit ...")` happen back-to-back in `git_push`, so the cache is always fresh. It preserves wm_deploy / fork branch behavior, the EE deployment-callback `main()` signature is unchanged, and the only min-version check in EE (`is_script_meets_min_version(28103)`) is comfortably below 28230 — so this revert is safe. Forward fix (separate PR): publish a new thin script that, alongside the existing GPG setup, writes a `gpg.program` wrapper using `--pinentry-mode loopback --passphrase-file` so signing is independent of the agent's cache state. Re-bump past 28231 then. Fixes WIN-1974 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(git-sync): check in source-of-truth for the next hub script (gpg.program wrapper) This is the script that will be published to hub.windmill.dev once verified on a customer GPG-signed deploy. It replaces hub/28231's agent-cache pre-warm (`gpg -bsau` with --passphrase) with a stateless gpg.program wrapper + chmod-600 passphrase file. Every git-invoked gpg call goes through the wrapper, which always uses --pinentry-mode loopback (and --passphrase-file when a passphrase exists). Signing no longer depends on gpg-agent having a cached passphrase by the time the CLI's `git commit` runs — which closes WIN-1974. Not wired in yet: LATEST_GIT_SYNC_SCRIPT_PATH stays on hub/28230 until this script is uploaded and the new hub id is known. This file is checked in so the diff is reviewable, future bumps have a source of truth, and a CLI regression test can `cat` it for fixture parity. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(frontend): skip format/pattern validation for $var/$res/$jsonvar references in ArgInput A resource field with a `pattern` constraint (e.g. the gpg_key.private_key field, whose pattern enforces a `-----BEGIN PGP PRIVATE KEY BLOCK-----` prefix) rejects values like `$var:u/me/gpg-private-key` with an "invalid format" error in the resource editor — even though `$var:`/`$res:`/`$jsonvar:` are placeholders the backend resolves at runtime, not the actual string that needs to match the regex. Bail out of all format/pattern checks (email, ipv4, ipv6, uuid, custom pattern) when the value is one of these references. Required/numeric bounds/array checks still apply since they're shape-level, not regex. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(git-sync): bump LATEST_GIT_SYNC_SCRIPT_PATH to hub/28234 (gpg.program-wrapper fix) hub/28234 is the forward fix for WIN-1974: replaces hub/28231's agent-cache pre-warm (which became stale by the time the CLI's `git commit` ran) with a stateless `gpg.program` wrapper that uses `--pinentry-mode loopback` (and `--passphrase-file` when a passphrase exists) on every gpg invocation. Bundled CLI is windmill-cli@1.705.0. Verified via reproducer at /tmp/git-sync-diff/test-gpg-fix.sh: deliberately killing gpg-agent between GPG setup and `git commit` reproduces the customer's `gpg failed to sign the data` error verbatim under the old flow, and the wrapper signs through it. Holds for passphrase-protected keys, split-subkey [C]+[S] layouts, and unprotected keys. Drops the local source-of-truth copy (`hub-scripts/`) — hub is canonical now that 28234 is published. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(git-sync): drop verbose comment above LATEST_GIT_SYNC_SCRIPT_PATH The git history (this PR) carries the why; the constant name + value carry the what. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(cli): wmill sync git-deploy stops committing; caller owns commit+push (#9284) Single contract for the deployment-callback path: the CLI does branch checkout + pull, the caller (hub script in production, test in test) does git add + commit + push. This restores the WIN-1974 invariant — GPG setup and `git commit` run back-to-back in the same process, so the agent's pre-warmed passphrase cache is still warm at sign time — without needing a `--skip-commit` flag for the hub case and a default "also-commit" for everything else. Same behavior in every call site. Changes: - sync.ts: drop the gitSyncDeployPush call from pull()'s deploy path (both the onlyCreateBranch fast-return and the post-pull commit). `gitSyncDeployPush` stays exported for any caller that wants the same commit/push semantics — just not invoked by the CLI subcommand. - gitsync_promotion.test.ts: e2e test now does its own git add + commit + push after `wmill sync git-deploy`, mirroring what the hub script does in production. Same regression coverage (wm_deploy branch created in Case A, main untouched; main updated in Case B, no new wm_deploy). CLI typecheck unchanged (two pre-existing TarAsZip errors at lines 2578/3307, present before this PR). All 743 unit tests still pass. The accompanying hub script (option-C — CLI for branch+pull, script for commit+push) lives at /tmp/git-sync-diff/sync-script-to-git-repo-windmill.option-C.ts. Once published, a follow-up bumps LATEST_GIT_SYNC_SCRIPT_PATH to its id. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * bump git sync to 28236 * fix: fork compare visibility for non-admins and stale-token superadmins (#9283) * fix: use fork-scoped authed for fork visibility in compare_workspaces * test: add EE end-to-end repro for fork rename visibility * chore: restore concurrency_locks sqlx cache lost in cleanup * test: add regression for stale-superadmin-token fork visibility bug * chore: update sqlx cache for new test queries * chore(main): release 1.706.1 (#9281) * chore(main): release 1.706.1 * Apply automatic changes --------- Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> * feat: add wmill job rerun subcommand (#9275) * feat: add wmill job rerun subcommand * feat: add wmill job restart subcommand for flow restart-at-step * chore(system_prompts): point plugin skills sync at plugins/windmill/ (#9287) * chore(system_prompts): point plugin skills sync at plugins/windmill/ The plugin checkout's plugin folder is being renamed from `plugins/windmill-code-plugin/` to `plugins/windmill/` to shorten the slash-command namespace and align with the matching Cursor plugin layout. Paired with windmill-labs/windmill-claude-plugin#8. That PR must merge first so the next sync run finds the new folder. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(system_prompts): update plugin-dir example to plugins/windmill Co-authored-by: centdix <centdix@users.noreply.github.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: centdix <centdix@users.noreply.github.com> * fix(cli): wmill sync pull updates wmill-lock.yaml for raw apps (#9289) * fix: flow recording teardown crash + rename package to @windmill-labs/components (#9288) * fix: guard against null recording during FlowRecordingReplay teardown Navigating away from a flow recording inside a workspace file-tree view threw `TypeError: Cannot read properties of null (reading 'flow')` from FlowGraphViewer once during the teardown tick. Svelte 5 compiles child component props as live getters that close over `$$props.recording.flow`. When `recording` flips to null on the parent's navigation, an outer `{#if !recording?.flow}` doesn't stop those getters from firing one more time as derived effects re-evaluate before the unmount lands — so the getter dereferences null and throws. Fix at the two layers where the deref actually happens: - FlowRecordingReplay: use `recording?.flow` at the binding sites (FlowViewer + graph-snippet FlowGraphViewer) so the compiler emits an optional-chained getter, and guard the snippet branch with `{:else if recording?.flow}` so it doesn't mount when there's nothing to show. - FlowGraphViewer: finish the optional chaining the rest of the file already used everywhere else (`flow?.value?.skip_expr`, `flow?.value?.cache_ttl`, `flow?.schema`). When the upstream binding returns undefined during teardown, the graph degrades to an empty frame instead of crashing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: rename package to @windmill-labs/components - frontend/package.json: rename `windmill-components` → `@windmill-labs/components` - frontend/publish.sh: drop the in-place sed rename dance; the checked-in name now matches what's published, so `npm run package && npm publish` is enough - frontend/package-lock.json, system_prompts/auto-generated/prompts.d.ts: regenerated by `npm run package` under the new name Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * default script name * save logic * Keyboard nav * finish keynav * nits * CI fix * nit stop propagation * Merge branch 'main' into feat/asset-graph-view * commit * update * fix: cropped save button on small screens * progress * managed scheduled removed * all * progress * feat: add data upload pipeline trigger with auto S3 picker Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: avoid pane editor remount flicker when deploying a pipeline draft Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: show only the edited script's I/O in the asset graph, not the saved version's Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: derive script asset rows server-side at deploy Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: shared fixture corpus keeps annotation parsers in parity Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: dev-run draft pipeline chains, live badges, deploy drift warning Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: ungate cascade producers, squash pipeline migrations Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: drop committed cli-sync fixtures and stray screenshots Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: show skip-asset-dispatch flag as badge instead of args row Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: pipeline view mode default with activity feed, drafts overlay chip Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: treat DROP TABLE as table-level write in sql asset parser Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: wmill datatable create + actionable sql extension error Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: ephemeral data-pipelines demo sync repo zip for handoff Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: wmill pipeline list/show renders the asset DAG in the terminal Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * nits * nits * nits * nits * fix: defer draft persist-back past the batch so discard sticks first click Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: band-reserving tidy-tree asset graph layout with join breakpoints Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: route skip-layer and long graph edges around occupied columns Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: seed s3 template outputs with canonical leading-slash paths Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * all * feat: bundle data-pipeline drafts into the DB-backed user draft system Pipeline drafts were browser-only (localStorage `pipeline-<folder>`), so they didn't sync across devices, weren't server-visible, and never showed in the drafts list. Store them instead as one per-user `draft` row of a new `data_pipeline` kind, keyed at the folder (`f/<folder>/data_pipeline`), holding the same `{ drafts, activeDraftPath }` bundle. Stage 1 — backend kind: add `data_pipeline` to DRAFT_KIND (migration) and `UserDraftItemKind` (deployed_table=None, private). The list/update handlers and folder-path access check already cover a backing-table-less kind. Stage 2 — sync: add `GET /drafts/get_own/{kind}/{path}` so an editor with no deployed-overlay GET can load its own draft. The pipeline page now hydrates from the DB on mount (one-time localStorage import for in-flight drafts) and persists via UserDraftDbSyncer (debounce + optimistic-concurrency), keeping a localStorage crash mirror. Stage 3 — surface: the drafts review page renders the bundle as a "pipeline" row that opens `/pipeline/<folder>` (open-only; excluded from bulk deploy). Verified end-to-end in-browser: DB-seeded draft hydrates to "Edit (1)", edits persist back, and the row shows with Open pipeline / Discard. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: pipeline Activity panel grouping, run↔graph highlight, deploy-conflict handling Activity panel (view mode): - Group cascade runs by the connected component of the asset-dispatch graph (new GET /jobs/asset_dispatch_edges over the dispatch_event table, incl. join_pending inputs), headed by the earliest originating run + its trigger, with a "+N" chip for joins fed by multiple triggers. - Success/failure count histogram with drag-to-filter brushing, an always-on time axis + per-bar tooltips, a Reset, and Last hour/24h/48h/7/30/90d ranges. - Node run-count/status badges now derive from the same merged historic+live events the panel shows (previously session-only). Run ↔ graph highlight: - Hovering a run row (or a group header → the whole cascade) rings the node(s), animates their incident edges, and borders the adjacent assets in the edge hue (blue write / gray read); expanding a run pins a soft-blue ring. - Switching edit→view re-surfaces the Activity feed. Deploy: - Live-content autosave for the open pipeline draft + an autosave indicator. - Re-saving a script now chains off the hash just created instead of a stale parent_hash (fixes the "lineage must be linear" error on a second save), and a genuine concurrent deploy opens a keep-mine / view-latest conflict modal. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: pipeline editor badge requires asset-parse, not just main-function parse A pipeline script's asset lineage is load-bearing — a deploy that can't parse assets silently records no edges. The editor "parsable" dot only reflected inferArgs (the main function), so a body the asset parser rejects (e.g. a trailing `/////` in DuckDB) still showed green and deployed with empty lineage. ScriptEditor gains `requireValidAssets` (set by the pipeline pane); when on, the EditorBar badge is green only if BOTH the main function and inferAssets parse, with the tooltip distinguishing "Main function not parsable" / "Assets not parsable" / "Parsable". Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: route asset-graph edges around nodes that sit in their path Edges could draw straight through an unrelated node (a join fan-out or long cross-component edge), making it ambiguous whether that node shared the input. AssetGraphEdge only saw its own endpoints, so it could only detour the near-vertical same-column skip case. The canvas now (once per layout, O(edges × nodes) — no per-frame cost) samples each edge's straight run against every non-incident node center and, on a crossing, passes a clear gutter lane to the edge via `data.detourX`; AssetGraphEdge routes the rounded-orthogonal detour through it. Verified: 0 edge↔node box crossings on the orders pipeline. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: deploy pipeline drafts with freshly-inferred assets, not a stale snapshot "Save all" spread `...draft.script` into createScript, which carries a `assets` snapshot that isn't refreshed when the body is edited. So a renamed/removed output (e.g. an old `CREATE TABLE exciting_en32z9` later changed to `exciting_880909`) was re-deployed as a phantom write edge and lingered as an orphan asset on the graph — shown with no producer, and shifting position on click as the graph re-derived. saveDraft now re-runs inferAssets on the current body and passes the result as `assets`, overriding the snapshot — mirroring the per-pane save. The backend clears+reinserts from the sent set, so a re-deploy drops the stale rows. Verified: deploying with the fresh asset set removes the orphan from the graph. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: collect upstream reads from CTAS and CREATE VIEW in SQL asset parser `CREATE TABLE x AS SELECT … FROM y` (and `CREATE VIEW`) recorded only the write to x — the source read of y was silently dropped. Table-level reads are gathered in the `Statement::Query` arm via handle_table_with_joins; the generic table-factor visitor only picks up read-functions and string literals, not plain `FROM <table>` references. The AS-query of a CTAS isn't a `Statement::Query`, so its FROM tables were never walked. On the pipeline canvas this meant a `datatable://…` upstream consumed by a CTAS step showed no read node/edge — the step looked like it produced its output from nothing. Factor the Query arm's read collection into handle_query_reads and call it from the CreateTable (when it has an AS-query) and CreateView arms, balancing the cte_name_stack push in post_visit_statement. Updated the drop_then_create test (which had pinned the old drop-the-read behavior) and added CTAS + CREATE VIEW read coverage. Verified against the rebuilt asset wasm: the live editor now infers the read. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * update * updates * refactor: dedup asset-graph code, squash migrations, drop artifacts Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * perf: gate asset dispatch on a cached per-workspace producer set Cache the producer-path→writes map per workspace and invalidate it from the asset-clear paths via the notify_event polling system, so a top-level script/preview completion that isn't an asset producer costs an in-memory lookup instead of a per-completion query. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: remove dead unquote fn that failed backend check under -D warnings Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: green the frontend check (pin published wasm-asset, fix type errors) Pin windmill-parser-wasm-asset to the published 1.728.1 (was a file: link to a gitignored, CI-unbuilt pkg-asset). Exclude test files from svelte-check (the parity test reads a backend fixture via node:fs, which the browser app tsconfig has no @types/node for; vitest still runs them). Fix pre-existing branch type errors: drop the unsupported 2nd getScriptByPath arg, cast script.schema to Schema for inferArgs, coerce has_preprocessor to a definite boolean, and wrap the cancelJob handler so it isn't possibly-undefined. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: move pipeline partition resolution to ee-private (free-CE) Partition resolution becomes a private module (partition_ee in windmill-ee-private, hidden from the public repo) with an OSS no-op fallback (partition_oss); call sites resolve via the aliased windmill_common::partition. Not enterprise-gated — free to run in CE. Bumps ee-repo-ref to the ee branch carrying partition_ee. Verified building in default, private, and private,enterprise (offline). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: move asset-cascade join/debounce/retry to ee-private (free-CE) Join barrier, debounce, and retry become the private windmill_queue::cascade module (cascade_ee in windmill-ee-private); OSS gets cascade_oss no-op fallbacks (plain OR fan-out). Core cascade stays public. Bumps ee-repo-ref. Verified default/private/private,enterprise. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: skeleton enterprise pipeline freshness + backfill (TODO, ee-private) Gated windmill_common::pipeline_advanced (private; pipeline_advanced_ee) with OSS fallback; entry points return a clear not-implemented error. Deploy surfaces a TODO when a script declares // freshness. Bumps ee-repo-ref. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: repair asset_trigger_dispatch test after cascade carve-out + cache its queries Stage-2 moved reap_stale_join_slots to windmill_queue::cascade; update the integration test's import. Also commit the test's sqlx query cache (was never prepared with --tests, so SQLX_OFFLINE cargo test failed pre-existing). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test: invalidate producer-cache in asset dispatch tests (mirror deploy) The tests seed asset rows directly and run no notify poller, so the per-workspace producer cache went stale across tests → 0 dispatched. Clear it at the seed point, as a deploy would via notify_event. All 8 asset_trigger_dispatch tests pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: update ee-repo-ref to ba677ea142011462ad4dfe77e8375a6dd274cdef This commit updates the EE repository reference after PR #619 was merged in windmill-ee-private. Previous ee-repo-ref: 925c350cff55d3ea738d9e2e4098d9ce4bdda418 New ee-repo-ref: ba677ea142011462ad4dfe77e8375a6dd274cdef Automated by sync-ee-ref workflow. * test: disable producer cache in asset dispatch tests (isolated-DB safe) The .remove(WS) approach still raced: #[sqlx::test] gives each test its own DB but they share one workspace id, so the WS-keyed process-global cache clobbered across DBs under concurrent threads. Add an ASSET_PRODUCER_CACHE_DISABLED test hook and set it in the tests so every dispatch reads its own DB. 8/8 pass at --test-threads=10. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: replace asset-cascade depth cap with cycle detection The hardcoded MAX_CHAIN_DEPTH=5 truncated legitimate deep pipelines (silently — the check returned before event logging). Replace it with per-edge cycle detection: carry the producer lineage in trigger.chain and skip only a subscriber already in the chain, recording a visible cycle_detected dispatch_event. Acyclic pipelines of any depth now cascade fully; a high MAX_CHAIN_LEN backstop guards against runaway. Tests + UI label updated; 8/8 pass at --test-threads=10. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: update dispatch_event reason examples (depth_cap → cycle_detected) Comment-only; the migration is idempotent and already in the potentially_stale self-heal list, so the checksum change re-applies cleanly. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: park cascade retry (P1 dead-end) + clear stale script_triggers on rename Two deploy-path fixes: - Retry is parked: a retried subscriber is wrapped in a SingleStepFlow, whose run is a flow step and ineligible for asset dispatch, so it would silently dead-end the cascade (P1). Stop persisting retry to script_trigger and warn at deploy; TODO(pipeline-retry) to re-enable once dispatch handles flow-wrapped producers. (Dispatch plumbing kept + still tested via direct seeding.) - Rename leaves stale script_trigger rows: clear was keyed on ns.path only, so old-path '// on' edges lingered and could trigger a script later recreated at that path. Also clear the old path on rename (assets already handled via the parent-hash clear). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: rubenfiszel <275584+rubenfiszel@users.noreply.github.com> Co-authored-by: hugocasa <hugo@casademont.ch> Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com> Co-authored-by: Arnaud <31803803+Araden14@users.noreply.github.com> Co-authored-by: Diego Imbert <diego@windmill.dev> Co-authored-by: centdix <40307056+centdix@users.noreply.github.com> Co-authored-by: Diego Imbert <70353967+diegoimbert@users.noreply.github.com> Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Aldrin Jenson <aldrinjenson@gmail.com> Co-authored-by: centdix <centdix@users.noreply.github.com> |
||
|
hugocasa
|
676e907ea6 |
docs: replace dead 0x0.st with gh-based PR screenshot recipe (#9512)
* docs: replace dead 0x0.st with gh-based PR screenshot recipe Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: harden PR screenshot recipe (filename, secrets, CI fallback) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
hugocasa
|
192574ab8f |
fix(forks): keep trigger/schedule operational state owned by the parent - WIN-2019 (#9476)
* fix(forks): defer trigger/schedule state to parent for clean git merge Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(forks): read parent trigger/schedule state on non-RLS pool for complete substitution Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(forks): read schedule fork-ness on non-RLS pool; clarify mutator-rule wording Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Ruben Fiszel
|
7590b28108 |
feat(sandbox): pull/extract images with crane instead of podman (#9455)
* feat(sandbox): pull/extract images with crane instead of podman (+ add to image)
The sandboxed container runtime (`# sandbox <image>`) only ever pulls + flattens an
image (nsjail does the run), so a full container engine is overkill — and podman was
never actually in any Dockerfile, so the merged feature couldn't run in the shipped
image. Switch to crane (google/go-containerregistry): a single ~25MB static binary,
no daemon/store/root/privileged.
- docker_v2.rs: crane export -> flattened rootfs tar, crane config -> OCI config,
crane digest -> content-addressed rootfs+config cache (cross-job dedup + automatic
freshness), crane manifest -> pre-download size guard. DOCKER_CONFIG authfile dir.
Cache eviction prunes the rootfs-tar cache by mtime (LRU). Pull policy honored via a
ref->digest cache (missing/never reuse without a registry hit).
- Dockerfile + docker/DockerfileSlim{,Ee}: install the crane binary (Full/FullEe and
the EE image inherit it via FROM the base image).
- docs + UI text + instance-setting descriptions updated (download size is compressed;
cache is the rootfs-tar cache).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(sandbox): address CI review — digest-pinned fetch, size cap on every job, eviction race
Codex P1s:
- Fetch by the resolved digest (name@digest), not the mutable tag, so content can't
diverge from the digest the cache is keyed under if a tag moves mid-fetch.
- Enforce the size cap on EVERY job via a cached {digest}.size sidecar (no registry call
on cache reuse), so lowering the limit rejects already-cached oversized images.
- Eviction race: hardlink the cache tar into the job dir before tar -xf (pins the inode
against concurrent eviction) and re-fetch if it was evicted first.
Claude P2s: atomic config sidecar (tmp+rename) + tolerate torn parse; soften the LRU
comment (mtime = creation order); sweep orphaned *.tmp.* and .size on eviction.
+digest_key/ref_key unit tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(sandbox): P1 cross-fs cache staging (EXDEV), Dockerfile arch fail-fast
CI re-review (Claude + Codex P1): the eviction-race hardlink crosses filesystems in the
shipped deployments — the cache is its own volume (/tmp/windmill/cache) while the job dir
is on the container fs — so hard_link returns EXDEV (not NotFound) and every sandbox job
fails. Fall back to tokio::fs::copy on a non-NotFound link error; copy reads through the
source inode so it still survives a concurrent eviction.
Also: Dockerfiles fail fast with a clear error on an unsupported arch instead of building
a 404 crane URL; ref->digest file written via tmp+rename (no torn read under missing/never).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(sandbox): say 'oldest by creation time' not 'LRU' for cache eviction
Codex P2: the code evicts by tar creation time (cache hits don't touch mtime), so the
user-facing docs + instance-setting text shouldn't claim true LRU.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|
Ruben Fiszel
|
1727271e19 |
feat: sandboxed daemonless container runtime via '# sandbox <image>' (#9453)
* feat: add sandboxed docker v2 runtime via '# docker <image>' Run a container image as a subprogram of the job's own nsjail sandbox: extract the image rootfs with podman (rootless) and run it chrooted inside the job's nsjail, so the container inherits the job's confinement and is safe under nsjail / for untrusted code. Selected by '# docker <image>'; a bare '# docker' keeps the v1 (dind) path untouched. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: default to daemonless docker (drop dind from compose, allow docker on cloud) docker-compose no longer ships the dind sidecar (v2 is daemonless: podman + nsjail in the worker); removed the dind service, DOCKER_HOST env, depends_on and volume. Removed the language-picker guard that blocked Docker scripts on the multi-tenant platform, now that v2 makes docker safe to run sandboxed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat: select sandboxed container via # sandbox <image>; add pull policy + size guards - Surface moved from '# docker <image>' to '# sandbox <image>' (groups under the sandbox annotation; '# docker' stays v1-only, '# sandbox' stays nsjail-bash). - SANDBOX_IMAGE_PULL_POLICY (default 'newer') so moving tags don't go stale. - SANDBOX_IMAGE_MAX_SIZE_MB rejects oversized images before extraction. - SANDBOX_IMAGE_CACHE_MAX_MB best-effort LRU eviction of podman's image store. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(sandbox): support # volume, honor nsjail tmp instance settings, v2 docker template - Thread shared_mount into the sandbox container nsjail config so '# volume' mounts (and the same-worker /tmp/shared folder) apply inside the container. - Use resolve_nsjail_tmp_mount_block for the container's /tmp so it honors the same nsjail_tmp_backing / nsjail_tmpfs_size_mb instance settings as other nsjail jobs. - docker-compose comment + the editor's Docker template now use '# sandbox <image>'. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(sandbox): make image size/cache/pull-policy UI instance settings Convert SANDBOX_IMAGE_* from worker env vars to DB-backed instance settings (sandbox_image_max_size_mb, sandbox_image_cache_max_mb, sandbox_image_pull_policy), hot-reloaded via the same mechanism as nsjail_tmpfs_size_mb and configurable in #superadmin-settings. No worker restart needed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(sandbox): windmill-managed registry — default registry + private auth Two new instance settings: - sandbox_image_default_registry: prepended to unqualified image refs (alpine -> <registry>/alpine); fully-qualified refs untouched. - sandbox_registry_auth: docker/podman auth.json blob written to a per-job authfile (0600, removed with the job) and passed to podman --authfile for private registries. Both hot-reloaded and configurable in #superadmin-settings. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sandbox): protobuf-safe proto_str escaper, atomic 0600 authfile, registry tests Addresses local-review P2s: proto_str now emits valid protobuf octal escapes for control/non-ASCII bytes (not Rust \u{..} that nsjail would reject); the registry authfile is created 0600 atomically (no world-readable window); add a registry_qualified table test + a non-ASCII proto_str case. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sandbox): P0 — deliver image env via nsjail envar:, never the launcher process env CI review (P0): the image's OCI Env (attacker-controlled keys+values) was applied to the nsjail launcher process via .envs(), so a hostile image could set LD_PRELOAD/ LD_LIBRARY_PATH/LD_AUDIT on nsjail itself and execute code as the worker outside the jail. Now the image env is rendered as proto-escaped 'envar:' directives (child-only) and nsjail's process env carries only windmill-trusted keys (reserved vars + proxy). Also: warn instead of silently bypassing the size guard on inspect failure; reset the eviction guard via a Drop guard (no stuck flag on panic/early-return). +render_envars test. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sandbox): P0 symlink-write escape via rootfs script; P1 redact registry-auth logging CI review: - P0 (Codex): the body was written into the image-controlled rootfs as .windmill_docker_main.sh via write_file (follows symlinks) — a hostile image could plant that path as a symlink to a host file and capture the worker's write before nsjail starts. Now the body is passed straight to 'sh -c <body> sh <args>'; no file is written into the rootfs at all. - P1 (Codex): sandbox_registry_auth flowed through the generic setting loader which logs the value (raw auth.json credentials). Replaced with a secret-aware reload that loads directly and logs only a redacted 'configured=' message. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sandbox): redact sandbox_registry_auth in instance-settings write log too The settings API also logs 'Set global setting <key> to <value>' via format_setting_value; add sandbox_registry_auth to SENSITIVE_SETTINGS so the credential is redacted there as well as on reload. * fix(sandbox): don't silently disable cache eviction on podman images parse error Re-review (cubic/Claude P2): serde_json::from_slice(...).unwrap_or_default() meant any parse hiccup (e.g. podman omitting Size/Created via omitempty for a zero value, or schema drift) silently degraded to an empty Vec and disabled eviction with no log. Now Size/Created are #[serde(default)] (a missing omitempty key -> 0, not a whole-array parse failure) and a real parse error warns + breaks instead of being swallowed. --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
 centdix
|
a7d85a39ff |
refactor: clean up ai provider proxy logic (#9360)
* refactor: clean up ai provider proxy logic * docs: remove completed ai refactor plan * fix: audit failed google global proxy calls |
||
|
centdix
|
9752f0f909 | docs: remove stale planning notes (#9342) | ||
|
centdix
|
4be930f585 |
refactor: unify AI provider credentials (#9317)
* refactor: use provider credentials for worker builders * refactor: resolve api proxy credentials directly * fix: lazy load frontend eval modes |
||
|
centdix
|
c96be0e903 |
refactor: move bedrock proxy handling to windmill-ai (#9309)
* refactor: move bedrock proxy handling to windmill-ai * docs: track ai refactor follow-ups |
||
|
centdix
|
289549a048 |
refactor: move google ai proxy handling to windmill-ai (#9260)
* refactor: add ai proxy execution mode * refactor: move google ai proxy handling * refactor: share google ai request building |
||
|
centdix
|
bd32c5f951 |
refactor: move openai-compatible proxy building (#9133)
* refactor: introduce ai proxy request types * refactor: move openai-compatible proxy building |