* feat: optional reason when denying an approval
* fix: keep the full deny reason in the audit entry
* fix: name the denial reason in the payload guard and document error.reason
* feat: tuck the deny reason behind an add a reason link
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: ask for the deny reason in a popover on deny
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: label the run page cancel action cancel step
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* feat: cap concurrent branches of a parallel branch-all step
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: reject a zero parallelism cap and regenerate flow guidance
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* feat: mark mocked and skipped steps in the flow run view and step logs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep the skipped badge to what the run state can tell
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: skip the mocked badge on expanded subflow steps
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor: keep only the step log lines for mocked and skipped steps
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: let flow step mocks apply to preview runs only
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: apply the test-runs pin default when pinning from the flow graph
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: choose a pin's scope from the pin and show pins where they apply
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: build the pin scope menu on the standard split button
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* fix: keep gitsync-settings override from writing into a fork's parent entry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep a fork's gitsync-settings override in its parent's entry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: refuse unknown roles and stale operator_settings in settings apply
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep omitted-key clears when a push only removes a workspace role
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: load instance roles on the held connection in the settings document
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: resolve gitsync-settings wmill.yaml entry by workspace, not branch
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: write gitsync-settings pull overrides to the resolved workspace entry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: refuse ambiguous gitsync-settings override target instead of guessing
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: never adopt a branch entry that names another workspace on override
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: refuse gitsync-settings override when the workspace resolves to no entry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep the branch binding in the gitsync-settings override refusal hint
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: pin git-sync hub scripts to windmill-cli 1.862.1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add max iterations and max duration bounds to while loops
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: fail exhausted while loops regardless of skip_failures and prior recovery
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: state that a while loop's duration limit can overrun by one iteration
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: let the while loop iterations field be cleared and retyped
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* feat: filter workspace webhook events by type
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: carry webhook_events through workspace rename and cli settings sync
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update sqlx cache for workspace rename
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add category presets to the webhook event filter
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: reject an empty webhook event list and document editWebhook's url field
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: hint when every webhook event is selected and check presets cover all types
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: make event categories the main webhook filter control
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(cli): suggest known instance URLs in workspace add
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci: retry bun setup in cli tests after a release download outage
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: flow-level wall-clock timeout
* chore: regenerate flow schema prompts after rebase
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: claim timed-out flows before cancelling, scope the handler to the expired flow
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor: scope the flow timeout to root flows
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor: drop flownode from the flow timeout sweep
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: apply a flow's timeout when it runs as a subflow step
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: align subflow timeouts with script timeouts and let the ai chat set them
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: give a calling step the timeout error whether or not the subflow has a failure module
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* refactor: point the pipeline editor prompt at the shared pipeline guidance
* fix: keep a read-side annotation summary for sessions that cannot write drafts
* fix: count non-BMP characters once when naming a default table in the canvas and cli
* fix: teach pipeline nodes to attach the lake and read real columns
* test: run the data pipelines ai evals build against a real ducklake
* test: run only fed-by-nothing pipeline nodes and record run failures
* feat: name a materialized table after its script when the target names none
* fix: inspect pipeline columns read-only and cap the eval run's roots
* test: cap the roots of the tables-named-after-steps eval
* fix: keep flow steps and explicit targets out of the materialize default
* fix: name the table of a script run from a flow, recover bare materialize in the cli
* ci: point eval workers at the installed bun and serve native scripts
* fix: keep inline step tests out of the materialize default, recover bare scd2 in the cli
* chore: drop formatter-only changes from the materialize default diff
* fix: let a referenced-script step test name its table after the script
* fix: tell inline step tests apart by the missing script hash, not the path
* fix: teach pipeline nodes to attach the lake and read real columns
* test: run the data pipelines ai evals build against a real ducklake
* test: run only fed-by-nothing pipeline nodes and record run failures
* fix: inspect pipeline columns read-only and cap the eval run's roots
* ci: point eval workers at the installed bun and serve native scripts
- settings.yaml carries `role_overrides`, the workspace's per-role overrides and
workspace-only roles, applied as a whole after the legacy `operator_settings`.
- users/*.user.yaml carries the member's workspace role by name, so a custom role
survives `wmill sync pull` and `wmill sync push`; `admin` is still the admin flag.
- The User API schema documents the `role` field the endpoints already return.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: reference existing HashiCorp Vault secrets from secret variables
A secret variable can hold `$external:vault://<path>#<key>` instead of a
value. The reference is resolved from Vault each time the variable is
read, so the value is never stored in Windmill. An instance-level
allow-list of path prefixes, optionally per workspace, is checked when a
reference is saved and again when it is resolved. Other schemes are
parsed and refused as unsupported backends.
Adds AppRole as a Vault auth method, an "External reference" toggle in
the variable editor and an instance settings section for the connection
and the allow-list.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: point ee-repo-ref at the external secret references branch
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep external secret references intact on delete, deploy and export
- Deleting a reference no longer runs the managed backend cleanup, which
could delete the secret it points at.
- Deploying a variable to another workspace copies the reference, which
the target's allow-list then checks, instead of its resolved value.
- A plain-secrets workspace export writes references verbatim.
- Reference paths reject backslashes, `#` and control characters, which
the URL parser would otherwise normalize past the allow-list.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: skip external secret references in key rotation and the read cache
- Workspace key rotation no longer tries to decrypt references.
- `get_value?allow_cache=true` does not cache a resolved reference, so
Vault rotation and allow-list changes apply on the next read.
- `VaultSettings.mount_path` is optional in the OpenAPI spec, matching
its serde default.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: keep the OSS Vault reader stub public and regenerate workspace tool schemas
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: restrict external secret references to workspace admins and keep them out of the managed Vault storage
Creating, repointing or removing a reference now takes a workspace admin, on
create and update including already-encrypted pushes and cross-workspace
deploys; the variable form disables the toggle and fields for anyone else.
A reference into the storage of Windmill's own Vault secret backend (same
address, namespace folded into the path) is refused on save and on resolve,
whatever the allow-list says.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: compare external secret references as written in workspace comparison
Two references that currently resolve to the same value still point at
different secrets, so comparing their resolved values hid a repoint from the
diff and from deployment.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: let external secret references reuse the Vault backend connection
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: hide the external reference toggle from non-admins unless already set
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: read whole Vault secrets, show allowed paths, and pick the variable type in one control
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: mask JSON fields only for whole Vault secrets, and skip PEM armor and JSON lines
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: align the reference editor and settings warning with the form and alert guidelines
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: let a saved reference become non-secret directly, and warn when no prefix is allowed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: save an empty value when a reference is switched to another type
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep a saved reference's baseline through type round trips
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: drop an unused binding in the reference parser
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: offer vault reference only when a vault path is allowed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update ee-repo-ref to c0fd22ba77e6618cea7611d72fe2e75c8855c595
This commit updates the EE repository reference after PR #932 was merged in windmill-ee-private.
Previous ee-repo-ref: 56cba4e7771e7a87e56a67eb115549a31dd12b1a
New ee-repo-ref: c0fd22ba77e6618cea7611d72fe2e75c8855c595
Automated by sync-ee-ref workflow.
---------
Co-authored-by: Claude Opus 5.5 <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>
* feat: add read-only generic HTTP secret store backend
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep forks and oauth tokens working under the http secret store
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: redact http store credentials, refuse workspace id changes over references
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: refuse invalid http secret store settings when they are saved
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: update http store form readers after in-place edits
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: keep the ai config comment above its hook arm
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update ee-repo-ref to 235a17b0ffe64a77bc816b8c38270437d3596674
This commit updates the EE repository reference after PR #935 was merged in windmill-ee-private.
Previous ee-repo-ref: 3c46237920cc20fc4ab34bd07d0773f761aa63d2
New ee-repo-ref: 235a17b0ffe64a77bc816b8c38270437d3596674
Automated by sync-ee-ref workflow.
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
Windows forbids '*' in a file name, so creating it failed the test on the
Windows CLI runner. The :(literal) pathspec guard it covers is
platform-independent and stays exercised on Linux and macOS.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): drop deprecated and unused fields from trigger new templates
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): flow preview takes the windmill path and runs hub steps with --step
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): run a deployed script step with its deployed lock in flow preview --step
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): flow preview --remote honors nonDottedPaths when resolving the folder
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The worker schedules step i after the sleep of module i-1
(worker_flow.rs), so a module's sleep delays the step after it. The
schema said "Delay before executing this step", and that text reaches
the write-flow skill, the flow chat and the MCP session instructions.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add ai review to the drafts page, draft diffs and the session review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: drop an ai review when its workspace changes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: follow the diff version picker in ai review and review only your own draft from the badge
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: give the drafts page ai review the full width
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: gate guest apps by their mode and the protection rule alone
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep apps that admitted no guest closed on upgrade
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update ee-repo-ref to 0605eac866b49f0de913ab41c1168b79eec31ca0
This commit updates the EE repository reference after PR #931 was merged in windmill-ee-private.
Previous ee-repo-ref: 1f643a1aaa697578b36d67982358299ee20af7f4
New ee-repo-ref: 0605eac866b49f0de913ab41c1168b79eec31ca0
Automated by sync-ee-ref workflow.
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* fix(cli): resolve /ui/ in app dev and lint, and its bare imports from the app
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): match shared ui/ files by real path so a symlinked ui/ still redirects
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): keep relative css @import in shared ui/ resolving next to the file
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): let esbuild resolve relative css @import in ui/ so suffixes keep working
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: rebuild raw apps on a ui/-only change and fail sync push on ui/ errors
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: catch unquoted css ui/ imports and surface app lookup errors
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: match the raw app metadata file on windows sync paths
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add ai review to deployment requests
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: bound ai review fetches and surface unreadable items
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add fix in ai session and model picker to deployment ai review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add workspace instructions for deployment ai review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: read review instructions from the parent and bind ai review to the fork
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: pin the fix-all session preview to the fork's compare page
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: show the protection-rule bypass toggle inline
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: make the bypass toggle small and red
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor: drop workspace-settings instructions from deployment ai review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: folder-scoped review instructions for the deployment ai review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: review the selected items with ai on compare and deploy
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep reviewing when review instructions cannot be listed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: say the review instruction floor is a prompt request, not enforcement
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: mark an ai review out of date when its items change
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update ee-repo-ref to 77703cf32e58964906d87ee83ddda44b5b8d1b7e
This commit updates the EE repository reference after PR #926 was merged in windmill-ee-private.
Previous ee-repo-ref: e30ab9e69d1854fcaed5620c934ace32acb0a729
New ee-repo-ref: 77703cf32e58964906d87ee83ddda44b5b8d1b7e
Automated by sync-ee-ref workflow.
* feat: review git sync pull requests with wmill review
* fix: withhold retyped resources and encryption keys, fall back from the responses route
* fix: withhold fileset children, workspace-specific resources and pathspec-named files
* feat: include the ready-to-post review in wmill review --json
* feat: review a workspace synced into a repository subfolder
* docs: say what wmill review takes from flags rather than wmill.yaml
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* feat: fork capability per role and fork role mapping on rulesets
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep unset fork for unrestricted roles and apply fork role mapping to fork-owner adds
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: fork_roles feature usage telemetry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: derive an unset fork in the role editor as the server does
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: update ee-repo-ref to d535972f0b35c6a7f257720816bdaec18465adef
This commit updates the EE repository reference after PR #929 was merged in windmill-ee-private.
Previous ee-repo-ref: 4a8d59cd1563382fcec85b1367f7e15e09bc13c2
New ee-repo-ref: d535972f0b35c6a7f257720816bdaec18465adef
Automated by sync-ee-ref workflow.
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* feat: app conversations through the memory_id query parameter, chat-mode flows included
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: regenerate the mcp session instructions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: type backendAsync's memoryId option in the eval diagnostics
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: pin git-sync hub scripts to windmill-cli 1.849.0
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: memoryId option on the sync backend call too
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: bump the ui builder artifact for the memoryId option
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: shared-utils 1.0.14
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: cli takes shared-utils 1.0.14 for the memoryId option
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: pin the app conversation scoping and the memoryId signatures
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: assert the ownership refusal, not any refusal
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: match the memoryId option in the cli wmill.ts signature tests
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: file an app's turns as the deployed flow's conversation, preview included
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: guidance for building standalone ai agents in ai sessions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: agent guidance for resource-only sessions, no flow tools
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: tell the user to deploy a drafted tool script with its agent
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: scope plain agent values, document tool_inputs, list agents in get_instructions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: test and run ai agents from ai sessions, open agents in their editor
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: full-bleed agent editor tabs, back to the run form for agent tests
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: describe read-and-run as running agents too, pin agent run links
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: host the agent editor natively in session tabs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: switch the agent editor to tabs below 900px
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: name an agent's session tab after its summary
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: show deployed agents in session tabs, open and run them from the chat
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: deploy agents from the chat, report agent tabs as the active editor
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: pick agents from the tab picker, name their tabs, scope the agent page to its workspace
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: leave open editors alone on agent writes, read the agent page's workspace user
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: refresh an agent's deployed page when the chat deploys or deletes it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: name agent tabs before they load, mark agents in the changes drawer, stay on a deleted agent's tab
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep a cleared agent summary out of its tab name
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep the resource drawer's json option that the resources list still passes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: open an agent in an AI session from its pages, fix review findings on agent tabs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: name the reserved agent tool names in the agent guidance
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: reload an agent's editor on a discard, open a new agent in a session
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: show agents as agents on compare and deploy, name a never-deployed one by its path
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep a deployed agent's type in its draft diff
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: link a fork row to the agent editor only on the side that holds the agent
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: guard agent page paths, mark drafted agents in the picker, side-aware agent rows on fork compare
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): built-in approval tool that parks the agent
An AI agent step can now be given a built-in "Request approval" tool. The model
calls `request_approval` with a message; the agent stores its conversation in
the new `ai_agent_checkpoint` table, releases its worker by parking its own
queue row like a workflow-as-code parent, and resumes with the answer (approved,
approver, comment) or a timeout once someone answers from the run page.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): tie approval answers to their request and hold the turn
- A turn that asks for approval runs none of its other calls; they are refused
so the model repeats them after the answer.
- The run page sends the request's call id. An answer naming another request is
ignored and the agent parks again for the time left; `suspend` is zeroed when
the answer is read, so answers sent while the agent runs are refused.
- The checkpoint is read whatever the current roster holds, the answer's
outcome is written by position, and a cancel that beats the park completes
the job as cancelled.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): say why calls beside an invalid approval request were refused
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): one approval form per request, none on a finished run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): answer approval requests from a flow's chat
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): show chat approvals for agents that do not stream
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): approval as a per-tool setting, built-in tool asks a question
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): say when a nested agent leaves out tools that require approval
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): show chat approvals and questions on the tool's own card
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): question choices, and approval buttons shared with approval steps
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): show a waiting agent as suspended, and refused calls as not run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): each added chat card shows its own call, answered marker keyed by job
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(ai-agent): approve and reject a held call through resume_suspended
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): require approval in a tool settings tab, plain descriptions on built-in tool panes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): sentence case for the web search tool label
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat(ai-agent): built-in tool drawers explain themselves in the header subtitle
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): clearer question tool subtitle
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai-agent): badge the tool settings tab like run settings
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore(ai-agent): regenerate system prompts and MCP session files
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>