| Age | Commit message (Collapse) | Author |
|---|
|
Merges 12 commits from github/main (formerly master) that were developed
independently. Key additions:
- LocalRunner: OpenAI-compatible local LLM execution (Ollama, LM Studio)
- Real GeminiRunner with full sandbox parity to ClaudeRunner
- llm.Client for enriching CI failures and elaboration via local model
- retry.ParseRetryAfter moved to shared package
- tokens_in/tokens_out columns in executions table
Conflict resolutions:
- Kept local main's VAPID/push, stories, projects, agent events schema
- Merged both sets of Config fields (local + LocalModel from github/main)
- Unified activePerAgent accounting (decActiveAgent helper)
- Removed duplicate helpers from claude.go (now in helpers.go)
- Fixed double-decrement bug in handleRunResult vs decActiveAgent
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Add CreateExecutionAndSetRunning to storage.DB and Store interface,
replacing the two sequential CreateExecution/UpdateTaskState calls in
executor.go. Eliminates the crash window where a task stays PENDING
with an orphaned RUNNING execution record.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Three related bugs fixed:
1. maybeUnblockParent: guard against promoting QUEUED leaf tasks (no
subtasks) to READY. The vacuously-true 'all subtasks done' check was
advancing tasks that stalled in QUEUED (due to a prior SQLite lock
error) to READY on server restart via RecoverStaleBlocked, despite
having only failed executions and no commits.
2. checkStoryCompletion: require COMPLETED (not just READY) for all
top-level tasks before advancing a story to SHIPPABLE. READY means
the checker agent is still pending or the task awaits human review;
a story with READY tasks is not ready to ship.
3. handleAcceptTask: call CheckStoryCompletion after a task is accepted
so stories with parent tasks (whose subtasks are all done and then
the parent is manually accepted) can auto-advance to SHIPPABLE.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Phase 4 of "local OSS models as agents" plan. Closes the epic.
When an execution finishes and the agent did NOT write a "## Summary"
heading in its stdout (so the existing extractSummary path returns
empty), and the Pool has a local LLM configured, we now synthesize a
2-4 sentence summary from the assistant text content of the log tail.
Behavior:
- Primary path unchanged: if the agent wrote "## Summary", that wins
byte-for-byte (TestPool_HandleRunResult_ExtractSummaryWins guards).
- Fallback path: empty extractSummary + Pool.LLM != nil → synthesize.
- All-empty path: when no LLM is configured, summary stays empty —
identical to pre-Phase-4 behavior.
Implementation:
- Pool gains an LLM *llm.Client field, wired in serve.go and run.go
alongside Classifier.LLM (same localClient used everywhere).
- New synthesizeSummary in internal/executor/summary.go:
* 6s timeout so a slow local model can't stall finalization
* 16 KB tail cap on the stdout log
* readAssistantTextTail seeks to the last 16 KB and skips the
first (likely partial) line, parses each line as a stream-json
event, joins assistant `text` blocks (skips system/result/etc).
* Returns "" on any error so the caller's behavior never regresses.
- handleRunResult: 3-tier summary resolution — exec.Summary set by
runner → extractSummary → synthesizeSummary → empty.
- minimalMockStore now records UpdateTaskSummary calls (additive;
existing tests unaffected) so integration tests can assert.
Tests (9 new):
- synthesizeSummary nil client / empty path / missing file all
return "" without HTTP calls.
- empty assistant content short-circuits without LLM call.
- success path returns trimmed body, with both assistant texts in
the user prompt.
- LLM 500 returns "" (caller handles same as no-summary).
- readAssistantTextTail seeks past early content in a large file.
- Pool integration: ## Summary present → LLM not called, agent text
used. ## Summary absent + LLM set → LLM called, synthesized summary
recorded against the right task ID.
Plan: docs/plans/local-oss-runner.md.
Epic complete. Post-epic deep cleanup queue captured in the same plan
file for follow-up.
https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J
|
|
Fix 1: Remove QuestionRegistry and related types (QuestionHandler, PendingQuestion)
from question.go -- nothing reads Pool.Questions or uses the registry. Remove
NewQuestionRegistry() call from NewPool and the Questions field from Pool.
Remove the now-superfluous registry tests; keep stream/parse helpers which are
still used by the claude runner.
Fix 2: Check scanner.Err() after the parseStream loop so I/O errors from the
scanner are not silently swallowed when streamErr is still nil.
Fix 3: Delete internal/api/changestats.go -- the parseChangestatFromFile and
parseChangestatFromOutput wrappers were only needed to support processResult(),
which no longer calls them; they are unreachable dead code.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
failure states
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
consecutive failures
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
When a story is approved with pre-created subtasks, parent tasks are
QUEUED but never run. Their subtasks complete, but:
- maybeUnblockParent only handled BLOCKED parents, not QUEUED ones
- checkStoryCompletion required ALL tasks (incl. subtasks) to be done
Fixes:
- maybeUnblockParent now also promotes QUEUED parents to READY when all
subtasks are COMPLETED
- checkStoryCompletion only checks top-level tasks (parent_task_id="")
- RecoverStaleBlocked now also scans QUEUED parents on startup and
triggers checkStoryCompletion if it promotes them
- Add QUEUED→READY to valid state transitions (subtask delegation path)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- Add workerWg to Pool; Shutdown() closes workCh and waits for all
in-flight execute/executeResume goroutines to finish
- Signal handler now shuts down HTTP first, then drains the pool
- ShutdownTimeout config field (toml: shutdown_timeout); default 3m
- Tests: WaitsForWorkers and TimesOut
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
createStoryBranch was pushing to 'origin' which doesn't exist — branches
never landed in the bare repo so agents couldn't clone them. Now uses
the project's RemoteURL (bare repo path) directly for fetch and push.
Raise drain threshold from 2 to 3 consecutive failures to reduce false
positives from transient errors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- executor.go: merge story branch to main before deploy
- container.go: error messages reference git push origin main
- api/stories.go: create story branch from origin/main (drop master fallback)
- executor_test.go: test setup uses main branch
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- triggerStoryDeploy: fetch/checkout/merge --no-ff/push before running deploy script (ADR-007)
- executor_test: TestPool_StoryDeploy_MergesStoryBranch proves merge happens
- seed.go: add doot project with deploy script; wire claudomator deploy script
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
|
|
Add checkValidationResult which inspects the final task.State of a
completed validation task and updates the story to REVIEW_READY (pass)
or NEEDS_FIX (fail). Wire into handleRunResult so stories in
VALIDATING state are dispatched to checkValidationResult instead of
checkStoryCompletion, covering both success and FAILED terminal paths.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
|
|
Add triggerStoryDeploy to Pool: fetches story's project, runs its
DeployScript via exec.CommandContext, and advances story to DEPLOYED on
success. Wire into checkStoryCompletion with go p.triggerStoryDeploy
after the SHIPPABLE transition. Covered by TestPool_StoryDeploy_RunsDeployScript.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Agent added: Store on ContainerRunner (direct story/project lookup), --reference
clone for speed, explicit story branch push, checkStoryCompletion → SHIPPABLE.
My additions: BranchName on Task as fallback when Store is nil, tests updated
to match checkout-after-clone approach.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- Add BranchName field to task.Task (populated from story at execution time)
- Add GetStory to executor Store interface; resolve BranchName from story in both
execute() and executeResume() parallel to RepositoryURL resolution
- Pass --branch <name> to git clone when BranchName is set; default clone otherwise
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
check, deployment status
- ContainerRunner: add Store field; clone with --reference when story has a
local project path; checkout story branch after clone; push to story branch
instead of HEAD
- executor.Store interface: add GetStory, ListTasksByStory, UpdateStoryStatus
- Pool.handleRunResult: trigger checkStoryCompletion when a story task succeeds
- Pool.checkStoryCompletion: transitions story to SHIPPABLE when all tasks done
- serve.go: wire Store into each ContainerRunner
- stories.go: update createStoryBranch to fetch+checkout from origin/master base;
add GET /api/stories/{id}/deployment-status endpoint
- server.go: register deployment-status route
- Tests: TestPool_CheckStoryCompletion_AllComplete/PartialComplete,
TestHandleStoryDeploymentStatus
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- Add GetProject to Store interface used by executor
- Resolve RepositoryURL from project registry when task.RepositoryURL is empty
- Call SeedProjects at server startup so the project registry is populated
- Add GetProject stub to minimalMockStore in executor tests
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
TestPool_MaxPerAgent_BlocksSecondTask
|
|
creds, auth recovery
- maxPerAgent=1: only 1 in-flight execution per agent type at a time; excess tasks are requeued after 30s
- Drain gate: after 2 consecutive failures the agent is drained and a question is set on the task; reset on first success; POST /api/pool/agents/{agent}/undrain to acknowledge
- Pre-flight credential check: verify .credentials.json and .claude.json exist in agentHome before spinning up a container
- Auth error auto-recovery: detect auth errors (Not logged in, OAuth token has expired, etc.) and retry once after running sync-credentials and re-copying fresh credentials
- Extracted runContainer() helper from ContainerRunner.Run() to support the retry flow
- Wire CredentialSyncCmd in serve.go for all three ContainerRunner instances
- Tests: TestPool_MaxPerAgent_*, TestPool_ConsecutiveFailures_*, TestPool_Undrain_*, TestContainerRunner_Missing{Credentials,Settings}_FailsFast, TestIsAuthError_*, TestContainerRunner_AuthError_SyncsAndRetries
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
detection
- Detect Gemini TerminalQuotaError (daily quota) as BUDGET_EXCEEDED, not generic FAILED
- Surface container stderr tail in error so quota/rate-limit classifiers can match it
- Add agent_events table to persist rate-limit start/recovery events across restarts
- Add GET /api/agents/status endpoint returning live agent state + 24h event history
- Stats dashboard: agent status cards, 24h availability timeline, per-run execution table
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- Fix Critical Bug 1: Only remove workspace on success, preserve on failure/BLOCKED.
- Fix Critical Bug 2: Use correct Claude flag (--resume) and pass instructions via file.
- Fix Critical Bug 3: Actually mount and use the instructions file in the container.
- Address Design Issue 4: Implement Resume/BLOCKED detection and host-side workspace re-use.
- Address Design Issue 5: Consolidate RepositoryURL to Task level and fix API fallback.
- Address Design Issue 6: Make agent images configurable per runner type via CLI flags.
- Address Design Issue 7: Secure API keys via .claudomator-env file and --env-file flag.
- Address Code Quality 8: Add unit tests for ContainerRunner arg construction.
- Address Code Quality 9: Fix indentation regression in app.js.
- Address Code Quality 10: Clean up orphaned Claude/Gemini runner files and move helpers.
- Fix tests: Update server_test.go and executor_test.go to work with new model.
|
|
Move activePerAgent decrement/deletion out of execute() and
executeResume() defers and into the code paths immediately before each
resultCh send (handleRunResult and early-return paths). This guarantees
that when a result consumer reads from the channel the map is already
clean, eliminating a race between defer and result receipt.
Remove the polling loop from TestPool_ActivePerAgent_DeletesZeroEntries
and check the map state immediately after reading the result instead.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
The deferred activePerAgent cleanup in execute() runs after resultCh is
sent, so a consumer reading Results() could observe the map entry before
it was removed. Poll briefly (100ms max) instead of checking immediately.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
When the server restarts after all subtasks complete, the parent task
was left stuck in BLOCKED state because maybeUnblockParent only fires
during a live executor run. RecoverStaleBlocked() scans all BLOCKED
tasks on startup and re-evaluates them using the existing logic.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Files changed: CLAUDE.md, internal/api/changestats.go,
internal/executor/executor.go, internal/executor/executor_test.go,
internal/task/changestats.go (new)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
sandboxes
#1 - Diagnostics: tailFile() reads last 20 lines of subprocess stderr and
appends to error message when claude/gemini exits non-zero. Previously all
exit-1 failures were opaque; now the error_msg carries the actual subprocess
output.
#4 - Restart recovery: RecoverStaleRunning() now re-queues tasks after
marking them FAILED, so tasks killed by a server restart automatically
retry on the next boot rather than staying permanently FAILED.
#2 - Stale sandbox: If a resume execution's preserved SandboxDir no longer
exists (e.g. /tmp purge after reboot), clone a fresh sandbox instead of
failing immediately with "no such file or directory".
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
|
|
- Added an agent selector (Auto, Claude, Gemini) to the Start Next Task button.
- Updated the backend to pass query parameters as environment variables to scripts.
- Modified the executor pool to skip classification when a specific agent is requested.
- Added --agent flag to claudomator start command.
- Updated tests to cover the new functionality.
|
|
Add Pool.RecoverStaleQueued() that lists all QUEUED tasks from the DB on
startup and re-submits them to the in-memory pool. Previously, tasks that
were QUEUED when the server restarted would remain stuck indefinitely since
only RUNNING tasks were recovered (and marked FAILED).
Called in serve.go immediately after RecoverStaleRunning().
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
pickAgent() deterministically selects the agent with the fewest active tasks,
skipping rate-limited agents. The classifier now only selects the model for the
pre-assigned agent, so Gemini gets tasks from the start rather than only as a
fallback when Claude's quota is exhausted.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Both execute() and executeResume() shared ~80% identical post-run logic:
error classification (BLOCKED, TIMED_OUT, CANCELLED, BUDGET_EXCEEDED, FAILED),
state transitions, result emission, and UpdateExecution. Extract this into
handleRunResult(ctx, t, exec, err, agentType) on *Pool. Both functions now
call it after runner.Run() returns.
Also adds TestHandleRunResult_SharedPath which directly exercises the new
function via a minimalMockStore, covering FAILED, READY, COMPLETED, and
TIMED_OUT classification paths.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Add maybeUnblockParent helper that transitions a BLOCKED parent task to
READY once every subtask is in the COMPLETED state. Called in both
execute() and executeResume() immediately after a subtask is marked
COMPLETED. Any non-COMPLETED sibling (RUNNING, FAILED, etc.) keeps the
parent BLOCKED.
Tests added:
- TestPool_Submit_LastSubtask_UnblocksParent
- TestPool_Submit_NotLastSubtask_ParentStaysBlocked
- TestPool_Submit_ParentNotBlocked_NoTransition
|
|
When a top-level task (ParentTaskID == "") finishes successfully,
check for subtasks before deciding the next state:
- subtasks exist → BLOCKED (waiting for subtasks to complete)
- no subtasks → READY (existing behavior, unchanged)
This applies to both execute() and executeResume().
Adds ListSubtasks to the Store interface.
Tests:
- TestPool_Submit_TopLevel_WithSubtasks_GoesBlocked
- TestPool_Submit_TopLevel_NoSubtasks_GoesReady
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
All previously ignored errors from p.store.UpdateTaskState() and
p.store.UpdateTaskQuestion() in execute() and executeResume() now log
with structured context (taskID, state, error).
Introduces a Store interface so tests can inject a failing mock store.
Adds TestPool_UpdateTaskState_DBError_IsLoggedAndResultDelivered to
verify that a DB write failure is logged and the result is still
delivered to resultCh.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
activePerAgent: delete zero-count entries after decrement so the map
doesn't accumulate stale keys for agent types that are no longer active.
rateLimited: delete entries whose deadline has passed when reading them
(in both the classifier block and the execute() pre-flight), so stale
entries are cleaned up on the next check rather than accumulating forever.
Both fixes are covered by new regression tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
On restart, any tasks in RUNNING state have no active goroutine.
RecoverStaleRunning() marks them FAILED (retryable) and closes
their open execution records with an appropriate error message.
Called once from serve.go after the pool is created.
|
|
Fix: use file:// prefix in git fetch during sandbox teardown to force
pack-protocol transfer. The local optimization uses hard links which
fail across devices and with mixed-owner object stores.
Feature: before running a task, query prior failed/timed-out executions
and prepend their error messages to the agent's --append-system-prompt.
This tells the agent what went wrong in previous attempts so it doesn't
repeat the same mistakes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- Resolve conflicts in API server, CLI, and executor.
- Maintain Gemini classification and assignment logic.
- Update UI to use generic agent config and project_dir.
- Fix ProjectDir/WorkingDir inconsistencies in Gemini runner.
- All tests passing after merge.
|
|
Replace the at-capacity error return from Submit/SubmitResume with an
internal workCh/doneCh channel pair. A dispatch() goroutine blocks
waiting for a free slot and launches the worker goroutine, so tasks are
buffered up to 10x pool capacity instead of being rejected.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
agent test)
|
|
|
|
POST /api/tasks/{id}/cancel now works. Pool tracks a cancel func per
running task ID; Cancel(taskID) calls it and returns false if the task
isn't running. The execute goroutine registers/deregisters the cancel
func around the runner call.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Add LogPather interface; ClaudeRunner implements it via ExecLogDir().
Pool pre-populates stdout_path/stderr_path/artifact_dir on the execution
record before CreateExecution, so paths are in the DB from the moment
a task starts running.
ClaudeRunner.Run() skips path assignment when already set by the pool.
Also update scripts/debug-execution to derive paths from the known
convention (<data-dir>/executions/<exec-id>/) as a fallback for
historical records that predate this change.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Top-level tasks now land in READY after successful execution instead of
going directly to COMPLETED. Subtasks (with parent_task_id) skip the gate
and remain COMPLETED. Users accept or reject via new API endpoints:
POST /api/tasks/{id}/accept → READY → COMPLETED
POST /api/tasks/{id}/reject → READY → PENDING (with rejection_comment)
- task: add StateReady, RejectionComment field, update ValidTransition
- storage: migrate rejection_comment column, add RejectTask method
- executor: route top-level vs subtask to READY vs COMPLETED
- api: /accept and /reject handlers with 409 on invalid state
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
