claudomator.git, branch main

docs: fix workflow diagram — create_story does not auto-spawn a builder task

2026-07-11T09:52:47+00:00

The StoryOrchestrator skips stories with no root_task_id (if st.RootTaskID == "") so create_story / POST /api/stories do not trigger Builder spawning on the next tick as the diagram incorrectly claimed. Corrected the flowchart node, the entry-point table rows, and added an explanatory note on the story lifecycle kickoff flow. Co-Authored-By: Claude Sonnet 4.6

fix(executor): validate the model classifier's output against a known model list

2026-07-11T09:37:31+00:00

The Gemini-based Classifier trusted its LLM output verbatim. Twice in production it echoed part of its own prompt's JSON schema literally -- 'model-name' (the prompt's own placeholder, also fixed here to be less echo-prone) and separately 'choose-the-best-model' -- instead of substituting a real model identifier. Both were syntactically valid JSON strings that passed straight through to the claude CLI's --model flag, which rejected them and failed the task outright. validateClassification now rejects anything outside the known model list, which Classify's existing error handling already treats as 'classification failed' and falls back to no explicit model override -- the same documented fallback path, now also covering 'succeeded but returned garbage.'

fix(scheduler): retry role-typed FAILED tasks even with no active role_configs

2026-07-11T08:33:10+00:00

Before this, a role with no seeded role_configs (every role except builder/planner) got no retry safety net at all: processTask returned immediately on GetActiveRoleConfig's error, leaving a task FAILED forever after a single transient infra blip. retryWithoutLadder mirrors escalateAskUserTimeout's existing 'no active role config -- still resuming, just without a provider/model change' fallback, bounded by maxRetriesNoRoleConfig (2) before declining final=true. Same treatment now applies to a decoded role config with an empty EscalationLadder.

docs: fix workflow diagram — webhook and spawn_subtask don't auto-submit to pool

2026-07-11T07:46:30+00:00

- GitHub webhook (createCIFailureTask) only calls store.CreateTask with PENDING state; it never calls Pool.Submit. Previous diagram said "creates task + auto-runs" which was wrong. - spawn_subtask (both role= and no-role= variants) only calls store.CreateTask with PENDING state via storeChannel.SpawnSubtask. The pool is not called. Previous diagram labelled this "Pool.Submit() for new child/sibling" which was wrong. - Both spawn_subtask variants always set parent_task_id. The "sibling with depends_on" description for the role= case was misleading. - propose_epic and propose_role_config are storage-only writes with no connection to the pool at all. Previous diagram drew arrows from these to executor.Pool; removed and replaced with a STORAGE node. - Added explicit note that PENDING children need a separate /run call (scripts/start-next-task, StoryOrchestrator.spawnRoleTask, or manual). - StoryOrchestrator's spawnRoleTask correctly creates + QUEUED + Pool.Submit in one step; that path remains accurate. Co-Authored-By: Claude Sonnet 4.6

fix(scheduler): make arbitration fail-closed on a missing verdict, seed planner's system prompt

2026-07-11T05:38:25+00:00

A live production run (2026-07-11) showed finalizeArbitration's 'no verdict reported = approve' default silently shipping work an evaluator had already flagged as factually wrong -- the arbitration agent never called report_verdict because the planner role had no system prompt telling it to. finalizeArbitration now treats a missing verdict the same as an explicit rejection (fail-closed), and SeedRoleConfigs now also seeds planner with a prompt that explicitly mandates calling report_verdict before finishing.

docs: add workflow and entry points diagram

2026-07-11T01:19:24+00:00

Covers all entry points verified against current code: - REST API (POST /api/tasks + /run), chatbot MCP (submit_task, create_story, accept_story), GitHub webhook, Story REST API, agent spawn_subtask (parent_task_id vs depends_on/role paths), propose_epic, propose_role_config, StoryOrchestrator's internal spawning (ensureEvaluators/ensureArbitration/ensureFixAttempt/ spawnNestedFixAttempt/processRetro), Scheduler retry/escalation and ask_user-timeout escalation, claudomator run CLI. Includes task state machine diagram and recursive arbitrated-review cycle showing that builder-role READY means awaiting arbitration, not done. All diagrams use Mermaid (renders on GitHub). Co-Authored-By: Claude Sonnet 4.6

docs: rewrite CLAUDE.md's Story orchestrator section to describe the finished recursive arbitrated-review design

2026-07-10T22:19:37+00:00

The old text described pre-piece-4a behavior (root auto-accepted eagerly) and a since-closed Design Debt item (arbitration claimed to never parse a verdict, when ReportVerdict/KindVerdictReported already existed). Rewritten to describe the actual current mechanism: builder-role nodes at any depth only reach COMPLETED via finalizeArbitration's approval, the tree-walk trigger, task.CurrentAttempt resolution, root-vs-nested fix-attempt plumbing, and SeedRoleConfigs seeding the builder role's prompt.

fix(executor): periodically sweep stale dispatch workspace directories

2026-07-10T22:13:49+00:00

ContainerRunner preserves a failed execution's workspace indefinitely for debugging, with no expiry -- this accumulated 161 stale directories (~17.6GB) and took the host to 100% disk full on 2026-07-10. Pool.RunWorkspaceCleanup sweeps claudomator-workspace-* dirs older than 24h every hour, started from serve.go, mirroring StoryOrchestrator.Run's ticker shape. Never removes a directory still referenced as a currently-BLOCKED task's sandbox_dir, regardless of age.

feat(storage): seed the builder role's system prompt on server startup

2026-07-10T20:22:30+00:00

docs: rewrite piece 5 plan as a code-based SeedRoleConfigs (mirrors SeedProjects) instead of a manual API call

2026-07-10T20:17:33+00:00