* feat(ai-chat): workspace ai_skill table + CRUD API
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): AI Skills workspace settings tab with SKILL.md upload
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): advertise skills in global system prompt + read_skill tool
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): move custom skills into AI settings (paste or folder)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): cap folder import (depth<=3, max 50 skills, confirm dialog)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* style(ai-chat): give import folder its own labeled subsection
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): resolve svelte-check never-narrowing in skills preview
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: address ai skills review issues
* fix: validate ai skills and reload workspace list
* fix(ai-chat): spec-align skill validation and cap skills per workspace
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): reject duplicate skill uploads, audit skill names
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): sync deref openapi specs with skill validation rules
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci: add path-gated AI agent integration tests workflow
Runs integration_tests/ai_agent_tests against real LLM providers
(Anthropic/OpenAI/Google) only when AI-agent backend code or the tests
change, since runs make paid LLM calls. Adds a conftest fixture that
skips provider-parametrized cases whose API keys are absent, so CI
exercises only the providers it has secrets for.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci: add path-gated ai_evals global-mode smoke workflow
Runs the global AI chat eval (global-test1) across one cheap model per
provider (Anthropic/OpenAI/Google/DeepSeek) only when the eval harness or
copilot chat code change, since runs make paid LLM calls. Builds Windmill
CE from source as the AI proxy; global tools/drafts run in the Vitest
bridge. Gates on the deterministic draft pipeline (run succeeded +
produced a draft + used write_script), not the variable LLM judge score.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci: run AI smokes on PR ready-for-review instead of every push
Switch the pull_request trigger from `synchronize` (every commit) to
`ready_for_review`, with a job guard skipping draft PRs, so the paid LLM
runs only fire when a PR is marked ready to merge (plus push-to-main and
manual dispatch).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai_evals): lazily load cli mode so non-cli evals skip the cli toolchain
The entrypoint eagerly imported modes/cli, which pulls the wmill CLI
guidance modules and their JSR deps (@cliffy/*). Global/flow/script/app
runs then crashed with "Cannot find module '@cliffy/ansi/colors'" when
the cli workspace deps were not installed. Import createCliModeRunner
dynamically inside runCliBenchmark instead.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai_agent): raise low max_completion_tokens to OpenAI's 16 minimum
OpenAI's /v1/responses rejects max_output_tokens < 16 with a 400, failing
test_low_max_tokens for openai. 16 still exercises a truncated response.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci: run ai_evals workflow on Node 22 for the frontend undici 8.x dep
The Vitest bridge loads frontend/node_modules/undici@8.x, which requires
Node >=22.19; Node 20 failed with "webidl.util.markAsUncloneable is not a
function" when loading vitest.config.ts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai_evals): run frontend evals autonomously + give global-test1 more turns
Frontend evals (flow/script/app/global) ran the production chat prompt, which
assumes an interactive human — so cheaper models burned their turn budget
asking for confirmation, waiting for approval, or presenting a plan, sometimes
hitting maxTurns without producing a draft. Append a shared autonomy note in
baseEvalRunner (the path all frontend modes share, mirroring cli mode): act
directly on clear requests; only ask on genuinely ambiguous ones (preserving
the askUserQuestion cases). Also raise global-test1's maxTurns 8 -> 10 so a
model that over-explores still converges.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ci(ai_evals): watch draft/prompt deps outside copilot/
The global eval runs production frontend code in-process, so the smoke's
behavior depends on files outside frontend/src/lib/components/copilot/**:
the draft model (userDraft.svelte.ts, userDraftDbSyncer.svelte.ts), script
inference (infer.ts), and the chat system prompts ($system_prompts ->
system_prompts/auto-generated). Add them to both push and PR path filters so
a change there actually triggers the smoke that gates on draft production.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: skip direct provider tests without credentials
* feat: add ai evals skip judge flag
* fix: simplify ai evals ci gate
* fix: simplify ai evals smoke gate
* fix: handle ai eval workflow triggers
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add global-mode path-selection eval cases with seeded user
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(copilot): guide global-mode path selection with injected folder list
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(copilot): tailor global-mode folder guidance for workspace admins
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(copilot): type folders_read; isolate global-eval user from store
Addresses PR review:
- Add folders_read to the User/whoami openapi schema and UserExt; the global prompt builder and eval harness now read it typed instead of via inline casts (regen the client to pick it up).
- prepareGlobalSystemMessage takes an explicit user; the eval harness passes it rather than mutating the process-global userStore, removing the concurrency race (path cases no longer need --verbose).
- Rewrite the path-selection case comment as a current invariant.
- Add buildFolderGuidance unit tests in core.test.ts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: add global AI chat context-optimization plan for raw apps
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): add global raw-app debugging cases on a large fixture
Adds a ~20-file analytics_dashboard raw-app fixture (incl. a 5k-line data module
and a planted wrong-totals bug), two global cases (read-heavy debug + small-edit
baseline), app-seed support in the mock backend, directory-fixture loading, and a
decorateHelpers seam so read-dedupe is measurable. Records tokenUsage for before/
after comparison of the read-tool optimization.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): cap and dedupe read_app_file to bound context in large apps
read_app_file now defaults to a head slice (1500 lines / 50k chars) with offset/
limit to page further, and skips resending a file whose earlier read is still in
context (per-conversation ledger keyed off the originating tool-call id, so it
self-heals after compaction). Bounds the file-content portion of global-chat
context when working in large raw apps.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): add read-heavy raw-app debug case (large data module)
global-test31 induces the model to inspect the 5k-line seedData module, exercising
the read_app_file cap/offset path. Baseline ~262k tokens vs ~200k with the cap+dedupe
change (-24%).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: record A+B benchmark results and fixed-overhead finding
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): clearer read_app_file past-EOF message + unit tests for cap/dedupe
Addresses local-review nits: out-of-range offset now reports 'offset N is past the
end of the file' instead of a backwards 'lines 11-10' label; adds unit coverage for
the slicing (line cap, offset/limit window, char budget, past-EOF) and re-read dedupe
(hit + miss-when-not-retained).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): char-level paging + per-range dedupe for read_app_file
Adds char_offset/char_limit so minified/long-line files can be paged within a line
window, keys the re-read ledger by range (so reading different ranges no longer
collides), and dedupes on the full-file hash (a cached range stub is invalidated
when any byte of the file changes, not just the returned range). Tests updated for
the char-slice behavior plus single-line capping, char paging, and out-of-window
change detection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-chat): add read_app_file context micro-benchmark + re-read eval case
Adds a deterministic micro-benchmark (no LLM) that drives read_app_file through a
realistic big-project read pattern (large file, re-read, minified bundle, paging)
and asserts the cap+dedupe cut returned context >50% vs the old whole-file behavior
— isolating the feature's effect from model nondeterminism and guarding against
silent weakening. Adds global-test32, a cross-file consistency investigation that
revisits overlapping files so re-read dedupe is exercised in a real run.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): clarify test32 measures the read cap, not dedupe
Verified: sonnet and haiku both read each file once per conversation and retain
it, so test32 never triggers read_app_file re-read dedupe. Dedupe is measured
deterministically by the micro-benchmark instead. Comment corrected to match.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): drop read_app_file re-read dedupe, ship the cap only
Benchmarking showed the per-conversation re-read dedupe never fires in practice:
across sonnet/opus/gpt-5.5/haiku, every model reads each file once per conversation
and keeps it in context (0 within-conversation re-reads). It was a correct but unused
guard, so this removes the ledger, full-file hash, retention predicate, the
AIChatManager wiring, and the eval decorateHelpers seam — keeping the read cap +
offset/limit/char paging (A), which is the lever that actually bounds context. The
micro-benchmark is now cap-only; test32 is kept as a multi-file read-load case.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): add search_app grep tool for global raw-app chat (experimental)
Client-side grep over a raw app's frontend files and inline runnables (literal,
case-insensitive, optional file_glob/context_lines/max_matches, head-capped).
Completes the list -> search -> ranged-read triad. Includes the eval A/B gate
(WMILL_AI_EVAL_DISABLE_SEARCH_APP), unit tests + micro-benchmark, and a
find-all-usages eval case (global-test33).
Experimental: A/B benchmarking shows it is not an unconditional win — it helps
on find-all-usages but adds agentic iterations on navigable apps.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): accept search_app as a valid file-inspection tool in raw-app cases
Add requiredToolsAnyOf alternatives-group to ToolValidationSpec and switch
global-test29..32 to it so a model that locates files via search_app instead
of read_app_file no longer false-fails the tool assertion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: remove stale ai-chat context-optimization planning doc
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): drop read_app_file char paging for a hard char cap
The char_offset/char_limit params guarded minified files (a single line over
the char budget) but were effectively unused in benchmarks. Remove them and the
in-window char paging; keep the hard 50k-char budget and, when a read hits it,
tell the model to narrow the line limit (or treat the file as unreadable if a
single line exceeds the budget). Proper long-line handling is left as a TODO.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): bake search_app context to 1 line, clarify query is literal
Drop the context_lines param (models varied it to little effect) for a fixed
SEARCH_APP_CONTEXT_LINES=1, and cap on matching lines instead of pushed rows so
max_matches stays accurate with context always on. Sharpen the query description
to state it is a literal (non-regex) substring and to suggest the call form
(e.g. formatCurrency() to hit call sites and skip formatCurrencyPrecise.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): widen baked search_app context to 2 lines
Models that set the old context_lines param leaned to 2; match the lean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): count every file with a match in search_app header
Move fileHadMatch ahead of the render cap so files whose matches fall past max_matches are still counted (with a regression test). Also swap the raw NUL globstar sentinel for a printable escape (the NUL bytes made core.ts read as binary to grep) and reword two comments to describe current constraints instead of drafting history.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): drop redundant input echoes from app tool results
read_app_file and search_app no longer prefix results with the tool name or echo back the caller's own inputs (file path, query, file_glob) — the model already has them from the call args, and the unbounded query echo could push the search result past its output budget. Keeps the useful signals (line range, match/file counts, truncation) and the actionable advice. Also reword max_matches to 'matching lines' since it caps lines (each expands to context rows). Unit tests updated to the new format.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Drop empty/unknown `type` values (Windmill emits `type: ""` for untyped fields) and infer `type: array` for nodes carrying `items`, so generated MCP tool schemas validate against JSON Schema draft 2020-12. Anthropic's tool registration rejected the whole tool list otherwise.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
finishAppDraftWrite returned `item: result.item`, whose `value` is the entire
app draft (every frontend file body and inline runnable). Each write_app_file /
patch_app_file / write_app_runnable therefore re-sent the whole app back to the
model; on a large app a few edits overflow the 200k context window.
This restores #9530 (which removed the echo) — the DB-backed-draft refactor
(#9601) reintroduced it by routing all app writes through this shared helper
with `item:` re-added. Write results now return only `{ success, message }`,
matching the flow write tools. Adds a regression test asserting the value is
not echoed.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Record finalContextTokens per attempt: the input-token total of the last
model request (input + cache-creation + cache-read), i.e. how full the
context window ended up. Complements the cumulative tokenUsage.prompt,
which conflates context size with loop-iteration count.
Captured generically in the shared frontend runEval via the chat loop's
lastIterationUsage, so it covers all frontend modes (global/flow/script/
app), plus CLI mode via the last assistant turn's usage. Aggregated as
average and max over passed attempts and printed in the run summary.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): summary-based conversation compaction
Replace drop-oldest compaction with summary-based partial compaction: when
a send would cross the context-window trigger, summarize the older prefix
into one message and keep the recent tail verbatim, replacing the prefix in
both the model context and the visible transcript with a collapsible
boundary. Drop-oldest remains a fallback; a circuit breaker disables the
summary round-trip after repeated failures.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* nit
* fix(ai-chat): address review findings on summary compaction
- Stop during an in-flight summary no longer falls through to a destructive
drop-oldest compaction. The aborted controller short-circuits the fallback
and its save, so the cancel path rolls the unsent turn back cleanly instead
of permanently dropping older history (P1).
- Preserve the original chat title across compaction: once the summary
boundary leads the transcript, reuse the title computed before compaction
rather than re-deriving it from the first surviving tail message (P2).
- Strip every <analysis> block from the model's summary, not just the first,
so extra scratchpad blocks can't leak into context (P2).
- Reindent AIChatMessage.svelte / ContextUsageIndicator.svelte (prettier).
Adds regression tests for the abort path, title preservation, and
multi-analysis stripping.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* nit
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(frontend): add user-level toggle to disable Windmill AI
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(frontend): hide AI sessions sidebar section when AI is disabled
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: remove deprecated enable_1m_context from AI provider code
1M context is now standard on Anthropic models — the beta header
`anthropic-beta: context-1m-2025-08-07` is no longer needed.
Remove the field from ProviderCredentials and AnthropicQueryBuilder,
and stop injecting the beta header in both the API proxy and worker
query builder paths.
The field is kept (as `_enable_1m_context`) on the ProviderResource
deserialization structs in both windmill-api and windmill-ai so
existing resources with the field still deserialize without error.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: drop vestigial _enable_1m_context field from AI resources
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: assert legacy enable_1m_context keys still deserialize
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: track real ai chat token usage and show context indicator
* fix: keep context anchor full-history accurate after trimmed sends
* nits
* feat: restyle context indicator and disable trim for unknown windows
* feat: hide context indicator below 50% usage when window is known
* fix: gate 1M claude context window to sonnet/opus 4.6+
* refactor: import context window helpers from modelConfig directly
* fix: keep base gpt-5 models at 400k context window
* fix: exclude date-suffixed claude 4 ids from 1M window gate
* refactor: replace context window heuristics with explicit model table
* fix: account for context overhead in trim loop stop condition
* fix: re-base context anchor when mode switch changes system prompt or tools
* refactor: replace context estimation with usage-report-driven compaction
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: chars/4 fallback for context usage when provider reports none
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: remove unused slide import failing svelte-check
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: re-seed context usage estimate on rewind so retry can compact
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor: lazy read-side estimate fallback for context usage
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: fix reasoningRegistry mock to match resolveRequestReasoning
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix: stop sending temperature for AI chat across all providers
Remove the temperature field from all AI chat completion requests and
drop the model-based send-or-not special-casing. Previously the chat sent
temperature: 0 for determinism and omitted it for reasoning models
(claude-opus-4-7/4-8, gpt-5+, o-series) that reject sampling params, which
required hand-maintaining a growing model list.
The model-detection helper is kept (renamed modelDisallowsSamplingParams ->
requiresMaxCompletionTokens) since it still serves a separate concern:
choosing max_completion_tokens over max_tokens for OpenAI/Azure reasoning
models on the Chat Completions API.
The FIM autocomplete temperature: 0 is intentionally left untouched (it is
the code-autocomplete path, not the chat).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor: drop dead claude-* branches from requiresMaxCompletionTokens
After temperature removal, requiresMaxCompletionTokens only governs the
max_completion_tokens vs max_tokens choice for OpenAI/Azure reasoning
models (its sole call site is gated on provider === openai|azure_openai).
The retained claude-* branches were leftovers from when the function
omitted temperature for Anthropic reasoning models; they are unreachable
for the max_completion_tokens decision and made the kept detection tests
assert a semantically false claim. Claude reasoning behavior is owned by
reasoningRegistry. Drop the dead branches and their tests so name, comment,
code, and tests agree. Behaviorally inert.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat: add get_app_runtime_logs tool to global chat
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: only handle raw app backend messages from the runner's own iframe
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: add list_app_runs tool to global chat for raw app backend runs
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor: simplify raw app chat tool results
* nits
* nits
* chore: bump ui builder artifact
* fix: resolve pending runtime log requests on cleanup
* fix: harden raw app runtime log requests
* nits
* fix: show raw app tool results in status
* fix: cap raw app runtime log results
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: make default chat model optional in AI settings
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: stop auto-seeding default chat model on provider enable
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai): add list_runs and get_job_logs tools to global chat mode
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai): always suppress ansi hint in get_job_logs, drop misnamed param
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai_evals): add global list_runs and get_job_logs eval cases
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* style(ai): trim get_job_logs description and format global core
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai): surface list_runs/get_job_logs output as tool result
The tools set showDetails but never set message.result, so the details panel rendered "No result yet" even on success. Set result in setToolStatus (logs go in result for get_job_logs).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add datatable tool coverage to global ai_evals (stage 0+1)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add seeded datatable difficulty-ladder global ai_evals (stage 2)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: skipJudge datatable evals and make stringIncludesAnyOf existential
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: make ai_evals datatable mock reflect SQL writes
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: add workspace datatable tools to global AI chat mode
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: cover global-mode datatable tools pure logic
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: expose datatable SQL SDK reference via get_instructions in global mode
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: make datatable get_instructions language-aware, default TypeScript
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor: drop datatable/whitelist args from global init_app tool
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: flag missing datatable config as an explicit blocking error in global mode
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor: drop dead branch in exec_datatable_sql result handling
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: add global ai chat test tools
* fix: avoid session id in flow test preview
* test: cover global flow preview ids
* test: require script and flow test tools
* fix: harden global flow test fallback
* Revert "fix: harden global flow test fallback"
This reverts commit 97254ef33a.
* fix: fallback from inactive flow test hook
* fix: list nested flow steps in errors
* 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>
* feat(ai-chat): link workspace paths and show tool item references
Detect Windmill paths (u/..., f/...) in assistant messages and render
them as clickable pills with the right icon, resolved against a per-
workspace cache. Tool execution headers now list the script/flow/app
paths referenced in tool parameters as external links.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(ai-chat): linkify inline-code paths, refine pill styling
- Inline-code spans whose value is exactly a Windmill path now render
as a link pill (paths inside larger inline code or fenced blocks
stay as code).
- Tool-header chips moved to their own row to avoid overflow clipping
when the title wraps.
- Borderless pills, no default background (hover only), kind icons
use the home-page palette (script blue, flow teal, app orange),
and the external-link indicator only appears on hover.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(ai-chat): linkify variables/resources/triggers + inline drawer
- Workspace item registry now also lists variables, resources, schedules,
and all 10 trigger kinds; resource wins over variable on path collisions
(Windmill auto-creates a companion variable for every resource).
- Pill icons delegated to the canonical RowIcon component so each kind
matches the home-page styling (script blue, flow teal, app orange,
resource boxes, schedule calendar, etc.).
- Pill href includes the hash fragment each list page already consumes
(#/resource/<path>, #<path> for variables/schedules/triggers), so
opening the link puts the user on the list page with the matching
editor drawer already open.
- For variable and resource pills, a hover-revealed side-panel button
opens (or toggles closed) the editor drawer inline next to the chat,
without navigating away. VariableEditor and ResourceEditorDrawer gain
a closeDrawer() export and forward their close event so the host can
drive toggling.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor: simplify ai chat workspace item links
* refactor: keep ai chat path linkification only
* perf: avoid eager ai chat path cache loads
* refactor: simplify ai chat path linking
* feat: open ai chat path links in drawers
* refactor: homogenize workspace item kinds
* fix: toggle ai chat item drawer
* refactor: trim ai chat path cache
* fix: cancel ai chat drawer reopen
---------
Co-authored-by: Guilhem Lemouel <guilhemlemouel@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* docs: add global ai mode plan
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add global ai draft mode
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: scope global ai mode to scripts and flows
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: simplify global ai workspace item shape
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: split global ai write tool into per-type tools
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add global ai schedule and trigger workspace item tools
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add dev-only /global_drafts route to inspect ai draft store
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add edit_script and patch_flow_json global ai tools
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add deploy_workspace_item global ai tool with confirmation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: emit open-resource action card after deploy_workspace_item
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add delete_workspace_item global ai tool with confirmation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore(system_prompts): emit RESOURCES_BASE and resource/variable zod schemas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add global ai resource and variable workspace item tools
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: search_resource_types uses listResourceType to avoid embedding feature dep
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Revert "fix: search_resource_types uses listResourceType to avoid embedding feature dep"
This reverts commit 6d1d19514a.
* feat: emit open-resource action card for variable and resource deploys
* feat: add global ai raw app workspace item tools
* feat: split raw-app prompt into chat-only authoring and cli prefix
* feat: add init_app global ai tool to scaffold raw apps from templates
* fix: pass write_flow value as JSON string for gemini compat
* refactor: hoist countExactMatches and applyExactReplace to chat/shared
* refactor: extract editableFlowJson module shared with global mode
* fix(global): preserve flow schema and groups across draft and deploy
* feat: extract inline scripts from flow reads and patches in global mode
* refactor: add findAndReplace helper for match-validated text patches
* refactor: extract getInlineRunnableContent helper for app file tools
* refactor: extract assertNotGeneratedAppFile guard for /wmill.d.ts
* feat: gate global ai mode behind localStorage flag for dev rollout
* chore: bump svelte to ^5.55.5 in raw app template (sync with main)
* fix: isolate global ai draft rollout
* fix: preserve global ai deploy metadata
* fix: harden global ai draft tools
* chore: remove global ai plan doc
* fix: align raw app prompt guidance
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* docs: refine windmill ai refactor plan
* refactor: move ai sse plumbing to windmill-ai
* refactor: remove ai re-export shims
* fix: update ee ai memory ref
* chore: update ee-repo-ref to d3bc7fa85195b46b7a38d43c2f806520bf8b5454
This commit updates the EE repository reference after PR #560 was merged in windmill-ee-private.
Previous ee-repo-ref: ff35bf7cc198e13884b33654e1d6dbd8a8b314d3
New ee-repo-ref: d3bc7fa85195b46b7a38d43c2f806520bf8b5454
Automated by sync-ee-ref workflow.
---------
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* feat: add ai chat resource action buttons
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: avoid proxied drawer state equality
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: show tool action cards
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add workflow-as-code skill
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: make system prompt freshness self-contained
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Revert "fix: make system prompt freshness self-contained"
This reverts commit 7d2fde9585.
* fix: refresh wac generated guidance
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add wac cli eval cases
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: align wac prompt imports
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* fix: slim app ai chat context
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: remove stale app chat selection UI
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: trim app chat selected context
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: trim app chat context coverage
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: remove app tool assertion
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add ai agent chat output flag
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: suppress ai agent tool chat messages
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: rename ai agent conversation output flag
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: expose ai agent conversation output toggle
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: gate ai agent chat tab by chat mode
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: regenerate system prompts
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: address ai agent chat review feedback
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: support windmill chat answer override
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: remove output fallback from chat override
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: handle non-string chat answer overrides
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: add flow conversation token scope
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: make flow conversations scope plural
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: update flow chat service import
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: skip opus 4.7 sampling params
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: keep opus 4.7 handling frontend side
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: generalize opus 4.7 model matching
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: stop normalizing opus 4.7 thinking
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: create windmill-ai crate and move base AI types from windmill-common
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: move worker AI types to windmill-ai crate
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: move QueryBuilder trait and StreamEventSink abstraction to windmill-ai
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: add base64 dependency to windmill-ai for bedrock PDF support
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add windmill-ai refactor plan
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: address PR review — remove dead bedrock feature, add boxed_sink helper, move plan to docs
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add cli eval behavior checks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: harden cli eval command parsing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add proxy transport for ai evals
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: strip propertyNames for gemini schemas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: require explicit eval transport
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: make flow chat code edits explicit
* refactor: centralize flow tree lookups
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: simplify flow chat tree mutations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: reuse flow tree lookup in schema map
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: remove flow lookup alias
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: reuse flow tree in previous results
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: reuse canonical flow module lookup
* fix: align rebased flow helpers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* docs: remove flow chat cleanup plan
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: remove flow chat helper wrappers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: preserve non-flowmodule AI agent tools in skeleton and previous_result
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: consolidate flow module ID collectors into flowTree
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: search full flow tree in test_run_step to find special modules
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: recurse into aiagent tools in collectAllFlowModuleIds
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add homepage connect drawer
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: reset connect drawer state
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: polish home connect button
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: use standard home connect button style
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* chore: record app benchmark baseline
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: strengthen app benchmark persistence checks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: seed inventory tracker benchmark case
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add deterministic app diagnostics
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add app chat patch_file tool
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add app session id micro-edit case
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: narrow app patch file content
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: stop gating app evals on lint
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: use compact json for flow patches
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: improve flow eval harness
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: record flow benchmark history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: preserve schema in set flow json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* style: clean set flow json schema guard
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: clean flow patch review followups
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: avoid persisting system prompts in ai memory
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: keep ai memory cleanup write-side only
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add bedrock prompt caching for claude
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add bedrock memory regression
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: gate bedrock prompt caching by model id
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* docs: link bedrock caching allowlist source
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: support special flow modules in evals
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: extract shared flow helper logic
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: make special flow tools openai-compatible
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: improve flow eval prompts and validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: relax flow benchmark overfits
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: record updated flow benchmark history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: address flow review findings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: source flow chat special module prompt
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: narrow rawscript helper return type
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: dedupe flow chat prompt guidance
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: relax flow test10 validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add backend preview validation to ai evals
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: refresh shared preview workspace assets
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: harden shared backend preview validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: extract flow delete helpers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: unify flow delete planning
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: stabilize flow delete execution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: simplify flow delete plan execution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: restore ai agent tool deletion
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: reduce ai tool delete tree walks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
centdixandClaude Opus 4.8
