| Age | Commit message (Collapse) | Author |
|---|
|
|
|
(Phase 7c)
Two independent pieces, completing Phase 7.
Epic-proposal tool: AgentChannel gains a 5th method, ProposeEpic(ctx,
EpicProposal{Name, Description, StoryIDs}) (epicID, err), implemented on
storeChannel -- matches an existing epic by exact name or creates one
(DiscoverySource: "agent"), sets epic_id on each resolvable story (skips,
doesn't fail, on an unresolved ID), emits KindEpicProposed attached to the
epic's own ID with payload {epic_id, name, story_ids}. Wired into both
transports exactly like Phase 6 wired role into spawn_subtask: a new
propose_epic tool in the native tool-use loop (internal/agentloop/tools.go)
and the MCP transport (internal/executor/agentmcp.go). This is the mechanism
for a discovery/planner-role agent to act on its own judgment that several
stories it's been given form one cohesive initiative -- the judgment itself
lives in the calling agent's instructions/model, not in this code.
AskUser-timeout escalation: extends the existing Scheduler (Phase 5's
retry-then-escalate watcher) rather than adding a new component, since
"stuck task needs escalation" is exactly what it already does. Finds
role-typed BLOCKED tasks whose question has been outstanding longer than
SchedulerConfig.AskUserTimeoutSeconds (default 10 minutes) using
task.UpdatedAt as the outstanding-since timestamp -- no new column needed,
since UpdateTaskQuestion already stamps it the instant a question is
recorded and nothing else touches the row while BLOCKED. Resolves the next
ladder tier from the latest execution's EscalationRung, records the
system-authored fallback answer as an audit-trail task.Interaction, clears
the question, sets the new tasks.needs_review flag, emits KindEscalated
(now carrying a trigger field: "failure" vs "ask_user_timeout" for the
existing failure-retry path vs this one), and resumes via Pool.SubmitResume
at the escalated tier -- degrading to same-tier resume with final:true if
the ladder's exhausted or no role config exists, since unblocking the task
takes priority over having somewhere higher to escalate to.
GET /api/tasks?needs_review=true surfaces auto-decided tasks for human
review.
go build/vet/test -race -count=1 all pass, full suite (20 packages), run
twice to rule out flakiness in the new tests. (One pre-existing, unrelated
test -- TestHandleRunTask_CascadesRetryToFailedDeps, a tempdir-cleanup race
-- appeared once under full-suite load per the implementing agent's report
and did not reproduce in this verification's runs either; not a regression
from this work.)
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Builder->Evaluators->Arbitration->accept (Phase 7b)
A deterministic, poll-based watcher (internal/scheduler.StoryOrchestrator,
sibling to the Phase 5 Scheduler) that drives a story.Story through its
execution pipeline, rather than relying on an LLM agent to correctly
orchestrate its own fan-out via tool calls.
Mechanism: polling, not a handleRunResult hook. Every task the orchestrator
watches (a story's root/Builder task, 4 Evaluators, Arbitration) is
top-level (no ParentTaskID), and executor.Pool.handleRunResult only ever
lands a top-level task at READY or BLOCKED -- never COMPLETED directly, since
that transition normally requires a human/chatbot POST /api/tasks/{id}/accept
in a different package. A handleRunResult hook would never observe it;
polling doesn't care how/whether a task reached a given state.
Stages: Builder COMPLETED -> spawn 4 role-typed Evaluator tasks
(evaluator_quality/security/correctness/performance, DependsOn: [builder],
no ParentTaskID -- true DAG siblings, not delegated subtasks) + story ->
VALIDATING. Each Evaluator COMPLETED -> emit KindEvalVerdict (attached to
the story's ID, so one GET /api/stories/{id}/events call surfaces every
verdict). All 4 Evaluators COMPLETED -> spawn 1 Arbitration task
(role: planner, DependsOn: all 4 evaluator IDs). Arbitration COMPLETED ->
emit KindArbitrationDecided, story -> REVIEW_READY. POST
/api/stories/{id}/accept (mirrors handleAcceptTask) -> DONE, emits
KindHumanAccepted.
Fixes a gap caught before merging: since none of Builder/Evaluators/
Arbitration have a ParentTaskID, none of them auto-complete -- each would
otherwise need a separate manual /api/tasks/{id}/accept, meaning 6 human
clicks per story before ever reaching the intended single story-level gate.
StoryOrchestrator.autoAccept now transitions each of these specific tasks
READY->COMPLETED itself (via the same validated Store.UpdateTaskState path
acceptTask uses), scoped only to tasks already established as part of a
story's pipeline (root task, or role-matched dependents from
ensureEvaluators/ensureArbitration) -- never a blanket sweep of unrelated
READY tasks. This makes POST /api/stories/{id}/accept the system's only
required human touchpoint for the whole chain, matching the design goal
that story (not task/subtask) is the human-interaction atom.
Idempotency: structural for task-creation stages (ensureEvaluators/
ensureArbitration check ListDependents for already-existing role-matched
tasks before creating -- crash/restart-safe); story.Status=="VALIDATING"
gates the Arbitration->REVIEW_READY write (nothing further downstream to
check structurally there); an in-memory handledVerdicts set (mirrors
Scheduler.handled) dedupes per-evaluator KindEvalVerdict emission across
poll ticks, resetting harmlessly on restart.
Documented simplification: finalizeArbitration never parses the Arbitration
summary for approve/reject -- always routes to REVIEW_READY; NEEDS_FIX is
manually settable via PUT /api/stories/{id}. A later phase could close this
with a dedicated verdict-reporting AgentChannel method instead of parsing
free text.
go build/vet/test -race -count=1 all pass, full suite (20 packages).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Two parts:
Part A (fixes a gap from Phase 1): Groq/OpenRouter/OpenAI were documented in
docs/api-keys-setup.md as usable once configured, but nothing actually
constructed runners for them. internal/cli/cloudrunners.go consolidates
anthropic/google/groq/openrouter/openai NativeRunner construction into one
table-driven registerCloudRunners() helper, replacing the two hand-written
per-provider blocks in serve.go/run.go. Groq/OpenRouter/OpenAI reuse
openaicompat (no new adapter code) at SandboxKind: "docker".
Part B: the token-husbanding harness's core routing mechanism.
- internal/role: RoleConfig/Tier/Rung -- a role's system prompt and a
multi-tier (provider, model) escalation ladder, versioned via config_json.
- storage: new role_configs table (draft/active/retired, UNIQUE(role,
version)) with transactional activate-retires-prior-active semantics;
new executions.escalation_rung column.
- task.AgentConfig.Role string -- purely additive; every existing task shape
(Agent.Role == "") is unaffected, proven by TestPool_Execute_NonRoleTask_Unaffected
plus the full pre-existing suite passing unchanged.
- executor.Pool.execute(): role-typed tasks with no Agent.Type yet resolve
tier 0 of their active ladder (round-robin across multi-candidate tiers,
skipping rate-limited providers, falling back to soonest-clearing) before
the existing pickAgent/Classifier path runs; SystemPrompt applies to
Agent.SystemPromptAppend. Already-resolved role tasks (scheduler resubmits)
get their escalation_rung re-derived read-only via findTierIndex.
- internal/scheduler: polls role-typed FAILED tasks, retries at the same
rung under MaxRetries or escalates to the next tier's first candidate when
budget.Accountant.Allow() permits (emitting event.KindEscalated), else
leaves the task FAILED with a final:true KindEscalated event. An
in-memory per-execution-ID "handled" set keeps the poll loop convergent.
Started by `serve` only, config knob [scheduler].poll_interval_seconds.
- internal/api: POST/GET /api/roles/{role}/versions, POST
/api/roles/{role}/activate -- unauthenticated, matching the existing
projects/tasks REST endpoints' auth posture (only chatbot MCP, agent MCP,
and WebSocket are api_token-gated in this codebase today).
Documented as stored-but-not-yet-enforced (CLAUDE.md Design Debt, matching
how task.Priority/RetryConfig are already documented): RoleConfig.Tools/
SandboxKind don't affect dispatch yet; DefaultBudgetUSD is read narrowly as
the scheduler's escalation cost estimate, not enforced at initial dispatch;
scheduler escalation always targets Candidates[0] (no round-robin, unlike
initial-dispatch tier-0 resolution); the scheduler's dedupe is per-process
and resets on restart (idempotent, harmless).
go build/vet/test -race -count=1 all pass, 21 packages.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Adds internal/provider/google, the second native cloud adapter (following
internal/provider/anthropic's pattern) on top of Phase 1's provider-neutral
tool-use loop, wired to a Docker-sandboxed NativeRunner under agent.type:
"google" -- a separate execution path and budget bucket from the existing
CLI-subprocess "gemini" ContainerRunner, which is untouched.
Wire-format research (the highest-risk part of this adapter): Gemini's
multi-turn function-calling shape was resolved by cross-referencing the
REST API reference's own generateContent example against the go-genai SDK's
struct tags on GitHub -- both agree on functionCall/functionResponse parts
keyed by "name" (with an optional "id" for round-tripping ToolCall.ID),
with the response fed back inside a "user"-role Content (Gemini has no
tool/function role, mirroring Anthropic's lack of one). A separate fetched
source (the function-calling guide page) was deliberately discarded as a
reference for this shape -- it documents a different, newer "Interactions
API" whose call_id/type:"function_result" structure doesn't fit the
contents/parts/candidates shape used everywhere else.
- internal/provider/google: request/response translation, systemInstruction
handling, role mapping (assistant->model, tool-results->user role),
per-model-prefix pricing table (2.5 Pro/Flash/Flash-Lite, 2.0, 1.5 tiers)
- internal/retry: IsRateLimitError additively extended for RESOURCE_EXHAUSTED
- internal/config: RunnersConfig.Google/GoogleEnabled()
- internal/cli/serve.go, run.go: runners["google"] construction mirroring
the Anthropic wiring exactly (Docker sandbox default)
- docs/api-keys-setup.md: Google marked wired-up, budget-bucket/disable/
verify guidance added matching the Anthropic section
go build/vet/test -race all pass. No live Gemini API key available in this
environment; verified via fake-httptest-server adapter tests (plain text,
tool-use round-trip, multi-turn tool-result, rate-limit error matching) plus
a Pool/NativeRunner routing test. Live E2E is a follow-up once a key is
configured, same as Phase 2's Anthropic adapter.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Gives native-API-driven agents (currently just the Phase 2 Anthropic
adapter) real container isolation, decoupled from model invocation --
the model call happens in the Go process via provider.Provider, only tool
execution happens in the container, unlike the CLI-subprocess ContainerRunner
(left completely untouched) where the claude/gemini CLI runs inside the
container.
- internal/sandbox/dockersandbox.go: Sandbox via a long-lived
`docker run -d ... sleep infinity` container (started once per execution,
not per tool call), host-side git clone + bind-mount matching
ContainerRunner's existing pattern, docker exec for read/write/bash/glob.
Reuses images/agent-base (claudomator-agent:latest) rather than
standing up a second image. WorkDir()/resume persists the host bind-mount
directory (matching HostSandbox's contract); a resumed sandbox lazily
starts a fresh container against that directory rather than trying to
reattach to a possibly-gone one.
- internal/sandbox/guard.go, hooks.go: Hook interface (CheckBash/CheckWrite),
Guarded wrapper, DenylistBashHook (rm -rf /, force-push, curl|sh, sudo,
chmod 777, dd if=) and ProtectedPathHook (.git/**, .env*, credentials/,
.github/workflows/**). A rejection returns *RejectionError, which
agentloop/tools.go now recognizes and feeds back to the model as a normal
(non-fatal) tool-error result instead of aborting the run.
- NativeRunner wraps whichever Sandbox it builds (Host or Docker) in
Guarded{Hooks: DefaultHooks()} uniformly. The "anthropic" runner now uses
DockerSandbox; "local" stays on HostSandbox by design (local models are
the harness's more-trusted, lower-stakes-to-run tier).
Docker is not installed in this dev environment (no docker/podman/containerd
on PATH), so DockerSandbox's real container-lifecycle behavior is verified
via mocked-command unit tests only -- go test -race ./... passes throughout,
with the two real-daemon integration tests gated behind a dockerAvailable(t)
check and skipping here. Live verification against an actual Docker host is
a follow-up before relying on the "anthropic" agent type in production.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Adds internal/provider/anthropic, the first genuinely new provider.Provider
implementation on top of Phase 1's provider-neutral tool-use loop, alongside
(not replacing) the existing Docker/CLI-subprocess ContainerRunner path for
the "claude" agent type:
- internal/provider/anthropic: translates the neutral ChatRequest/ChatResponse
shape to/from Anthropic's Messages API content-block format (system as a
top-level field, tool_use/tool_result blocks, no "tool" role -- tool
results become user-role messages), with a per-model-prefix pricing table
for CostUSD
- internal/retry: IsRateLimitError additively extended to recognize
Anthropic's rate_limit_error/overloaded_error/529 shapes
- internal/config: RunnersConfig.Anthropic/AnthropicEnabled() gate
- internal/cli/serve.go, run.go: register runners["anthropic"] as a
NativeRunner when [providers.anthropic].api_key is set and enabled --
tracked as a distinct executions.agent="anthropic" budget bucket, separate
from the CLI-subprocess "claude" runner even though both bill the same
Anthropic account
go build/vet/test -race all pass. No live Anthropic API key is available in
this environment, so verification is via fake-httptest-server adapter tests
(12 cases, incl. multi-turn tool_result round-trip and rate-limit error
matching) plus a Pool/NativeRunner routing test proving agent.type:
"anthropic" actually reaches the new provider. Live end-to-end verification
against the real API is a follow-up once a key is configured.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Splits LocalRunner's OpenAI-specific agentic loop into reusable, provider-
agnostic pieces so later phases can add native Anthropic/OpenAI/Google/Groq/
OpenRouter adapters without duplicating the control flow:
- internal/provider: neutral Provider/ChatRequest/ChatResponse types, plus
an openaicompat adapter wrapping the existing internal/llm.Client unchanged
- internal/sandbox: Sandbox interface + HostSandbox (git clone/push/cleanup,
read_file/write_file/run_bash/glob), lifted verbatim from local.go/localtools.go
- internal/agentloop: the extracted tool-use loop (request/response/tool-
dispatch/loop, ask_user blocking, stream-json envelope, summary fallback)
- internal/agentchannel: AgentChannel/SubtaskSpec/BlockedError/ErrAgentBlocked
moved out of internal/executor so agentloop can use them without an import
cycle; internal/executor re-exports via type aliases, so no call site changes
- internal/executor/nativerunner.go: NativeRunner replaces LocalRunner,
wiring agentloop.Loop + openaicompat + HostSandbox together
- config.Providers map[string]ProviderConfig added (unused until Phase 2+)
Zero intended behavior change: go test -race ./... passes across all
packages, and end-to-end stream-json/summary/changestats output was verified
byte-compatible against a fake OpenAI-compatible server. Adds test coverage
for sandbox tool-dispatch (git clone/push, read/write/bash/glob) that
LocalRunner never had.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
|
|
Remove the dead stories/checker backend tracked as design debt in CLAUDE.md:
- Delete internal/api/stories.go, stories_test.go, elaborate.go
- Delete internal/task/story.go, story_test.go
- Remove story/checker columns from storage schema and all CRUD methods
- Remove checkStoryCompletion, spawnCheckerTask, triggerStoryDeploy,
createValidationTask, checkValidationResult, ShipStory, CheckStoryCompletion
from executor; simplify handleRunResult
- Remove story/checker fields from task.Task (StoryID, AcceptanceCriteria,
CheckerForTaskID, CheckerReport)
- Remove story routes and geminiBinPath from API server
- Move claudeJSONResult/extractJSON from elaborate.go to validate.go
- Rename ensureStoryBranch -> ensureBranch in ContainerRunner
- Fix git identity in bare-repo tests; fix initial-branch to use main
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
loopback-only bind
Key features from OSS branch:
- Budget gating: rolling per-provider spend caps with BUDGET_EXCEEDED task state
- Agent MCP back-channel: runners mint tokens; /mcp endpoint resolves them
- Chatbot MCP server at /chatbot/mcp (requires api_token in config)
- Event timeline: unified event stream replacing ad-hoc question/summary flows
- Loopback-only default bind (127.0.0.1:8484); external_bind_allowed=true to expose
- repository_url required on task creation (enforces traceability)
- Auto-checker: spawns verification task after each execution
Conflict resolutions:
- serve.go: keep cfg.Runners.XEnabled() conditional registration from main + agentRegistry from oss
- config.go: keep RunnersConfig from main + BudgetConfig/ExternalBindAllowed from oss
- server.go: handleStaticFiles (base-path rewrite) kept; deduplicated duplicate from both sides
- executor/claude.go: accepted oss deletion (ClaudeRunner replaced by ContainerRunner)
- container_test.go: added noopChannel + AgentChannel parameter to Run call
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Allows running multiple instances (e.g. /claudomator and /claudomator-oss)
behind a reverse proxy. The server rewrites the base-path meta tag in
index.html at request time rather than baking it into the embed.
Also adds --branch support to deploy script for isolated branch builds
via git worktrees.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
The server now defaults to binding 127.0.0.1 and refuses to bind a non-loopback
address (:8484, 0.0.0.0, a LAN IP, …) unless external_bind_allowed = true is set
in config — failing loud at startup instead of silently exposing itself.
External access is expected to go through a reverse proxy (Tailscale / Cloudflare
Access / Caddy), per the locked auth model.
- config: ExternalBindAllowed flag + ValidateBindAddr/isLoopbackHost (tested
across loopback, all-interfaces, LAN, and override cases).
- cli: --addr default is now 127.0.0.1:8484; serve() validates before binding.
Per-client bearer rotation stays deferred (single shared token for now).
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
|
|
Adds GET /api/budget returning per-provider rolling-window headroom (empty when
budget gating is unconfigured), wired from serve.go via SetBudget. The web UI
polls it and renders a chip per limited provider in the header, flagging any
under 20% remaining. New pure JS helpers formatBudgetHeadroom/
renderBudgetHeadroom are unit-tested; the endpoint is covered by Go handler
tests (empty/reports/500). UI render not browser-verified in this environment.
Completes Phase 6: spend accounting + dispatcher gating + observability surface.
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
|
|
(Phase 6)
The pool now consults a BudgetGate before taking an agent slot. If running on
the chosen paid provider could breach its rolling window (estimated by the
task's max_budget_usd), it reroutes to the free local runner when one is
registered; otherwise it stops before running and marks the task
BUDGET_EXCEEDED. serve.go builds a budget.Accountant from [budget] config and
wires it into the pool (only when limits are configured).
Allows the QUEUED → BUDGET_EXCEEDED transition, since the gate blocks a queued
task before it ever reaches RUNNING. Covered by pool tests for both the block
and reroute paths against a fake gate.
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
|
|
Adds a chatbot-facing MCP server mounted at /chatbot/mcp, guarded by the shared
API bearer token (new config api_token, wired through SetAPIToken). Tools:
submit_task, list_tasks, get_task, get_events, answer_question, accept_task,
reject_task, cancel_task. submit_task creates and immediately queues a task,
resolving the repository URL from a named project when not given explicitly.
To keep the REST API and the MCP surface from drifting, the accept/reject/
cancel/answer operations are extracted into a shared service layer (taskops.go)
with typed errors mapped to REST status codes; the existing HTTP handlers now
delegate to it. The endpoint is only served when a token is configured and
presented as a bearer.
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
|
|
ContainerRunner now mints a per-task MCP token (from an injected Registry),
writes a claude mcp-config into the workspace pointing at the host agent MCP
server over host.docker.internal with that bearer, and adds --mcp-config to the
in-container claude invocation. The token is revoked when the run ends. After
the run, a buffered ask_user (PendingQuestion on the channel) is converted into
a BlockedError — the MCP path to BLOCKED — with the file-based question.json
kept as a fallback for in-flight tasks started on the old wire.
The API server mounts the StreamableHTTP MCP handler at POST/GET/DELETE /mcp
when a registry is provided; serve.go constructs one Registry shared by the
runners (mint) and the server (resolve). Minting is skipped for gemini agents.
Tests: writeMCPConfig output shape, buildInnerCmd flag presence/absence, and an
api-level end-to-end MCP tool call through NewServer/Handler proving the route
is mounted (and absent without a registry).
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
|
|
Adds RunnersConfig{Claude,Gemini,Local,Container *bool} to Config,
parsed from a [runners] TOML section. Each field uses the *bool pointer
pattern (nil = enabled by default, false = disabled) so existing installs
require no config changes.
serve.go / run.go now gate each runner registration on the corresponding
Enabled() method. The pool's runners map remains the authoritative
routing table — absent entries are already skipped by pickAgent and
fail-fast in getRunner, so no executor changes are needed.
Example:
[runners]
gemini = false # disable cloud gemini runner
local = true # explicit (same as default)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
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>
|
|
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
|
|
Phase 2 of "local OSS models as agents" plan. Adds a third elaboration
path that calls the local OpenAI-compatible LLM via the internal/llm
client, and reorders dispatch so the cheap path is tried first:
local → claude → gemini, with each next attempt only on hard failure
of the prior.
Wiring is opt-out, not opt-in: when [local_model].endpoint is set,
elaboration prefers local by default. Users with a slow or low-quality
local model can disable just elaboration via:
[local_model]
endpoint = "..."
prefer_for_elaborate = false
without giving up the runner or the classifier path.
Implementation:
- Server gains an optional *llm.Client field via SetLLM (matches the
existing SetNotifier/SetWorkspaceRoot setter pattern, no NewServer
signature break).
- elaborateWithLocal() reuses buildElaboratePrompt verbatim and asks
for response_format=json_object so we skip markdown-fence cleanup.
- handleElaborateTask reorders try chain; existing Claude-first
behavior is preserved exactly when SetLLM is not called.
- LocalModel.UseForElaborate() encapsulates the default-true gating
with a *bool so explicit-false survives TOML parse.
Tests:
- elaborateWithLocal: parses valid response, errors on nil client,
errors on bad JSON.
- handler: local preferred when wired; falls back to claude when
local fails; unchanged behavior when no LLM is configured.
- config: UseForElaborate gating across empty/default/explicit-true/
explicit-false cases.
Pre-existing test failures noted in docs/plans/local-oss-runner.md
(post-epic cleanup): TestGeminiLogs_ParsedCorrectly returns 404 for
gemini execution log fetch — predates this change.
Plan: docs/plans/local-oss-runner.md.
https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J
|
|
Phase 1 of "local OSS models as agents" plan. Adds a third Runner
backed by any OpenAI-compatible HTTP server (Ollama, vLLM, LM Studio,
llama.cpp), and migrates the Gemini-CLI classifier to route through
the same client when configured.
Two-layer split: internal/llm.Client is the workhorse (HTTP, no Pool,
no DB) used directly by the classifier and any future internal helper
that needs cheap reasoning. internal/executor.LocalRunner is a thin
adapter implementing Runner for user-facing tasks. This avoids
Pool reentrancy/deadlock when sub-second internal calls fire from
inside Pool.execute().
Highlights:
- internal/retry: relocated runWithBackoff/IsRateLimitError/ParseRetryAfter
into a shared package reused by executor and llm.
- internal/llm: Chat (non-streaming) and ChatStream (SSE) over
/chat/completions with optional bearer auth, json_object response
format, retry on 429/503, Retry-After parsing.
- internal/executor/LocalRunner: streams deltas into stdout.log in the
same stream-json envelope ClaudeRunner emits, then writes one
consolidated assistant block plus a result terminator so existing
parsers (extractSummary, ParseChangestatFromOutput) work unchanged.
- internal/executor/Classifier: gains optional LLM field; uses
json_object response format (no markdown-fence cleanup needed).
Falls back to Gemini-CLI subprocess when LLM is nil.
- Pool.skipClassification: now skips only when the requested agent
type is registered, so unknown types still reach the load balancer.
- Storage: additive tokens_in/tokens_out ALTERs on executions; CLI
runners record cost_usd as before, LocalRunner records 0 + tokens.
- Config: [local_model] section (endpoint, model, timeout_seconds,
default_temperature, api_key). Empty endpoint = no LocalRunner
registered, classifier falls back to Gemini.
Pre-existing test issues fixed in passing:
- claude_test.go setupSandbox callsites updated to current signature.
- gemini_test.go TestParseGeminiStream skipped (asserts unimplemented
GeminiRunner stream-error parsing; tracked separately).
Plan: docs/plans/local-oss-runner.md.
https://claude.ai/code/session_017Edeq947TpSm1vQTxMhi1J
|
|
Fix 1 (server.go): Replace context.Background() with s.ctx in
handleAnswerQuestion, handleResumeTimedOutTask, and handleRunTask.
Add a ctx field to Server (defaulting to context.Background()) and
a SetContext method so the serve command can wire in the signal-
cancellable lifecycle context.
Fix 2 (serve.go): Call srv.SetContext(ctx) before StartHub so all
pool submissions use the server's root context (already cancelled
on SIGTERM/SIGINT). Pool.Shutdown and its wiring were already present.
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>
|
|
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>
|
|
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>
|
|
The server runs as www-data whose HOME is /var/www — deriving
credentials from $HOME/.claude always produced an empty path.
Now reads from ClaudeConfigDir (default: /workspace/claudomator/credentials/claude),
which sync-credentials keeps populated with fresh OAuth tokens.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- ContainerRunner replaces ClaudeRunner/GeminiRunner; all agent types run
in Docker containers via claudomator-agent:latest
- Writable agentHome staging dir (/home/agent) satisfies home-dir
requirements for both claude and gemini CLIs without exposing host creds
- Copy .credentials.json and .claude.json into staging dir at run time;
GEMINI_API_KEY passed via env file
- Fix git clone: remove MkdirTemp-created dir before cloning (git rejects
pre-existing dirs even when empty)
- Replace localhost with host.docker.internal in APIURL so container can
reach host API; add --add-host=host.docker.internal:host-gateway
- Run container as --user=$(uid):$(gid) so host-owned workspace files are
readable; chmod workspace 0755 and instructions file 0644 after clone
- Pre-create .gemini/ in staging dir to avoid atomic-rename ENOENT on first
gemini-cli run
- Add ct CLI tool to container image: pre-built Bash wrapper for
Claudomator API (ct task submit/create/run/wait/status/list)
- Document ct tool in CLAUDE.md agent instructions section
- Add drain-failed-tasks script: retries failed tasks on a 5-minute interval
- Update Dockerfile: Node 22 via NodeSource, Go 1.24, gemini-cli,
git safe.directory=*, default ~/.claude.json
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.
|
|
This commit implements the architectural shift from local directory-based
sandboxing to containerized execution using canonical repository URLs.
Key changes:
- Data Model: Added RepositoryURL and ContainerImage to task/agent configs.
- Storage: Updated SQLite schema and queries to handle new fields.
- Executor: Implemented ContainerRunner using Docker/Podman for isolation.
- API/UI: Overhauled task creation to use Repository URLs and Image selection.
- Webhook: Updated GitHub webhook to derive Repository URLs automatically.
- Docs: Updated ADR-005 with risk feedback and added ADR-006 to document the
new containerized model.
- Defaults: Updated serve command to use ContainerRunner for all agents.
This fixes systemic task failures caused by build dependency and permission
issues on the host system.
|
|
The DB may contain keys generated before the swap fix, with the private
key stored as the public key. Add ValidateVAPIDPublicKey() and use it in
serve.go to detect and regenerate invalid stored keys on startup.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
The service runs as www-data which cannot write to the root-owned
config file. VAPID keys are now stored in the settings table in
SQLite (which is writable), loaded on startup, and generated once.
Removes saveVAPIDToConfig and the stale warning on every restart.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Web Push:
- WebPushNotifier with VAPID auth; urgency mapped to event type
(BLOCKED=urgent, FAILED=high, COMPLETED=low)
- Auto-generates VAPID keys on first serve, persists to config file
- push_subscriptions table in SQLite (upsert by endpoint)
- GET /api/push/vapid-key, POST/DELETE /api/push/subscribe endpoints
- Service worker (sw.js) handles push events and notification clicks
- Notification bell button in web UI; subscribes on click
File Drop:
- GET /api/drops, GET /api/drops/{filename}, POST /api/drops
- Persistent ~/.claudomator/drops/ directory
- CLAUDOMATOR_DROP_DIR env var passed to agent subprocesses
- Drops tab (📁) in web UI with file listing and download links
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Adds POST /api/webhooks/github that receives check_run and workflow_run
events and creates a Claudomator task to investigate and fix the failure.
- Config: new webhook_secret and [[projects]] fields in config.toml
- HMAC-SHA256 validation when webhook_secret is configured
- Ignores non-failure events (success, skipped, etc.) with 204
- Matches repo name to configured project dirs (case-insensitive)
- Falls back to single project when no name match found
- 11 new tests covering all acceptance criteria
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>
|
|
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>
|
|
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>
|
|
- Add workspaceRoot field (default "/workspace") to Server struct
- Add SetWorkspaceRoot method on Server
- Update handleListWorkspaces to use s.workspaceRoot
- Add WorkspaceRoot field to Config with default "/workspace"
- Wire cfg.WorkspaceRoot into server in serve.go
- Expose --workspace-root flag on the serve command
- Add TestListWorkspaces_UsesConfiguredRoot integration test
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.
|
|
Restore the script registry in internal/cli/serve.go which was lost
during the gemini merge. This fixes the 'Start Next Task' button in the
web UI which relies on the /api/scripts/start-next-task endpoint.
|
|
- 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.
|
|
- Add Classifier using gemini-2.0-flash-lite to automatically select agent/model.
- Update Pool to track per-agent active tasks and rate limit status.
- Enable classification for all tasks (top-level and subtasks).
- Refine SystemStatus to be dynamic across all supported agents.
- Add unit tests for the classifier and updated pool logic.
- Minor UI improvements for project selection and 'Start Next' action.
|
|
- Extract newLogger() to remove duplication across run/serve/start
- Add defaultServerURL const ("http://localhost:8484") used by all client commands
- Move http.Client into internal/cli/http.go with 30s timeout
- Add 'report' command for printing execution summaries
- Add test coverage for create and serve commands
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
|
|
Adds `claudomator start <task-id>` to queue a task via the running API
server. Adds internal/version for embedding VCS commit hash in the
server banner.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
- POST /api/tasks/elaborate: calls claude to draft a task config from
a natural-language prompt
- GET /api/executions/{id}/logs/stream: SSE tail of stdout.log
- CRUD /api/templates: create/list/get/update/delete reusable task configs
- GET /api/tasks/{id}/subtasks: list child tasks
- Server.NewServer accepts claudeBinPath for elaborate; injectable
elaborateCmdPath and logStore for test isolation
- Valid-transition guard added to POST /api/tasks/{id}/run
- CLI passes claude binary path through to the server
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
|
Claudomator automation toolkit for Claude Code with:
- Task model with YAML parsing, validation, state machine (49 tests, 0 races)
- SQLite storage for tasks and executions
- Executor pool with bounded concurrency, timeout, cancellation
- REST API + WebSocket for mobile PWA integration
- Webhook/multi-notifier system
- CLI: init, run, serve, list, status commands
- Console, JSON, HTML reporters with cost tracking
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
