defer RUNNING/STARTING moves instead of immediate MoveTask; add normalizeTaskState aliases; regression test for promptless Work to Done.
Co-authored-by: cybertronic <cybertronic@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(workflow): explicit step-completion signal for auto-advance
Adds `step_complete_kandev` MCP tool + `WorkflowStep.auto_advance_requires_signal`
column so workflow steps can gate their `on_turn_complete` transitions on an
agent-emitted completion signal instead of inferring "done" from any turn-end.
See docs/decisions/0015-explicit-completion-signal-for-auto-advance.md for the
motivation, alternatives considered, and trade-offs.
* fix(workflow): address PR review feedback for explicit completion signal
- Dedup `LoadPendingStepSignal` into `internal/task/models` so the MCP
handler (write site) and the orchestrator (read site) share one decoder.
- Gate the out-of-band subscriber on `WorkflowStep.AutoAdvanceRequiresSignal`
so `step_complete_kandev` is not an unintended manual-advance path for
signalless steps.
- Fail closed on step-load errors in `processOnTurnCompleteViaEngine`: a
loader hiccup must block the transition rather than silently bypass the
gate.
- Reject `step_complete_kandev` for terminal sessions
(Completed / Failed / Cancelled) so the agent gets a clear error instead
of `accepted: true` followed by a no-op.
- Surface bus-publish failures back to the agent instead of swallowing
them — the idempotency guard makes the retry safe and prevents the
session from getting stuck.
- New `TestOnStepCompletionSignaled` covers the subscriber paths
(RUNNING / WAITING+match / stale step / not signal-gated).
- ADR doc fixes: payload field list now matches the wire shape, writer
ownership is documented, the unsubstantiated 250ms-debounce claim is
removed, and the late-signal re-close race is recorded as a deferred
open question.
- Drop the new toggle's HelpTip in favour of an inline description — the
shadcn tooltip portal was intercepting clicks on the agent-profile
dropdown options in the workflow settings E2E.
* fix(workflow): round-2 review fixes for explicit completion signal
- Split `handleStepComplete` into `resolveStepCompleteTarget` +
`publishStepCompletionEvent` helpers so the entrypoint clears funlen
(88 → under 80 lines) and the two halves are independently testable.
- Classify session/task load errors instead of returning `NotFound` for
every failure: use the exported `taskrepo.ErrTaskNotFound` sentinel for
task lookups, substring-match for the session repo (no sentinel today),
and surface anything else as `InternalError` with the raw error logged
but not leaked to the agent — so a transient DB hiccup triggers a retry
rather than session abandonment.
- Pin `step_complete_kandev` explicitly in the mode-specific tool-count
tests: `Contains` in `ModeTask`, `NotContains` in `ModeConfig` and
`ModeOffice`, so accidental dereg or cross-mode registration is caught
by the diff instead of by a still-equal count.
* fix(workflow): round-3 review fixes + defer pipeline-editor toggle
- Defer the "Wait for agent completion signal" sub-toggle to a follow-up
PR. Adding it to the step config card shifts the layout enough that the
agent profile select's Radix popper opens into a sibling tooltip's hover
path, breaking workflow-agent-profile.spec.ts on shard 7. The backend
column ships in this PR — workflows can opt in via the YAML import or
the MCP `update_workflow_step_kandev` tool — and the UI affordance gets
its own iteration where the test interference can be investigated
without blocking the rest of the change.
- Re-publish the bus event on the `already_signaled` short-circuit when
the session is WAITING_FOR_INPUT. Without this, an agent's retry after
the first call's publish failed would short-circuit on the persisted
bag, never fire the subscriber, and leave the session stuck.
- handleStepComplete docstring: drop the non-existent feature-flag claim
and the "audit entry" wording — gating is purely
`WorkflowStep.AutoAdvanceRequiresSignal` and the bag is cleared on the
next turn start with no separate audit trail.
- `step_complete_kandev` tool description: same fix — clarify that the
call succeeds for non-gated steps but the signal is discarded on the
next turn start (no audit history to query later).
* test(workflow): cover handleStepComplete + reword defer-comment
- Add `TestHandleStepComplete_*` (6 subtests, all passing) covering the
uncovered handler paths flagged by Claude/cubic on round 3:
missing-fields validation, session-does-not-belong-to-task ownership
guard, terminal-session rejection (Completed/Failed/Cancelled),
first-call happy path (bag persisted + bus payload shape pinned), dedup
while RUNNING (no re-publish), and dedup while WAITING_FOR_INPUT (the
retry-after-publish-failure path — must re-publish so the subscriber
fires).
- Reword the deferred-toggle comment to drop the YAML-export claim:
the workflow export model doesn't yet serialize
`auto_advance_requires_signal`, so MCP `update_workflow_step_kandev`
is the only configuration path that round-trips today. Note the
follow-up needs to extend the export schema alongside the UI toggle.
* test(workflow): pin signaled_at + drop redundant GetTaskSession on bag-clear
- Assert `signaled_at` is present and parses as RFC3339Nano in
`TestHandleStepComplete_FirstCallAccepted`. The field is part of the
handler's documented response contract; pinning it catches accidental
drop/rename regressions.
- Add `clearPendingStepSignalByID(ctx, sessionID)` as a thin DB-only
variant of `clearPendingStepSignal` and use it from
`executeStepTransition`, where the session struct isn't read after the
clear. Avoids an extra `GetTaskSession` round-trip per transition.
`clearPendingStepSignal(session)` still exists for the
in-memory-mutation case (subscriber's stale-step path).
* fix(workflow): subscriber stale-clear guard + ADR/comment drift fixes
- onStepCompletionSignaled's stale-step path now reads the bag and only
clears it when its current StepID matches the (stale) event's stepID.
Previously the unconditional clear could destroy a valid signal that
the new step's agent had just written when sessions are reused across
steps without auto_start_agent. (Greptile P1.)
- Drop the "feature flag" phrase from WorkflowStep.AutoAdvanceRequiresSignal
docstring — leftover from an earlier draft. The gating is purely the
boolean field; the global flag was removed two rounds ago.
- Merge the two adjacent `if triggerOnEnter` blocks in
executeStepTransition so the full triggerOnEnter=true path reads top-
to-bottom in one place. (CodeRabbit + cubic.)
- ADR 0015 Mechanism section: re-label the SessionStepHistory.Metadata
audit annotation, the `step_complete_signaled` system message, and the
expvar telemetry counters as deferred. They're planned shapes, not
current behaviour — calling them "Audit" / "Chat visibility" /
"Telemetry" in present tense was misleading for future readers.
* fix(workflow): drop subscriber complexity + reload session on stale-clear
- Extract `parseStepCompletionEvent` and `stepIsSignalGated` helpers from
`onStepCompletionSignaled`. Cyclomatic complexity goes 17 → under 15
(cyclop on new code, CI lint regression after the round-6
stale-clear guard).
- The stale-step branch now re-loads the session from the DB before
deciding whether to clear the bag. The previous round-6 fix checked
the local `session.Metadata` snapshot, which can be older than a
concurrent write from the new step's agent — that check could see a
stale signal that had since been overwritten with a valid one and
erase the new bag entry. The narrower load-on-clear is cheap and
closes the cubic P1 hole. (The broader race in
`processOnTurnCompleteViaEngine` reading session.Metadata is the
monotonic-marker open question in ADR 0015; out of scope here.)
* test(workflow): pin stale-event guard's preserve-current-bag side + dedup StringFromAny
- Add `TestOnStepCompletionSignaled` subtest "stale event → valid bag
for CURRENT step is preserved" — fires a stale step-A event while
the bag holds a valid step-B signal, asserts the bag still contains
StepID=step_b after the subscriber runs. Pins the negative side of
the round-6 `existing.StepID == stepID` guard, so a regression that
drops or inverts the guard (and would silently leave signal-gated
steps stuck) fails the test instead of slipping through.
- Promote `pendingSignalString` to exported `models.StringFromAny`
and reuse it from the orchestrator subscriber's
`parseStepCompletionEvent`. Eliminates the byte-for-byte duplicate
helper across the two packages; the bag-shape decoder and the bus-
event decoder now share one source of truth for "missing string".
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
* feat(diff): use stored base_branch for diff stats + per-task compare picker
Task-card additions/deletions and the Changes panel were computed against a
hardcoded origin/main → master priority list inside agentctl. For tasks
branched off a release/staging branch this inflated the counts by every
commit since the actual fork point, and the Changes panel grouped unrelated
files alongside the task's real work.
This wires the per-repo task_repositories.base_branch end-to-end into the
agentctl WorkspaceTracker so each repo's diff stats resolve against the
recorded base instead of the integration-branch fallback. A picker on the
Changes panel branch hover card lets the user change the base mid-task; the
new value is persisted via PATCH /tasks/:id/repositories/:repo_id, pushed
live to the running agentctl instance, and the session's cached
base_commit_sha is cleared so the commits panel + cumulative diff refetch
against the new base without a session restart.
Falls back to the existing origin/main → master list for legacy tasks
(empty base_branch) and to the branch tip when no merge-base exists with
HEAD (unrelated histories — local rebase backups, etc.) so the stats and
commits panels stay anchored on the same SHA in every failure mode.
* fix(agentctl): sanitize user-controlled base_branch refs before git exec
CodeQL flagged the picker's user-controlled base_branch payload reaching
exec.Command("git", ..., baseBranch) inside workspace_git_cmd.go as a
command-built-from-user-controlled-source vulnerability. A malicious caller
could smuggle a leading-"-" argument like "-upload-pack=..." that git
itself reinterprets as a flag, even though exec.Command keeps args
separate from the shell.
Adds an IsSafeGitRef sanitizer at every boundary the value crosses on its
way to git: the service write path, the agentctl HTTP handlers
(/workspace/base-branches, /git/log, /git/cumulative-diff), and
WorkspaceTracker.SetBaseBranch itself. Unsafe values are rejected at the
service tier and silently downgraded to the no-override fallback inside
agentctl so a misbehaving caller can't half-break the tracker.
* fix(diff): address PR review blockers and CI lint
- Split UpdateRepositoryBaseBranch into validate/load/apply helpers to drop
cyclomatic complexity below the cyclop limit that gated Run Backend Tests.
- Replace direct m.cfg.BaseBranches reads/writes with getBaseBranches /
setBaseBranches under a dedicated RWMutex. UpdateBaseBranches used to
write under repoTrackersMu while rescan + lazy-subpath callers read under
workspaceTrackersMu, leaving an unsynchronized data race on the map.
- Drop the false 'PR target is auto-wired' claim from the MCP tool
description — GitOperator.CreatePR takes baseBranch as an explicit arg
and never reads the tracker's value.
- Picker no-op guard now compares against currentBase instead of storedBase
so selecting the displayed fallback (legacy task before any picker
change) is treated as no-op instead of triggering a spurious save.
- HTTP handler now maps non-validation service errors to 500 instead of
400, classifying via the existing isValidationError helper plus the new
unsafe-git-ref message.
* fix(diff): regex-based ref sanitiser at every git subprocess sink
CodeQL kept flagging workspace_git_cmd.go:43 even after SetBaseBranch
rejected unsafe values — the taint tracker doesn't follow sanitised stores
through struct fields, so it still saw user input flowing into
exec.Command("git", ..., baseBranch).
Switches IsSafeGitRef to a single regex check (a pattern CodeQL recognises
as a sanitiser barrier) and adds SanitizeGitRef calls inline at every
agentctl call site that splices a user-controlled ref into a git arg:
- workspace_git_status.resolveStoredRef (before the rev-parse probes)
- workspace_git_status.computeBaseCommit (before merge-base/rev-parse)
- workspace_git_status.getAheadBehindCounts (before rev-list)
- agentctl/server/api/git.go runGitLogForRepo + handleGitCumulativeDiff
(before computeMergeBase/GetRevParse on the HTTP TargetBranch)
Behaviour is unchanged for valid refs — only narrows the allowlist (now
[A-Za-z0-9_./-]) so the sanitiser barrier is recognisable to static
analysis. SetBaseBranch's field-store sanitiser stays as defence in depth.
* fix(diff): transform sanitiser at every map read for CodeQL taint flow
CodeQL still flagged workspace_git_cmd.go:43 because:
- handleSetBaseBranches used an IsSafeGitRef bool guard before a verbatim
map[k] = v copy. CodeQL recognises regex-transforming sanitisers but not
bool-guarded passthroughs.
- lookupBaseBranch returned m.cfg.BaseBranches[k] verbatim. Even though
the map was sanitised on write, taint flow across map stores + field
stores loses the sanitised state in the analyser.
Switches both sites to the transforming SanitizeGitRef helper so every
read produces a freshly-sanitised value before it flows to a downstream
git argument. Behaviour is unchanged for valid refs.
* fix(diff): regex transformer sanitiser + guard live push from empty map
CodeQL still flagged the previous SanitizeGitRef because it returned the
input string unchanged on success — an identity passthrough that the taint
tracker doesn't recognise as a sanitiser barrier.
Switches to safeGitRefPattern.FindString so the output comes from the
regex match (not the parameter). IsSafeGitRef now wraps SanitizeGitRef so
the predicate and the transformer share one allowlist.
Also addresses two Claude review blockers:
- collectTaskBaseBranches returns a nil/empty map when the task has no
recorded base_branches; pushing that to agentctl wipes every tracker's
override. Now skipped — the DB row is the source of truth for the next
session launch.
- applyBaseBranchSideEffects now runs on context.WithoutCancel so an HTTP
/ WS request cancel after the task_repositories UPDATE commits can't
leave session.base_commit_sha stale + the live agentctl tracker map
un-pushed, drifting from the persisted row.
* fix(diff): share securityutil.IsValidBranchName + harden error classification
CodeQL still flagged the picker's regex sanitiser as taint passthrough.
Refactors SanitizeGitRef / isSafeBaseBranchRef to delegate to the existing
securityutil.IsValidBranchName helper that agentctl's Rebase / Merge /
RenameBranch already use without being flagged. The shared allowlist also
fixes a Claude review blocker: 'feature/@2024' used to pass the service
validator but get dropped by the agentctl-side check at push time,
silently wiping every tracker's override.
Plus the two error-classification blockers Claude raised on the previous
HEAD:
- WS handler (task_ws_handlers.go wsUpdateTaskRepository) now distinguishes
validation errors (surfaced verbatim) from internal faults (opaque
500-style message). HTTP path already did this via the existing
isValidationError helper.
- MCP handler (handlers.handleUpdateRepositoryBaseBranch) gets the same
treatment via a new isValidationError local to the mcp/handlers
package so raw service error strings stop leaking across the MCP
boundary.
* fix(diff): inline securityutil.IsValidBranchName at every git subprocess sink
CodeQL's interprocedural taint tracking wasn't recognising SanitizeGitRef
as a sanitiser even after it delegated to securityutil.IsValidBranchName
— the wrapper helper + map/field hops between source and sink kept the
flow tainted in the analyser.
Inlines the IsValidBranchName allowlist check (already used inline by
Rebase/Merge in git.go without being flagged) at every call site that
splices a user-controlled ref into a git subprocess argument:
- workspace_git_status.resolveStoredRef (before rev-parse --verify)
- workspace_git_status.computeBaseCommit (before merge-base / rev-parse)
- workspace_git_status.getAheadBehindCounts (before rev-list)
- agentctl/server/api/git.go runGitLogForRepo + handleGitCumulativeDiff
- agentctl/server/api/workspace_base_branches.go handleSetBaseBranches
Behaviour unchanged: same allowlist as Rebase / Merge / RenameBranch
already use. SanitizeGitRef / IsSafeGitRef survive as defence-in-depth
helpers for callers that want a one-line check; they delegate to the same
securityutil helper so the rules stay aligned.
* fix(diff): inline regexp.MatchString at every git subprocess sink
CodeQL still flagged workspace_git_cmd.go:43 even with the inline
securityutil.IsValidBranchName helper — the taint tracker apparently does
not follow into helper functions for the go/command-injection rule on
this path.
Hoists the regex to package-scope vars (safeBranchRefPattern in both
process and api packages) and calls regexp.MatchString directly at each
sink site. Behaviour is identical to securityutil.IsValidBranchName; only
the call form changes.
* fix(diff): SHA-shape allowlist on BaseCommit before downstream git diff
CodeQL still flagged workspace_git_cmd.go:43 because update.BaseCommit
is the OUTPUT of an earlier merge-base / rev-parse call whose argument
list contained a user-controlled branch ref — the analyser treats that
command's output as still tainted even when the input ref was sanitised.
Adds an inline 40-hex SHA-shape allowlist check in enrichWithBranchDiff
right before `git diff --numstat <update.BaseCommit>` so the sanitiser
barrier sits in the same function as the next subprocess call. Behaviour
is unchanged: merge-base / rev-parse already produce SHA-shaped output.
* fix(diff): async tracker refresh + tighten init spread order
Two CodeRabbit/Claude review fixes:
- UpdateBaseBranches stamps each tracker's new baseBranch synchronously
then runs RefreshGitStatus on a background goroutine instead of inside
the picker-save HTTP handler. Per-tracker git subprocesses can each
take ~3-5 calls; serialising them on the request goroutine made the
PATCH response wait for every refresh to finish. The picker UI re-fetches
via the existing WS stream once Refresh emits, so the handler doesn't
need to block.
- updateTaskRepositoryBaseBranch now spreads options.init BEFORE the
required method/body fields so an upstream caller's init overrides
can't replace the PATCH method or the base_branch payload. Matches
the convention deleteTask / moveTask already follow.
* fix(diff): narrow mcp isValidationError + opaque 500 + post-sanitize log count
Three final Claude review threads on the latest commit:
- mcp/handlers isValidationError drops the broad 'invalid' substring so
DB / IO errors whose messages happen to contain 'invalid' don't
misclassify as ErrorCodeValidation.
- task_http_handlers httpUpdateTaskRepository now logs the raw service
error server-side and returns an opaque 'failed to update task
repository' on the 500 path. Stops potential DB / IO detail leakage
through the HTTP boundary.
- workspace_base_branches debug log reports accepted + rejected counts
(post-sanitisation) instead of the pre-filter total so the metric
actually reflects what hit UpdateBaseBranches.
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
* fix(worktree): promote FallbackBaseBranch when BaseBranch is empty
CreateRequest.Validate previously hard-rejected an empty BaseBranch even
when the caller supplied a FallbackBaseBranch. The fallback is plumbed
specifically so a missing primary branch can degrade into the repo's
default — this lets that path actually fire.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(task): probe provider default branch in add_branch resolve path
Adds an opt-in ProviderDefaultBranchProber seam (impl wired in cmd/kandev)
and threads a ResolveProviderDefaults flag through TaskRepositoryInput so
the add_branch_to_task GitHub-URL path can resolve a real default_branch
before writing the Repository row. Also backfills the existing repo's
default_branch when the probe succeeds and the workspace already had a row
with an empty value. The create_task path keeps its zero-default contract
(executor still backfills after clone).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): surface add_branch_to_task failures instead of silent orphans
AddBranchToTask used to return a success envelope even when the
post-insert worktree materialize step failed on a live task. The
task_repositories row stayed in place with no on-disk worktree, and
provider-URL flows also left an orphan repositories row behind.
Three coordinated changes:
- Gate empty base_branch after resolution with a typed error so no row
is written when nothing can be materialized.
- Track whether the repository row was created by this call and roll it
back on any subsequent failure.
- materializeBranch now returns its error; on a live worktree-executor
task, AddBranchToTask rolls back the task_repositories row and surfaces
the failure. Pre-launch tasks keep the legacy best-effort path so the
next session launch still materializes via the multi-repo prepare flow.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(mcp): classify add_branch base_branch resolution failure as validation
AddBranchToTask now returns a "cannot resolve base_branch" error when the
provider repo's default branch could not be probed. Map it to
ErrorCodeValidation so MCP agents see a user-fixable input issue rather
than an opaque internal error.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): defer task.updated until after worktree materializes
Publishing task.updated before materializeBranch ran meant a failed
materialize on a live task would push the new task_repository row to WS
clients and then silently roll it back, leaving stale UI state until the
next poll. Move the event after materialize success so the bus only sees
durable rows. Test now also asserts no task.updated fires on the rollback
path. Renames stubProber.lastProvid to lastProviderArg for clarity.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): emit repository.deleted on add_branch orphan rollback
Cleanup callback previously called repoEntities.DeleteRepository directly,
which soft-deletes the row but bypasses Service.DeleteRepository's event
publish. The create path emitted repository.created, so skipping the
delete event left WS subscribers and frontend caches holding a phantom
row after a resolve-then-fail sequence. Route through the service method
so the events stay symmetric. Test now asserts the symmetry.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): skip provider probe when workspace already has the repo
resolveRepoInput's add_branch probe fired on every add_branch_to_task
call with a github_url, even when the workspace already had the
provider repo registered with a non-empty default_branch. The existing
row's value would win seconds later via the repo.DefaultBranch fallback,
so the remote git ls-remote round-trip was pure waste — and unnecessarily
hit network on every call. Peek at the workspace registry first and
short-circuit when a usable default_branch is already on file.
Also adds a QA-tier test file covering probe-error fallthrough, bad URL
rejection, registered-repo probe skipping, empty-default backfill, and
the repository_id fast path.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): detach rollback paths from caller ctx, log probe-lookup errors
Two adjacent robustness fixes flagged on PR #1264:
1. resolveRepoInput silently discarded the GetRepositoryByProviderInfo
error before the provider probe. A transient DB failure was
indistinguishable from a clean "not found" lookup, so the code would
pay for a network probe instead of failing fast. Surface the error in
logs and skip the probe — FindOrCreateRepository below already hits
the same DB and will return the real cause.
2. The repository-create cleanup callback in resolveBranchAddRepoRef and
the task_repositories rollback in AddBranchToTask both captured the
caller ctx for their DELETE queries. Rollback often runs precisely
because that ctx was cancelled (timeout, client disconnect), and
reusing it would kill the cleanup and orphan the row we just created.
Use context.WithoutCancel so the rollback survives ctx death.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(task): close orphan-row gaps from caller cancel and concurrent create
Two findings from Claude's review on PR #1264:
1. (blocker) materializeBranch called taskAlreadyLaunched(ctx, ...) after
MaterializeBranch returned, using the same caller context that often
failed the materialize in the first place. A cancelled ctx made the
post-failure DB lookup return (nil, err), taskAlreadyLaunched returned
false, and the live-task rollback path silently demoted itself to the
pre-launch best-effort branch — leaving the orphan task_repositories
row the PR exists to prevent. Snapshot the launch state BEFORE
MaterializeBranch (launch state can't change during the synchronous
call) so the rollback decision is anchored to a live-ctx answer.
2. (suggestion) resolveBranchAddRepoRef inferred "this call created the
repo" by comparing the resolved ID against a workspace ListRepositories
snapshot taken before FindOrCreateRepository. A concurrent add_branch
for the same GitHub URL could create the row between snapshot and
lookup; the second request would treat it as "not in my snapshot, must
be mine" and register cleanup against the other request's data. On any
later failure, cleanup would DELETE a repository this call didn't
create and emit a spurious repository.deleted event.
Thread an explicit `created bool` out of CreateRepository through
FindOrCreateRepository → resolveRepoInput → ResolveRepositoryRef so
the cleanup callback fires only when this call physically inserted
the row. The flag is set at the CreateRepository / FindOrCreateRepository
sites themselves and cannot be spoofed by concurrent activity.
resolveRepoInput's branches were extracted into resolveRepoInputGitHub /
resolveRepoInputLocal helpers to keep the parent function inside the
cyclomatic-complexity and cognitive-complexity budgets after the signature
change.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: retrigger cubic CI
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat(mcp): accept repository_url and local_path on add_branch_to_task_kandev
Mirror create_task_kandev's repo-locator surface so agents can attach a
branch without first looking up the repository UUID. The MCP tool now
takes repository_id OR repository_url OR local_path; the service
resolves alternatives via the same workspace-scoped find-or-create
path used by create_task.
* fix(mcp): run executor guard before repo resolution on add_branch_to_task
ResolveRepositoryRef may FindOrCreateRepository / CreateRepository
inside the github_url / local_path paths. Running it before
requireWorktreeExecutorForBranchAdd let a rejected add_branch call
on a docker/sprites/SSH task leak an orphan Repository row into
the workspace.
Move the executor check ahead of resolution and add a regression
test that asserts ListRepositories count is unchanged after a
rejected call with a brand-new github_url.
* test(mcp): assert task_id default in add_branch local_path test
* fix(mcp): reject multiple repo locators on add_branch_to_task
resolveRepoInput applies a silent precedence (repository_id >
github_url > local_path), so an agent that accidentally supplies
two of the three locators got a behaviour change with no signal.
Reject at the WS handler with a clear error so the mistake is
surfaced.
Also refresh the AddBranchToTask docstring to document the new
LocalPath / GitHubURL inputs and to correct the workspace-membership
check ownership (now enforced by ResolveRepositoryRef → resolveRepoInput
for the alternative paths).
* fix(mcp): classify resolve_repository errors as validation, not internal
Failures from ResolveRepositoryRef are user-fixable input mistakes
(malformed URL, unknown local_path, cross-workspace repository_id).
Without a matching case the wrapper "resolve repository: ..." message
fell through to ErrorCodeInternalError, so an agent that supplied
e.g. a bitbucket URL saw a server-fault code instead of a validation
error it could correct.
* fix(mcp): narrow add_branch error classification + use wire field name
Two follow-ups to the round-3/4 review feedback:
- Mutual-exclusion error mentioned the MCP tool alias `repository_url`
but the WS handler sees the wire field `github_url`. A direct WS
caller would see an error naming a field it never passed.
- The broad `"resolve repository: "` prefix classified ALL wrapped
errors as Validation, including DB / system failures from
CreateRepository / ListRepositories inside ResolveRepositoryRef.
Narrow to specific user-fixable patterns (GitHub URL parse failures,
cross-workspace repository_id) so genuine internal errors no longer
masquerade as validation rejections.
* fix(mcp): mutual-exclusion check at MCP tier names agent-facing alias
WS-tier rejection works for direct WS callers but its error mentions
github_url, the wire field — confusing for MCP agents that supplied
repository_url. Move the check up to addBranchToTaskHandler so the
error reads "pass at most one of repository_id, repository_url,
local_path" using the names the agent actually typed. WS handler
still validates as defense-in-depth.
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
* feat(tasks): multi-branch tasks — N (repo, branch) pairs per task
Extends multi-repo into multi-branch so a single task can hold multiple
worktrees on the same repo (one per branch). Sibling worktrees layout at
<task>/<repo>/ + <task>/<repo>-<slug>/, dedicated PRWatch per branch,
live agentctl tracker rescan + frontend store updates so the UI splits
PRs / files / commits per branch without a session restart. MCP
add_branch_to_task_kandev tool is shielded to the worktree executor.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(web): unify multi-branch repo label as <repo> · <branch> across panels
PR Changes and Commits panels rendered repo labels differently for multi-branch
tasks — Commits showed "kandev · feature/x" while PR Changes leaked the raw
"kandev-feature-x" agentctl tracker tag. Reformat tracker-tagged repo names via
formatRepoLabel using the longest known-repo prefix so kandev-cli-* doesn't
collapse to kandev · cli-*.
* fix(tasks): address multi-branch PR review — data races, slug collisions, MCP error codes
Backend
- agentctl process.Manager: add repoTrackersMu RWMutex guarding repoTrackers
+ workspaceTracker. Reads snapshot under RLock; RescanRepositories builds
trackers first, takes Lock for swap/append. Validates newWorkDir via
os.Stat before publishing cfg.WorkDir.
- worktree.Manager: reject invalid explicit BranchSlug up-front; cache key
uses sanitized wt.BranchSlug so read/write paths are symmetric.
- worktree.store: narrow isDuplicateColumnError to "duplicate column name".
- task service AddBranchToTask: slug-collision guard rejects feat/a vs feat-a.
- orchestrator resolvePushRepo: two-pass exact-name match before subdir
prefix fallback so "backend" doesn't swallow pushes for "backend-admin".
- executor buildRepoSpecs: duplicate repos always get a non-empty BranchSlug
(falls back to branch-N when both branch fields sanitize to empty).
- MCP handler: classifyAddBranchError maps service errors to NOT_FOUND /
CONFLICT / VALIDATION_ERROR; add ErrorCodeConflict constant.
- MCP server: extract registerAddBranchToTaskTool, register in task mode
only (external mode contract: config tools + create_task_kandev).
- workspace_rescan handler: reject malformed JSON with 400 instead of
silently rescanning the current root.
- branch_materializer: split MaterializeBranch into prepare + finalize
helpers to satisfy the 80-line cap.
Frontend
- existingPrUrl returns undefined when a task has >1 PR so per-repo View PR
buttons take over (no silent linking to a sibling).
- formatRepoLabel checks exact known-repo match before prefix splitting so
"kandev-cli" isn't mislabeled as "kandev · cli".
- Repo chip key now includes base_branch so siblings differing only on
base render as distinct chips.
Docs
- multi-branch spec uniqueness wording aligned with the canonical 4-column
key (task_id, repository_id, base_branch, checkout_branch).
- worktree.CreateRequest.BranchSlug doc describes the sibling layout
(<repo>-<slug>) instead of the obsolete nested form.
* fix(tasks): scope slug-collision check to repo only + use errors.Is for ErrTaskNotFound
- service_branches: drop base_branch from the slug-collision check. Worktree
path is (repo, slug); two rows on the same repo cut from different bases
still collide on disk.
- service_branches: prepareBranchAdd wraps taskrepo.ErrTaskNotFound via
fmt.Errorf with %w so classifiers don't have to substring-match the
formatted task UUID.
- mcp handlers: classifyAddBranchError uses errors.Is(err, ErrTaskNotFound).
* fix(agentctl): sanitize rescan work_dir before os.Stat to clear CodeQL path-injection
CodeQL flagged the rescan endpoint as a path-injection sink (the
HTTP-supplied work_dir flowed straight into os.Stat and downstream
scanRepositorySubdirs). Add validateRescanPath which:
- requires the input to be a clean absolute path with no ".." segments
- rejects anything that isn't equal to or an ancestor of the current
cfg.WorkDir — the only legitimate use case is the branch materializer
promoting <task>/<repo>/ to <task>/
Defense in depth: agentctl binds to localhost, but any colocated process
could otherwise direct it at /etc or the user's home by POSTing
/api/v1/workspace/rescan.
* fix(agentctl): tighten validateRescanPath, close TOCTOU on existingTrackers, add tests
- Drop the strings.Contains(clean, "..") guard. filepath.Clean already
resolves traversal; the substring check rejects legitimate names like
/home/u/..hidden without adding defense (the ancestor check via
filepath.Rel is the real boundary).
- Drop the rel == "." branch in the ancestor check — early return for
clean == currentClean already covers identity.
- Read existingTrackers inside the write-lock section (not under RLock
then re-Lock) so two concurrent rescans can't both see 0 trackers and
double-bootstrap the multi-repo set.
- Add table-driven TestValidateRescanPath covering rejection paths
(relative, descendant, sibling, traversal-cleaned, empty input),
legitimate ancestor promotion, exact match, no-anchor first-launch,
and a /home/u/..hidden dotted-segment case.
* fix(agentctl): break taint flow into os.Stat — derive rescan path from cfg, not HTTP body
CodeQL's go/path-injection trace still flagged manager_rescan.go after the
prior sanitizer because the user-supplied newWorkDir flowed (after
validation) into os.Stat and then into cfg.WorkDir → tracker paths →
workspace_monitor os.Stat sinks.
Replace validateRescanPath with resolveRescanPath: it returns a path
DERIVED from currentWorkDir (no-op = currentClean, promotion =
filepath.Dir(currentClean)) and uses newPath only for comparison, never
as a source for the returned string. os.Stat now receives a path whose
provenance is trusted manager config.
Functionally the legitimate caller (branch materializer promoting
<task>/<repo>/ to <task>/) is unchanged.
* test(agentctl): make TestResolveRescanPath windows-portable
The Linux Backend Tests job passed but the Backend (windows) job rejected
every "absolute" case because filepath.IsAbs("/task/repo") is false on
Windows (no volume letter).
Build inputs via filepath.Join against absRoot() (filepath.Abs of "/" /
"\\") so the same table covers POSIX (`/...`) and Windows (`C:\...`)
without per-OS branches. Keep the traversal-after-Clean case POSIX-only
since filepath.Clean is the shared primitive and that input form needs a
volume to be considered absolute on Windows anyway.
* fix(agentctl): serialize RescanRepositories + re-check trackers under write lock
Two concurrent RescanRepositories calls could both observe an empty
tracker set (between the snapshot read and the bootstrap branch) and both
enter transitionToMultiRepoMode, leaking a duplicate bare-root tracker
and duplicate per-repo trackers. Same race in appendNewRepoTrackers would
double-append the same new child across both callers.
Fix:
- Add rescanMu sync.Mutex on Manager. Acquired for the full body of
RescanRepositories so the snapshot → branch → mutate sequence is
serialized. repoTrackersMu still guards individual field reads from
unrelated goroutines (subscribe/unsubscribe/poll-mode).
- appendNewRepoTrackers re-checks membership inside the write-lock
before appending and drops already-present trackers (Stop + detach
outside the lock). Defense in depth.
- Test: add `dotted segment is legal as promotion` case so the
..hidden-segment promotion path stays exercised.
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* chore: remove orphan executor tracing file and deprecated ResolveScript wrappers
- Delete internal/agentctl/tracing/executor.go (7 TraceExecutor* funcs)
- Delete internal/orchestrator/executor/script_template.go (deprecated wrapper)
- Delete scriptengine.ResolveScript convenience function
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove orphan setter methods across healthpoll, jira, linear, slack, updates
- Delete Poller.SetInterval from integrations/healthpoll (no callers)
- Delete Poller.SetIssueTickHook from jira and linear (no callers)
- Delete Trigger.SetInterval and Trigger.SetMatchHook from slack (no callers)
- Delete Service.SetPollInterval from system/updates (no callers)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove orphan wrapper functions and accessor method
- Delete updates.FetchLatestRelease shim (wraps FetchLatestReleaseFrom, no callers)
- Delete usage.NewClaudeUsageClient and NewCodexUsageClient shims (no callers)
- Delete database.Service.Path() accessor (no callers)
- Update ErrGitHubRateLimited godoc to reference FetchLatestReleaseFrom
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove unwired handleListExecutors MCP handler
The sibling profile handlers (list/create/update/delete) are registered
via RegisterFunc in handlers.go. handleListExecutors never was — dead flow.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove stale hook-field comments after setter deletion
SetIssueTickHook (jira, linear) and SetMatchHook (slack) were removed
in the deadcode cleanup. Their struct fields still claimed "tests use
this" — no test or caller can set these fields now.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove orphan hook fields and fire methods after setter deletion
issueTickHook (jira/linear) and matchHook (slack) are unexported and
never set after their public setters were removed; fireIssueTickHook /
fireHook were permanent no-ops.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(backend): forward base_branch override for same-repo subtasks via MCP
The create_task_kandev MCP handler dropped base_branch silently unless
the caller also passed a repository identifier. Same-repo subtasks then
inherited the parent's repos verbatim, so "branch off feature/X" calls
landed on the parent's branch instead.
Forward base_branch at the top level of the WS payload and apply it as
an override on the resolved repo list when no per-repo entries were
supplied; explicit per-repo BaseBranch wins as before.
* docs(backend): correct BaseBranch field comment to match actual fallback semantics
The struct doc on `req.BaseBranch` claimed it won over explicit per-repo
entries, but the override only fires when `len(req.Repositories) == 0`.
Reword as a fallback applied to inherited/resolved repos when no
per-repo list is supplied; explicit per-repo BaseBranch stays
authoritative when set. Flagged by CodeRabbit and Greptile.
* refactor(backend): forward top-level base_branch only when no per-repo entries
When the MCP caller supplies a repo identifier, the per-repo base_branch
is already authoritative on the backend side, so emitting a top-level
base_branch in the same payload was dead weight that the backend's
override gate explicitly ignored. Move the top-level forward into the
else of hasRepo so the two paths are mutually exclusive and the wire
contract reads as "top-level base_branch means inherit-with-override".
Flagged by the Claude review bot.
* feat(orchestrator): persist N-entry FIFO message queue
Replaces the single-slot, latest-wins, in-memory queue with a SQLite-backed
FIFO queue (default cap 10 per session, configurable via
KANDEV_QUEUE_MAX_PER_SESSION). Drain stays one-per-turn so each entry gets its
own user message and `on_turn_*` workflow cycle. Inter-task `message_task_kandev`
returns a structured `queue_full` error with sender attribution when the
target session is saturated, so the calling LLM can decide whether to retry.
Surfaces a new WS action `message.queue.remove` for single-entry deletion;
`message.queue.cancel` now means clear-all. Edit/remove are keyed on the
entry's UUID, returning `entry_not_found` when atomic-take won the drain race.
* feat(web): N-entry queue state, API, and optimistic hook
Replaces the single-slot QueueStatus with an ordered `entries[]` per session
plus capacity meta (`count`, `max`). API exposes typed `QueueFullError` and
`QueueEntryNotFoundError`; the hook surfaces optimistic edit/remove with
drain-race rollback (refetch on `entry_not_found`).
* feat(web): inline ghost-message queue UI with sender chips
Replaces the floating QueuedMessageIndicator overlay with a stack of ghost
messages rendered above the chat input. Each ghost shows a sender chip
(user / agent) and per-entry edit/remove. A small "n/max queued · clear all"
pill summarizes capacity. Inter-task entries are visually distinct and edit
is gated to the original sender.
* fix(queue): address review — auth guard, TOCTOU, error UX
- Add `messagequeue.QueuedByUser` / `QueuedByAgent` constants and centralize
the `queue_full` error code so the WS and MCP handlers stay in sync.
- WS `message.queue.{add,append,update}` default empty user_id to QueuedByUser
so the UpdateContent ownership guard always runs against a non-empty owner;
inter-task entries (`queued_by="agent"`) can no longer be overwritten by
user-initiated edits even when `user_id` is omitted from the payload.
- memoryRepository: hold the mutex through the whole append-or-insert path
(prior split released the lock between tail-check and Insert, allowing two
same-sender callers to race past coalescing). TransferSession now shifts
source positions past the destination's max so transferred entries always
drain after pre-existing destination entries, matching SQLite semantics.
- Frontend: surface edit/clear/remove failures via `sonner` toasts (drain race
→ "message already sent"); exit edit mode on failure instead of leaving the
textarea silently stuck. Hide the remove button on read-only (agent) ghosts.
- `useQueue.clearAll` no longer derives `max` from pre-clear entry count;
resets to `metaMax ?? 0` so the next status_changed event lands authoritative
capacity.
- `senderKindOf` drops the unreachable metadata fallback; route on `queued_by`
alone since `dispatchTaskMessage` always sets it.
- Test loggers now write to stderr per CLAUDE.md "stderr for logs" guideline.
* test(web): align queue e2e selectors with new ghost-message UI
The ghost-message rewrite renamed button titles ("Cancel queued message"
→ "Remove queued message", "Edit message" → "Edit queued message") and
introduced a `data-testid="queued-ghost-list"` container. The
`message-queue.spec.ts` Playwright tests still pointed at the old titles.
* fix(queue): address second review pass — auth, drain race, tests
- WS handlers (`add` / `append` / `update`) now reject `user_id="agent"`
outright, closing the gap a hostile WS client could exploit by
impersonating the inter-task sender identity to overwrite agent
entries (greptile P1).
- WS `update` / `remove` now require `session_id` so the post-mutation
`MessageQueueStatusChanged` broadcast can never be silently skipped.
- `sqliteRepository.TakeHead` checks `RowsAffected()` after DELETE;
when two concurrent take callers race past the busy-timeout the
loser sees 0 affected rows and now returns `nil, nil` instead of
the already-drained message (would otherwise dispatch the same
prompt twice).
- `Service.GetStatus` returns `Entries: []` instead of `nil` on the
error path so the wire shape stays consistent (frontend already
guards but strict consumers wouldn't tolerate the type mismatch).
- New tests: `queue-api.test.ts` covers `rethrowQueueError` mappings
(queue_full / entry_not_found / generic / Error pass-through);
`session-slice.upsert.test.ts` covers `setQueueEntries`,
`removeQueueEntry`, and `clearQueueStatus`. Backend gains an
agent-impersonation handler test.
- `rethrowQueueError` now surfaces `WSError.message` for non-queue
errors instead of stringifying the whole object.
- Cleanup: replace unused `a, c := ...` discards in service_test
with `_, _ = ...`.
* fix(queue): scope update/remove by session_id (cross-session deletion guard)
The MCP `queue_full` error payload deliberately discloses sibling-task
entry IDs (so the calling agent's LLM can reason about the wedge state).
Without a session_id filter on `DeleteByID` / `UpdateContent`, a hostile
agent that received that payload could call `wsRemoveEntry` /
`wsUpdateMessage` against another task's entries and delete or rewrite
them — only the per-entry UUID was being checked.
- `Repository.UpdateContent` and `Repository.DeleteByID` now require
`sessionID` and add `AND session_id = ?` to the SQL guard. The memory
repo mirrors the scope (lookup keyed on session before the entry scan).
- `Service.UpdateMessage` / `Service.RemoveEntry` take `sessionID`; the
WS handlers thread `req.SessionID` through (already validated as
non-empty in the previous fixup).
- TypeScript: `session_id` is now required on `updateQueuedMessage` /
`removeQueuedEntry` params so callers fail at compile time, matching
the backend contract.
- Tests cover the cross-session attack: `RemoveEntry`/`UpdateMessage`
with an attacker-supplied session_id but a real entry id from another
session must return `ErrEntryNotFound` and leave the victim entry
untouched. SQLite repo gets parallel coverage.
* fix(queue): propagate transfer error + tighten WSError narrowing
- `Service.TransferSession` now returns an error so callers can fail
closed instead of silently leaving entries orphaned on the previous
session. The two existing call sites pick the right policy:
`switchSessionForStep` (reusing an existing session) propagates the
error so the workflow switch aborts; the new-session path logs and
continues, since the new session is already committed and rolling
back here would leave a half-switched workflow.
- `asWSError` now also narrows on `message` / `details`, so WS payloads
without a `code` field are still mapped to a meaningful `Error.message`
via `rethrowQueueError` (instead of "[object Object]"). Native
`Error` instances explicitly skip the WS-error branch so they pass
through untouched, preserving the existing pass-through guarantee.
- `queue-api.test.ts`: `expect.assertions(N)` on the catch-only tests
so a missing throw fails the test instead of silently passing.
* fix(queue): check TransferSession error in service tests
The TransferSession signature change in 83abe6d7 broke errcheck on two
test sites that hadn't been updated. Wrap them in require.NoError.
* refactor(mcp): reframe cross-task agent message wrapper to authorize action
Receivers were refusing peer-agent messages with "the user can talk to
them directly" and stalling. The old wrapper demoted peer messages
("rather than a direct user instruction") and explicitly licensed
refusal ("you may decline, push back"). New wording states the user is
not reading the thread, frames the peer as coordinating on the user's
behalf, and directs the receiver to act with user-prompt authority.
Reply path through message_task_kandev is unchanged.
* test(mcp): pin authorization wording in wrap_agent_message tests
Three reviewers (CodeRabbit, Greptile, Claude) flagged that the
behavioral intent of the new wrapper lives entirely in the body string
yet has no unit-level guard. Add assertions that pin the reply tool
name, the user-prompt-authority phrase, and the absence of the old
refusal-licensing wording, plus a short comment on the deliberate
privilege-escalation trade-off so future readers understand why peer
agents inherit user-prompt authority.
* feat(backend): multi-question support for ask_user_question_kandev
Reshape the MCP tool from a single prompt+options pair to a questions[]
array (1-4 entries, single-choice each, custom text fallback). The
clarification HTTP handler gates the response until every question has an
answer, fans out one chat message per question (sharing pending_id, with
question_index/question_total in metadata), and returns a JSON map keyed
by question id back to the agent. The orchestrator resume prompt now
formats multi-line Q1/A1, Q2/A2 summaries when the bundle has more than
one question. Mock-agent gets a clarification-multi scenario and
ask_user_question_test.go covers the new schema + map response. No
back-compat shim — local-first tool, single-PR breaking change.
* feat(web): refresh clarification overlay with multi-question + modern UI
Each per-question chat message gets its own card with a "Question N of M"
progress chip, a ✓ Answered badge once committed, and shadcn-aligned
option buttons with kbd hints. A new useClarificationGroup hook coordinates
the per-question commits (decision A) and posts every answer in a single
batch once the user finishes the bundle; X rejects the whole group. The
single-question case keeps the 1-9 / Esc keyboard shortcuts. Playwright
e2e adds 6 multi-question scenarios (rendering, full happy path, partial
state, mixed option/custom, skip-rejects-bundle, sibling-state) on top of
the existing single-question regression suite.
* fix(web): clarification carousel UX with stepper navigation + race fix
Replaces the vertically stacked card layout with a horizontal stepper:
numbered circle dots up top show step state (active/answered/pending),
the single active question card sits in the middle, and Back / Next /
Submit buttons sit at the bottom. Picking an option auto-advances to the
next step (single-question case auto-submits, no explicit Submit button).
The stepper steps are clickable so users can revise prior answers.
Keyboard shortcuts: 1-9 for option pick, ArrowLeft/Right for navigation,
Esc for skip.
Also fixes a race that surfaced as a 400 BadRequest on the
/api/v1/clarification/:id/respond endpoint when the user clicked an
option before all N messages of a multi-question bundle had streamed in:
findPendingClarificationGroup now gates on metadata.question_total and
returns an empty array until the full bundle has arrived.
Playwright suite expanded from 6 to 12 multi-question scenarios:
stepper rendering, auto-advance, Back, stepper jump, Submit gating,
happy path, mixed custom-text, revise-via-jump, skip-from-mid-step,
number-key shortcuts, Esc skip, first-step Back disabled.
* fix(clarification): address CodeRabbit/Greptile/Claude review comments
Backend:
- Single source of truth for question validation: rename/export
NormalizeAndValidateQuestions and call it from both the HTTP and the
WebSocket-side MCP handlers, so duplicate question ids and bad option
counts can't slip through either path.
- httpRespond now validates that every answer references a real question
id from the bundle and that no id is answered twice (regression tests
added).
- questionsFromMessages reorders by metadata.question_index so the
reconstructed bundle preserves the original question order.
- adapters.CreateClarificationRequestMessages rolls back already-created
messages when a later write in the bundle fails.
- extractQuestionAnswers always returns a JSON map (even on rejection,
with an envelope { rejected, reject_reason }) and simplifyAnswer
preserves both selected_option and custom_text when both are present.
- MCP tool description: rewrite the response example to match the actual
output shape; add minItems / maxItems to the questions and options
arrays in the JSON Schema.
- Test helper: drop the local contains() shim, use strings.Contains.
Frontend:
- useMemo([props]) was a no-op (props is always a fresh ref); split into
[message, messages] so it actually memoizes.
- Drop the dead "expired" SubmitState branch — the backend never returns
410 from this endpoint.
- Remove the asymmetric option-list dimming: the agent now receives both
selected_option and custom_text together, so a half-grey state was
misleading.
- New tests: pending-clarification.test.ts covers
findPendingClarificationGroup including the question_total gate, and
use-clarification-group.test.ts covers the hook's record/submit/skip
flows and the override-merge path used by the single-question case.
* fix(web): treat clarification 409 as success so duplicate submit doesn't stick the overlay
* fix(clarification): unblock agent on persistence failure + nil-guard rejected branch
- Add Store.CancelRequest(pendingID) and call it from both the WebSocket
MCP handler and the HTTP create-request handler when message creation
fails. Without it, the agent's WaitForResponse parked for the full
2-hour MCP timeout while no clarification cards ever reached the user.
Both handlers now return an explicit error response on failure.
- applyAnswersToMessages now guards h.repo == nil in the rejected branch
(parity with sibling expectedQuestionIDs).
- extractQuestionAnswers stubs for unanswered questions in a rejected
bundle now carry { answered: false, rejected: true } so agents reading
per-question payloads see the rejection without inspecting the
envelope.
- Hook test: added 409-as-ok regression coverage for both submit and
skip paths so the previous fix can't drift.
- Store test: covers CancelRequest unblocking a parked WaitForResponse.
* fix: drop unused e2e helper + use channel sync in CancelRequest test
* refactor(web): drop dead 'message' prop from clarification overlay
Both call sites pass 'messages' (the bundle group), so the legacy
single-message prop was unused. Tightening the prop type also lets the
useMemo depend on a single value.
* fix(web): ignore modifier-keyed events in clarification carousel shortcuts
Bare 1..9 / ArrowLeft / ArrowRight / Esc still drive the carousel, but
Cmd/Ctrl+1..9 (browser tab switch) and Alt+ArrowLeft (browser back) now
pass through as the user expects.
* feat(slack): add cookie-mode integration that triages messages via utility agent
Adds an install-wide Slack integration that polls the connected user's
own messages for `!kandev <instruction>`, hands the thread context to a
configured utility agent with the Kandev MCP server attached, and
creates the resulting task. Auth uses the user's xoxc- token + d cookie
so it works on locked-down Enterprise Slack tenants where bot installs
aren't possible.
Shared infra:
- ACP host-utility executor accepts McpServers on session/new
- New MCP tool list_repositories_kandev so the triage agent can pick the
right repo
- Template engine exposes Slack-specific variables for prompt injection
- secretadapter + healthpoll reused from jira/linear
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(slack): address PR review feedback round 9
- Drop dead `var _ = time.Second` no-op and its misleading comment in
trigger_test.go.
- `RecordAuthHealth` now invalidates the cached client when the probe
fails, so the poller self-recovers from credential rotation without
requiring a re-save.
- Stable secondary sort key (`workspace_id DESC`) on the legacy →
singleton migration so promoted-row selection is deterministic on
`updated_at` ties.
- Extract `categorySlack` constant in `engine.go` and update the
`VariableInfo.Category` doc-comment to list the full set of values.
- Realign `slack-integration/spec.md` with what shipped: cookie-mode +
`!kandev` triage as v1, with bot install / User OAuth / reaction &
slash & shortcut triggers moved under Future scope.
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(orchestrator): carry sender_task metadata through user message paths
Add WithSenderTask builder to UserMessageMeta and a metadata-aware
QueueMessageWithMetadata variant on the message queue. The drain path
in event_handlers_agent merges queued metadata into the recorded user
message so attribution survives the queue → DB transition.
* feat(mcp): attribute message_task_kandev calls to the sending agent
The MCP server inside agentctl now injects sender_task_id and
sender_session_id from its own server context. The backend handler
validates the sender (rejecting missing IDs, self-messages, and unknown
tasks), looks up the sender title, wraps the prompt in a <kandev-system>
attribution block, and propagates structured metadata across all three
delivery paths (queue, created-session, record+prompt). The wrapped
content lets the receiving agent identify the peer both live and on ACP
session resume; the existing sysprompt strip pipeline hides the wrapper
from the UI.
* feat(web): render sender-task badge on cross-task agent messages
User messages whose metadata carries sender_task_id now render a
clickable purple badge above the bubble, linking to the source task.
The badge live-resolves the sender's title from the kanban store and
falls back to a greyed snapshot when the task isn't loaded
(cross-workspace, deleted, etc.). Adds a non-subscribing useTaskById
selector so badges don't fan out WS subscriptions per message.
* test(e2e): cover cross-task agent message attribution
Eight scenarios driven through the mock-agent's MCP script directive:
queue path, prompt path, self-message rejection, unknown-target error,
badge link target, live title re-resolution after rename, kandev-system
wrapper preservation in raw_content, and prompt bodies containing their
own kandev-system tags. Adds an updateTaskTitle helper to ApiClient.
* fix: address CodeRabbit + Greptile P1 findings on PR #819
- requeueMessage now forwards queuedMsg.Metadata via QueueMessageWithMetadata
so sender attribution survives transient delivery failures and retries.
- CREATED-session branch in handleMessageTask records the user message AFTER
StartCreatedSession succeeds, so a launch failure no longer leaves an
orphaned attributed chat row.
- SenderTaskBadge: collapse identical displayTitle/fullTitle locals.
- E2E: extract waitForTargetIdle helper; replace the 1.5s raw sleep in the
collision-check test with the same poll the rest of the suite uses.
* fix: address Claude review suggestions on PR #819
- wrapAgentMessage strips </kandev-system> from the embedded sender title
before formatting. Without this, a title containing the closing tag
would short-circuit the non-greedy strip regex and leak the attribution
tail into the visible UI bubble. Metadata snapshot keeps the original
title so the badge still displays it.
- Add a regression test covering the malicious-title case.
- Document the deliberate cross-workspace messaging policy on the sender
lookup so future readers don't add a workspace-scope check (Q13 of the
feature plan locked this as intentional).
* fix(backend): return mcp message_task once dispatched, not after target turn ends
The MCP message_task_kandev tool was synchronously waiting for the target
session's entire turn to complete before returning, even though its
description advertises a fast dispatch status. For idle target sessions,
the call would hang for the full duration of the agent's response (with
no upper bound — waitForPromptDone has no timeout).
Threads a dispatchOnly flag from the MCP handler down through
PromptTask → executor.Prompt → PromptAgent → SendPrompt. When set,
SendPrompt returns once agentctl.Prompt accepts the prompt instead of
blocking on the agent's complete event. Stale completion signals from
prior dispatch-only prompts are drained at the start of SendPrompt so
they don't poison the next waiting call.
* fix: address PR review feedback
- Replace time.Sleep with channel-based wait for WS connection in new
SendPrompt tests, per CLAUDE.md (channel sync over time.Sleep for
non-subprocess tests).
- Drop redundant Warn that logged the remapped sentinel after the
original error was already logged by the preceding Warn.
---------
Co-authored-by: Kandev Agent <agent@kandev.dev>