112 commits

Author	SHA1	Message	Date
Claude	99d430a0c2	fix: bug: architect has no path for approved PRs awaiting initial design questions (#570) ... Implementation: - Added detect_approved_pending_questions() function to identify approved PRs that have no ## Design forks section and no Q1:, Q2: comments yet. - Modified response processing block to handle three session modes: 1. questions_phase: Resume session for processing Q&A answers 2. start_questions: Fresh session to post initial design questions 3. pitch: Original behavior for new pitch generation - Added build_architect_prompt_for_mode() function to generate appropriate prompts for each session mode. - When an approved PR is detected, the agent posts initial design questions (Q1:, Q2:, etc.) and adds the ## Design forks section, transitioning the PR into the existing questions phase. This fixes the issue where approved architect PRs would sit indefinitely because the agent had no path to start the design conversation.	2026-04-10 11:30:46 +00:00
Claude	f0c3c773ff	fix: tech-debt: sweep cron-isms from code comments, helpers, lib, and public site copy (#548) ... - Rename acquire_cron_lock → acquire_run_lock in lib/formula-session.sh and all five *-run.sh call sites - Update all *-run.sh file headers: "Cron wrapper" → "Polling-loop wrapper" - Rewrite docs/updating-factory.md: replace crontab check with pgrep, replace "Crontab empty after restart" section with polling-loop equivalent - Update docs/EVAL-MCP-SERVER.md to reflect polling-loop reality - Update lib/guard.sh, lib/AGENTS.md, lib/ci-setup.sh comments - Update formulas/*.toml comments (cron → polling loop) - Update dev/dev-poll.sh usage comment - Update tests/smoke-init.sh to handle compose vs bare-metal scheduling - Update .woodpecker/agent-smoke.sh comments - Update site HTML: architecture.html, quickstart.html, index.html - Clarify _install_cron_impl is bare-metal only (compose uses polling loop) - Keep site/collect-engagement.sh and site/collect-metrics.sh cron refs (genuinely cron-driven on the website host, separate from factory loop) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-10 08:54:11 +00:00
Claude	f299bae77b	fix: bug: supervisor hardcodes ops repo expectation — fails silently on deployments without one (#544) ... Add OPS repo presence detection in supervisor-run.sh with degraded mode support: - Detect if OPS_REPO_ROOT is missing and log WARNING message - Set OPS_REPO_DEGRADED=1 flag and configure fallback paths - Bundle minimal knowledge files as fallback for degraded mode - Update formula to use OPS_KNOWLEDGE_ROOT, OPS_JOURNAL_ROOT, OPS_VAULT_ROOT - Support local vault destination and journal fallback when ops repo absent Knowledge files bundled: disk.md, memory.md, ci.md, git.md, dev-agent.md, review-agent.md, forge.md The supervisor now runs with full functionality when ops repo is available, or gracefully degrades to local paths when absent, making the failure mode explicit rather than silent.	2026-04-10 08:16:03 +00:00
Claude	48c97a9b09	fix: bug: supervisor P1 disk auto-fix uses docker system prune -f — too weak for real disk pressure (#539) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-10 07:29:01 +00:00
Claude	fbf1a6dcc2	fix: review feedback — cd path in release.sh, compose file access in edge container ... - formulas/release.sh: cd to $FACTORY_ROOT (not parent) for docker compose build - docker-compose.yml: mount docker-compose.yml into edge container, pass HOST_PROJECT_DIR - dispatcher.sh: use -f and --project-directory so compose resolves volume paths against the host filesystem when invoked from inside the edge container Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 19:23:08 +00:00
Claude	3c8b61168d	fix: eliminate duplicate action-TOML parsing between runner entrypoint and release formula ... Runner entrypoint now exports VAULT_ACTION_TOML for formula scripts, avoiding duplicated argument parsing that triggered CI duplicate detection. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 19:07:51 +00:00
Claude	77de5ef4c5	fix: bug: dispatcher runner invokes formulas as bash scripts but formulas are TOML (#516) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 19:02:52 +00:00
Agent	b11c4cca15	fix: refactor: architect pitching should be bash-driven with stateless model calls (#490)	2026-04-09 10:49:35 +00:00
Claude	e31a2d5c88	fix: refactor: architect design phase should be bash-driven with stateful session resumption (#491) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 10:15:17 +00:00
Agent	1426b1710f	fix: fix: architect creates duplicate sprint pitch for vision issues that already have sub-issues (#486)	2026-04-09 08:59:43 +00:00
Agent	045df63d07	fix: fix: review formula misses cross-cutting consequences and under-files tech-debt (#483)	2026-04-09 08:01:29 +00:00
Claude	87a0036baa	fix: fix: agents-update step uses vague instructions and disinto-specific examples — rewrite with mechanical discovery (#476) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 07:45:26 +00:00
Claude	655c383046	fix: architect should read review body text as human guidance when processing ACCEPT/REJECT (#469) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 06:15:09 +00:00
Claude	63bfed949e	fix: feat: architect should pitch up to 3 sprints per run when multiple vision issues exist (#451) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 21:21:00 +00:00
Claude	3a9b42bca3	fix: architect should label filed sub-issues as backlog and mark vision issue as in-progress (#441) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 20:21:26 +00:00
Agent	25433eaf67	fix: fix: architect should resume session when processing answers on an accepted sprint PR (#436) ... When the architect processes human answers to design questions (answer_parsing step), it now resumes the session from the research/questions run instead of starting fresh. This preserves Claude's deep codebase understanding from the research phase, ensuring sub-issues include specific file references and implementation details. Changes: - architect-run.sh: Added detect_questions_phase() to check if PR is in questions phase (has `## Design forks` section and question comments). If so, resume the session from SID_FILE to preserve context. - formulas/run-architect.toml: Documented session resumption behavior in answer_parsing step. Session is only preserved when PR is in questions-awaiting-answers phase. Fresh sessions are started for new pitches (no stale context from old sprints).	2026-04-08 19:37:36 +00:00
Claude	0d78dae5a8	fix: vault TOML template must match vault-env.sh schema ... Add required fields (id, formula, secrets), remove unknown fields (unblocks, focus, [execution] section). Move focus and unblocks info into context string and comments respectively. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 19:21:11 +00:00
Claude	29f3d451c7	fix: fix: predictor should dispatch actions through vault, not by filing action-labeled issues (#434) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 19:15:19 +00:00
dev-bot	6e9bb5348c	Merge pull request 'fix: fix: architect should detect Forgejo PR review approvals, not just ACCEPT comments (#432)' (#435) from fix/issue-432 into main	2026-04-08 19:13:10 +00:00
Claude	81b89259c3	fix: architect should detect Forgejo PR review approvals, not just ACCEPT comments (#432) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 19:02:55 +00:00
Agent	0c68421e6f	fix: fix: architect creates sprint PR with raw JSON body instead of formatted markdown (#431)	2026-04-08 18:54:40 +00:00
Agent	083c734390	fix: feat: reproduce agent re-verifies bug-report issues after all dependency fixes merge (#400)	2026-04-08 07:55:17 +00:00
Claude	9d7139afe3	fix: use jq for JSON-safe manifest writes in bug-report lifecycle step (#398) ... Avoid raw shell interpolation of multiline SUB_ISSUES into JSONL — titles with quotes/backslashes would produce invalid JSON. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 07:02:05 +00:00
Claude	4af309721e	fix: feat: gardener should auto-close original bug reports when all sub-issue fixes merge (#398) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-08 06:46:00 +00:00
Agent	19dd7e61f4	fix: fix: triage entrypoint overwrites original issue labels even when root cause was found (#387)	2026-04-07 22:03:25 +00:00
Agent	9a22e407a4	fix: fix: triage agent creates root cause issues without backlog label (#386)	2026-04-07 21:52:44 +00:00
dev-qwen	9c199cdd6f	Merge pull request 'fix: fix: supervisor code cleanup — LOG_FILE, dead files, stale tmux references (#343)' (#348) from fix/issue-343 into main	2026-04-07 09:08:29 +00:00
Agent	e6ac67811a	fix: fix: supervisor code cleanup — LOG_FILE, dead files, stale tmux references (#343)	2026-04-07 09:02:21 +00:00
Claude	ae826f935b	fix: add auth headers to curl commands and stack_lock field (#342) ... - Add Authorization header to read-findings curl calls (private Forgejo) - Add Authorization + Content-Type headers to decompose curl call - Add stack_lock placeholder to [project] extension section Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-07 08:57:39 +00:00
Claude	da70badb6d	fix: feat: triage formula template with generic investigation steps and best practices (#342) ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-07 08:51:38 +00:00
Claude	5189b70dd3	fix: feat: triage agent — deep root cause analysis for reproduced bugs (#258) ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-07 08:06:40 +00:00
Agent	3606d66a51	fix: fix: reproduce-agent formula — primary goal is reproduction, not root cause (#320)	2026-04-06 21:01:35 +00:00
Claude	5b1a3b2091	fix: feat: gardener should enrich bug-report issues with context, reproduction plan, and verification checklist (#285) ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-06 10:35:01 +00:00
Claude	300f335179	fix: feat: extend edge container with Playwright and docker compose for bug reproduction (#256) ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-06 07:45:14 +00:00
Claude	bd7a4d6d03	fix: feat: gardener should label issues as bug-report when they describe user-facing bugs with repro steps (#252) ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-05 20:10:18 +00:00
Agent	2b4c8be245	fix: remove hardcoded 'johba' references — use dynamic project config instead (#241)	2026-04-05 17:18:04 +00:00
Agent	7eacb27c62	fix: refactor: simplify gardener formula — remove AD check, portfolio, blocked-review, stale-PR (#127)	2026-04-01 19:36:04 +00:00
Agent	a7ad6eb32a	fix: feat: versioned releases — vault-gated tag, image build, and deploy (#112)	2026-04-01 14:03:49 +00:00
Agent	d315c79866	fix: correct Forgejo API references for merge and comments	2026-04-01 11:08:37 +00:00
Agent	3aca03a06b	fix: feat(96d): architect formula — answer parsing + sub-issue filing (#102)	2026-04-01 10:57:26 +00:00
Agent	7134752525	fix: feat(96c): architect formula — sprint PR creation with questions (#101)	2026-04-01 10:50:06 +00:00
Agent	171b9d2ae3	fix: feat(96b): architect formula — research + design fork identification (#100)	2026-04-01 10:22:54 +00:00
Agent	564e2e774d	fix: feat(96a): architect-bot user + directory + run script scaffold (#99)	2026-04-01 09:53:47 +00:00
Agent	ee99f185e6	fix: feat: generic journal aspect — post-session reflection + lessons-learned context injection (#97)	2026-04-01 09:28:49 +00:00
Agent	2d72e0e565	fix: refactor: tighten planner issue filing — template-or-vision gate (#95)	2026-04-01 08:57:14 +00:00
Agent	963d745bde	fix: feat(20a): disinto hire-an-agent subcommand + retrofit dev-qwen (#84)	2026-04-01 07:43:16 +00:00
Agent	aad21dc084	fix: chore: tear down old vault scripts — prepare for PR-based vault (#73)	2026-03-31 20:38:05 +00:00
Agent	d9a6030127	fix: remove remaining action-agent references from docs and configs ... - Remove action-agent card from site/docs/architecture.html - Remove action/ directory line from architecture.html - Update formula comments to reference dispatcher instead of action-agent - Remove action/action.log from log scan loops in preflight.sh and collect-metrics.sh - Remove action from find command in agent-smoke.sh	2026-03-31 19:55:00 +00:00
Agent	4bcd2c275b	fix: refactor: rename vault-runner → runner and vault-run → run (#43)	2026-03-29 12:43:18 +00:00
Claude	aa73ff88c4	fix: remove PROMPT.md files — formulas are the source of truth (#12) ... - Delete gardener/PROMPT.md (dust-vs-ore rules already in run-gardener.toml) - Delete supervisor/PROMPT.md (content covered by run-supervisor.toml; migrate unique "Learning" section into formula's journal step) - Delete vault/PROMPT.md and create formulas/run-vault.toml as the source-of-truth formula for vault action classification/routing - Update supervisor/supervisor-poll.sh to read from formula instead of PROMPT.md - Update vault/vault-agent.sh to read from formula instead of PROMPT.md - Update supervisor/AGENTS.md, vault/AGENTS.md, README.md references Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-03-28 16:40:21 +00:00