* feat(review): persist and publish native code-review findings
Adds the backend core for reviewing a task's working diff before a PR
exists: task-scoped review runs and anchored, advisory findings that the
Changes/Review panel can render as inline comments.
- task_review_runs / task_review_findings schema, models, and repository,
with supersede-on-re-review and a restart sweep that cancels in-flight
runs rather than leaving them looking alive.
- ReviewService as the single write path, publishing bus events that the
WS gateway forwards to the client.
- internal/review: reviewer-identity resolution (agent profile > code-review
utility agent > user default, failing closed on passthrough-only profiles),
change-set collection, prompt batching, response parsing, anchor
extraction, and run orchestration.
- publish_review_findings_kandev MCP tool plus the task.review.* WS actions.
- Go djb2 that matches apps/web/lib/utils/hash.ts, asserted from shared
fixtures on both sides so stale detection agrees across the wire.
Spec: docs/specs/native-code-review/spec.md
Plan: docs/plans/native-code-review/plan.md
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(review): add run_code_review workflow step and wire the review runner
Makes a review pass triggerable both ways and actually runnable end to end.
- run_code_review on_enter action across models, engine compile, and an
orchestrator callback that logs rather than propagates failures, so a task
never gets stuck in a step because no reviewer was configured.
- The step's optional agent_profile_id is what lets a step review with a
different model than it implemented with; export/import swap it for a
portable agent name/model/mode so it survives a cross-workspace round trip
instead of carrying a dangling id.
- Concrete adapters for reviewer identity, changed-file collection, prompt
rendering from the code-review utility agent's editable prompt, and
inference (session-bound agentctl, falling back to the host instance so a
review works on a task whose agent is not running).
- Boot sweep cancels review runs interrupted by a restart; the E2E reset
clears review state before deleting the tasks that own it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(web): add review findings state, helpers, and live updates
Frontend plumbing for native code review, ahead of the UI that renders it.
- Review types, WS message map, and an API client that preserves the backend's
machine-readable failure code so the surface can show an actionable message.
- A review store slice that merges findings by id (a re-publish refreshes an
issue rather than listing it twice) and keeps a bounded run history.
- Findings helpers: composite file keys matching reviewFileKey, staleness via
the same per-file diff hash that drives review marks, and best-effort
re-anchoring from the stored anchor text so a moved finding follows the code
it was written about instead of pointing at whatever now occupies its line.
- Hooks for backfill, resolve/dismiss/reopen with optimistic rollback, and
sending a finding to the agent as follow-up context without changing its
status — handing a finding to an agent is not the human accepting it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(web): render review findings inline in the Changes diff
Findings now appear where the code is, in the same annotation surface as
anchored review comments, with the run control that produces them.
- ReviewFindingCard: severity chip, category, Markdown body, and the three
advisory actions. A suggestion is labelled "not applied automatically"
because it is display-only in this iteration. Resolved and dismissed
findings collapse to one muted line with an Undo, so a reviewed diff does
not stay cluttered while the human can still change their mind.
- A review-finding annotation type threaded through the diff viewer, anchored
from the same per-file diff hash the backend stamped. A finding whose diff
moved is re-anchored from its stored text when that text survives, and
otherwise reported as unanchored rather than placed against unrelated code.
- Review changes control with idle / running / cancel / failed states, and an
inline Settings link for the one failure the user can actually fix.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(web): make the review control reachable from the Review toolbar
Mounts the Review changes control next to the walkthrough action and lets an
inline finding wire its own actions.
The finding card container now reads the active task and session from the store
instead of taking four callbacks threaded through FileDiffViewer and DiffViewer;
an inline finding annotation only exists when the active task has findings, so
the store is always present and every other diff consumer is spared the
plumbing. Staleness likewise hashes the diff the viewer already holds, which is
already normalized, so it matches the hash the backend stamped without passing
it down.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(web): surface stale review findings above their file's diff
A finding whose diff moved and whose anchor text is gone had nowhere to render,
so it was silently dropped. It now appears in a collapsed per-file banner above
the diff: the finding may still be valid, and placing it at its stored line
would point at whatever code now occupies that line instead.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs(review): mark the landed native code-review plan tasks done
Tasks 01-09 (backend persistence through inline diff rendering) are
implemented, tested, and committed. Tasks 10-13 — findings overview and step
editor, mobile parity, E2E, and public docs — remain pending.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(review): cover the on-demand review path end to end
Adds the mock-agent review responder and a Playwright spec, so both the happy
path and the no-reviewer path are verified against a real backend.
The mock agent answers any prompt carrying the review sentinel with fenced JSON,
deriving its anchors from the prompt's own diff rather than hardcoding them, so
findings land on files and lines the fixture really changed. It includes one
deliberately malformed entry to exercise the rejected-entry path.
Writing it caught an off-by-one shared by three diff walkers: splitting on "\n"
leaves an empty element after a trailing newline, which carries no diff marker
and was being counted as a context line, pushing new-side numbering one past the
end of a hunk. Interior blank lines still count, since a whitespace-stripped
blank context line legitimately appears as "".
Also adds a listInferenceAgents helper: default_utility_agent_id needs the
registered agent-type id, and an agent row UUID is rejected as not
inference-capable.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(review): close review-run races and stale client findings
Addresses the three blockers and three suggestions from the PR #1957 automated
reviews. Two independent reviewers found each blocker separately.
- Launch claimed the task slot only after inserting the run row, so two
concurrent launches both created a run and the loser returned a pending row
with no goroutine behind it — a review that never finished until the next
restart. The slot is now claimed before any DB write, and freed on every
early return.
- Cancelling only marked the row. The goroutine ran on the shared background
context, finished inference, and its completion overwrote the cancelled
status and published findings the user had declined. Runs now carry a cancel
handle, the WS action routes through the runner so the live context is
cancelled, CompleteRun/FailRun refuse to resurrect a terminal run, and a
cancelled pass neither publishes nor re-reports itself as failed.
- The backend deletes a superseded finding and inserts a replacement with a new
id, but the publish event carried only the new one, so every open browser
showed both at the same anchor until a reload. The event now names the
superseded ids and the slice drops them.
- Run() waited on the shared WaitGroup, blocking on every other task's review;
it now waits on its own pass only.
- createReviewSlice is typed over the `set` it actually uses, so call sites no
longer pass superfluous arguments (CodeQL js/superfluous-trailing-arguments).
- A GetAgentProfile fault no longer collapses into "profile not found", which
would have told the user to configure an agent they already have.
The cancel bug exposed a hole in the original tests: they asserted cancel could
not override a terminal run, but never the reverse. Both directions are covered
now, along with the concurrent-launch race, per-run waiting, and the supersede
path on both sides of the wire. Test fakes now mirror the service's terminal
guard rather than hiding it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat(workflow): ship explicit completion signal toggle + YAML round-trip
ADR 0015's "Wait for agent completion signal" UI shipped as a deferral
comment in PR #1276 instead of a working toggle, and the
auto_advance_requires_signal flag never reached the workflow export
format. Add the pipeline-editor sub-toggle and propagate the field
through StepPortable so the setting survives workflow export/import.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(workflow): guard completion-signal toggle + cover import in tests
Address PR review:
- hide ExplicitCompletionToggle when on_turn_complete has no transition
(flag has no effect there; visible checkbox was misleading)
- add service-level import test for auto_advance_requires_signal so the
field has explicit ImportWorkflows coverage, mirroring the existing
show_in_command_panel pattern
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(workflow): drop omitempty from AutoAdvanceRequiresSignal tags
Match the sibling bool fields (IsStartStep, ShowInCommandPanel,
AllowManualMove) so a `false` value still appears in exported YAML/JSON.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat(web): split file search from command panel and add inline task search
Separate the command panel (Cmd+K) from file search (Cmd+Shift+K) to
prevent file results from overpowering commands. Add inline task search
directly in the command panel — tasks appear in a "Tasks" group when
typing ≥2 characters, with workflow step badges and archived state
indicators. Archived tasks are sorted last with reduced opacity.
- Add "search-files" mode to CommandPanelMode
- Add FILE_SEARCH shortcut (Cmd/Ctrl+Shift+K)
- Move file search to dedicated mode, remove from commands mode
- Add useInlineTaskSearchEffect for commands mode task search
- Remove "Search Tasks" sub-mode entry point (now inline)
- Show file search shortcut hint in command panel footer
* feat(web): add configurable keyboard shortcuts in general settings
Add localStorage-based shortcut override system for the command panel
and file search keybindings. Users can record new key combos via the
settings UI and reset to defaults.
- Add shortcut-overrides module (get/set/reset via localStorage)
- Add KeyboardShortcutsCard with shortcut recorder UI
- Add "Keyboard Shortcuts" section to general settings page
* test(web): add e2e tests for command panel and file search split
Cover the key use cases: Cmd+K opens commands without files,
Cmd+Shift+K opens file search, inline task search with workflow step
badges, escape/backspace navigation, and panel toggle behavior.
* fix(test): remove unused seedData variable in command panel e2e test
* feat(settings): persist keyboard shortcuts to user settings API
Replace localStorage-based shortcut overrides with server-persisted
storage via the user settings API. Adds keyboard_shortcuts field to
the backend model, DTO, store, service, and controller. Frontend
reads overrides from Zustand store (hydrated from SSR/WS) and saves
via PATCH /api/v1/user/settings.
* fix(ui): prioritize tasks over commands, add step colors, fix shortcut display
- Move task results above command results in cmd+K for faster task switching
- Replace magnifier icon with task icon (IconSubtask) for task results
- Apply workflow step color to task badges
- Fix formatShortcut early return bug that dropped Shift modifier
when ctrlOrCmd was set (e.g. Cmd+Shift+K showed as Cmd+K)
- Fix same bug in shortcutToCodeMirrorKeybinding
* fix(ui): use clipboard icon for task results in command panel
* style: format command panel footer
* fix(ui): use hammer icon and map step colors to hex for task badges
* feat(ui): show repo directory and agent name on task results
Display secondary details (repository directory, agent name, last
updated) on the right side of task results in the command panel.
* fix: avoid inline selector closure to prevent getServerSnapshot loop
Select the raw repositories map from the store instead of using an
inline selector that closes over workspaceId and returns new array
references, which triggers React's getServerSnapshot infinite loop.
* feat(task): expose agent name and working directory in task DTO
Add primary_agent_name (from AgentProfileSnapshot) and
primary_working_directory (from RepositorySnapshot) to TaskDTO.
Extend the primary session info query to fetch agent_profile_snapshot
and repository_snapshot columns, and extract the new fields in the
handler layer.
* feat(ui): show agent name and working directory on command panel tasks
Replace executor name with agent name from the primary session and
display the working directory (with repository path fallback) in the
task result details.
* fix(ui): add Commands heading to separate tasks from commands in search
* fix(task): use profile display name instead of agent slug
* feat(workflow): add show_in_command_panel per-step configuration
Add a configurable boolean to each workflow step that controls whether
tasks in that step appear in the command panel (Cmd+K). Default
templates mark backlog/done steps as hidden, active steps as visible.
- Add show_in_command_panel to WorkflowStep, StepDefinition, StepPortable
- Add column with idempotent migration (DEFAULT 1 for backwards compat)
- Include field in DTO serialization and export/import round-trip
- Update all default templates (Plan & Build, Architecture, Kanban, PR Review)
- Add tests for export preservation and import round-trip
* feat(ui): wire show_in_command_panel through frontend and settings
- Add field to HTTP types (WorkflowStep, WorkflowStepDTO, StepDefinition)
- Add to kanban state types and KanbanUpdatePayload
- Map in SSR snapshot mapper and WS kanban handler
- Add "Show in command panel" checkbox to workflow step settings
- Extract StepCheckboxRow component to stay within lint limits
* feat(ui): filter command panel tasks by show_in_command_panel flag
Replace position-based heuristic (resolveExcludedStepIds) with the
per-step show_in_command_panel configuration. Tasks in steps where
the flag is false are hidden from the default Cmd+K view but still
accessible via search.
- Replace resolveExcludedStepIds with resolveVisibleStepIds
- Consolidate useInlineTaskSearchEffect params into options object
* fix(ui): differentiate task sections in command panel
Rename the inline task results heading to "Active Tasks" when showing
the default view, distinguishing it from the "Tasks" command group
that contains "Create New Task".
* fix(ui): keep auto-archive checkbox inline with other step options
* fix(ui): include show_in_command_panel in step update action
The server action was missing show_in_command_panel from its Pick type
and body builder, so the checkbox change was silently dropped.
* fix(ui): pass is_start_step and show_in_command_panel from template steps
Both normalizeWorkflowTemplate mappers (workflow-api.ts and
workspaces.ts) were only picking name/position/color/prompt/events
from backend template steps, dropping is_start_step and
show_in_command_panel. This caused all template steps to appear
with show_in_command_panel checked when creating a new workflow.
* fix(ui): fix command panel empty tasks and step update losing checkbox state
Two fixes:
- Command panel: when kanban steps haven't loaded yet, don't filter
tasks by visibility (resolveVisibleStepIds returns null for empty
steps instead of an empty Set that rejects everything)
- Workflow settings: BackendWorkflowStep type and transformWorkflowStep
were missing show_in_command_panel, so refreshing steps after an
update dropped the field and the checkbox always reverted
* fix(ui): prevent back button from stealing focus in command panel
The back button was focusable and appeared before CommandInput, so
opening file search mode focused the button instead of the input.
Add tabIndex={-1} to keep focus on the search input.
* feat(web): show archive icon for archived tasks in command panel
Replace the text badge (e.g. "COMPLETED") with an IconArchive for
archived tasks in the command panel search results. Active tasks
keep the existing IconHammer icon.
* style: fix Prettier formatting and extract useStepMaps hook
Fix Prettier formatting issues in command-panel.tsx and
workflow-pipeline-editor-panels.tsx. Extract useStepMaps hook
from useInlineTaskSearchEffect to stay within the 100-line
function limit.
* fix: address PR review feedback
- Validate keyboard shortcut payload shape before persisting (service.go)
- Normalize KeyboardShortcuts to {} on read path for legacy rows (sqlite.go)
- Deduplicate getRepoDir into getFileName (command-panel-footer.tsx)
- Show toast on shortcut persistence failure instead of swallowing (keyboard-shortcuts-card.tsx)
- Reset keyboard_shortcuts in E2E test fixture for deterministic tests (test-base.ts)
Carlos Florêncio