claudomator.git/internal/executor/preamble.go, branch fix/dockersandbox-gitpush-host-security

feat(executor): MCP-oriented planning preamble, applied by ContainerRunner (Phase 2)

2026-05-24T17:38:53+00:00

Rewrites the planning preamble to point the agent at the four MCP tools (ask_user/report_summary/spawn_subtask/record_progress) instead of the CLAUDOMATOR_QUESTION_FILE / CLAUDOMATOR_SUMMARY_FILE conventions: ask_user ends the turn, report_summary replaces the summary file, spawn_subtask replaces the POST-to-/api/tasks planning step. Git discipline is retained. ContainerRunner previously applied no preamble at all; it now prepends this preamble (via buildAgentInstructions) when the MCP back-channel is active and skip_planning is false, so the in-container agent is actually guided to use the tools. Gemini agents (no MCP) are unaffected. https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39

fix: hide deployment badge when not deployed and trim notification button label

2026-03-16T21:30:36+00:00

- Deployment badge now returns null (hidden) when includes_fix is false instead of showing "Not deployed" noise - Badge also suppressed when fix_commits is empty (no tracked commits to check) - Notification button label trimmed to just the bell emoji - Preamble: warn agents not to use absolute paths in git commands (sandbox bypass) Co-Authored-By: Claude Sonnet 4.6

feat: fix task failures via sandbox improvements and display commits in Web UI

2026-03-15T03:39:49+00:00

- Fix ephemeral sandbox deletion issue by passing $CLAUDOMATOR_PROJECT_DIR to agents and using it for subtask project_dir. - Implement sandbox autocommit in teardown to prevent task failures from uncommitted work. - Track git commits created during executions and persist them in the DB. - Display git commits and changestats badges in the Web UI execution history. - Add badge counts to Web UI tabs for Interrupted, Ready, and Running states. - Improve scripts/next-task to handle QUEUED tasks and configurable DB path.

fix: cancel blocked tasks + auto-complete completion reports

2026-03-14T00:33:46+00:00

Two fixes for BLOCKED task issues: 1. Allow BLOCKED → CANCELLED state transition so users can cancel tasks stuck waiting for input. Adds Cancel button to BLOCKED task cards in the UI alongside the question/answer controls. 2. Detect when agents write completion reports to $CLAUDOMATOR_QUESTION_FILE instead of real questions. If the question JSON has no options and no "?" in the text, treat it as a summary (stored on the execution) and fall through to normal completion + sandbox teardown rather than blocking. Also tightened the preamble to make the distinction explicit. Co-Authored-By: Claude Sonnet 4.6

merge: resolve conflicts with local/master (stats tab + summary styles)

2026-03-13T03:17:04+00:00

Keep file-based summary approach (CLAUDOMATOR_SUMMARY_FILE) from HEAD. Combine Q&A History and Stats tab CSS from both branches. Co-Authored-By: Claude Sonnet 4.6

feat: resume support, summary extraction, and task state improvements

2026-03-13T03:14:40+00:00

- Extend Resume to CANCELLED, FAILED, and BUDGET_EXCEEDED tasks - Add summary extraction from agent stdout stream-json output - Fix storage: persist stdout/stderr/artifact_dir paths in UpdateExecution - Clear question_json on ResetTaskForRetry - Resume BLOCKED tasks in preserved sandbox so Claude finds its session - Add planning preamble: CLAUDOMATOR_SUMMARY_FILE env var + summary step - Update ADR-002 with new state transitions - UI style improvements Co-Authored-By: Claude Sonnet 4.6

feat: require agents to write a final summary before exiting

2026-03-11T11:01:21+00:00

Add a mandatory '## Final Summary' section to planningPreamble instructing agents to output a 2-5 sentence summary paragraph (headed by '## Summary') as their last output before exiting. Adds three tests to verify the section and its required content are present in the preamble. Co-Authored-By: Claude Sonnet 4.6

executor: add git discipline section to agent preamble

2026-03-08T22:11:05+00:00

Agents running in a sandbox must commit all changes before exiting. The teardown rejects any dirty working tree. Add an explicit section to the planning preamble making this requirement clear. Co-Authored-By: Claude Sonnet 4.6

refactor(executor): update runners and tests for generic agents

2026-03-08T06:33:02+00:00

agent: lower breakdown threshold to 3min; use claudomator create CLI for subtasks

2026-03-07T08:30:13+00:00

Replaces the API POST instructions with the claudomator create command, which is simpler and consistent with how operators queue tasks. --start is explicitly omitted so subtasks are queued but not auto-started. Co-Authored-By: Claude Sonnet 4.6