30 commits

Author	SHA1	Message	Date
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	6a6d2d0774	fix: docs: per-agent AGENTS.md files still describe cron triggers (#547)	2026-04-10 08:35:19 +00:00
Agent	ac1b49767d	fix: architect: jq integer/string type mismatch in has_open_subissues self-exclusion filter (#499)	2026-04-09 15:11:50 +00:00
Agent	a72ab8b121	fix: architect: has_responses_to_process not set when open_arch_prs < 3 (#498)	2026-04-09 14:57:24 +00:00
Claude	6971371e27	chore: gardener housekeeping 2026-04-09	2026-04-09 14:24:52 +00:00
Agent	8eaad3a998	fix: address AI review feedback - JSON injection, exit on failure, branch collisions (#490)	2026-04-09 11:04:30 +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	03a119d16c	fix: review feedback — use global vars for multiline guidance, update PR body for answer detection ... - fetch_pr_review_decision now sets REVIEW_DECISION/REVIEW_GUIDANCE globals instead of printf to stdout (multiline guidance broke cut-based parsing) - ACCEPT handler instructs model to update PR body with Design forks section so fetch_pr_answers can detect the answers phase on subsequent runs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 10:27:53 +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	03962dd1d2	fix: fix: architect-run.sh should check preconditions in bash before invoking the model (#472) ... Add bash precondition checks to skip model invocation when: - No vision issues exist AND no open architect PRs to handle - Already at max 3 open architect PRs AND no ACCEPT/REJECT responses to process This avoids $0.28+ empty runs where the model reads context and concludes 'no work'. The model is only invoked when there's actual work: new pitches or response processing.	2026-04-09 06:26:08 +00:00
Claude	7c688bc196	chore: gardener housekeeping 2026-04-09	2026-04-09 06:02:34 +00:00
Claude	faaaeb0a1f	chore: gardener housekeeping 2026-04-09	2026-04-09 00:05:31 +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
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	887bc7bbea	chore: gardener housekeeping 2026-04-08	2026-04-08 18:02:36 +00:00
Claude	fe1ef3d5ef	chore: gardener housekeeping 2026-04-08	2026-04-08 12:22:13 +00:00
Agent	d653680d64	fix: fix: standardize logging across all agents — capture errors, log exit codes, consistent format (#367)	2026-04-07 21:15:36 +00:00
Claude	514de48f58	chore: gardener housekeeping 2026-04-07	2026-04-07 18:05:41 +00:00
Claude	6d0eaf2687	chore: gardener housekeeping 2026-04-07	2026-04-07 12:04:45 +00:00
Claude	4aa824c203	chore: gardener housekeeping 2026-04-07	2026-04-07 06:01:36 +00:00
Claude	b7bba15037	chore: gardener housekeeping 2026-04-07	2026-04-07 00:05:33 +00:00
Claude	b21408e668	chore: gardener housekeeping 2026-04-06	2026-04-06 18:06:28 +00:00
Claude	b1695d8329	chore: gardener housekeeping 2026-04-06	2026-04-06 12:05:35 +00:00
Agent	e7b11b22da	fix: fix: duplicated memory guard — memory_guard() in env.sh vs check_memory() in formula-session.sh (#279) ... Remove check_memory() from lib/formula-session.sh and update all *-run.sh scripts to use memory_guard() from lib/env.sh. Changes: - lib/formula-session.sh: Removed check_memory() function and its documentation - gardener/gardener-run.sh: Replaced check_memory(2000) with memory_guard(2000) - planner/planner-run.sh: Replaced check_memory(2000) with memory_guard(2000) - architect/architect-run.sh: Replaced check_memory(2000) with memory_guard(2000) - predictor/predictor-run.sh: Replaced check_memory(2000) with memory_guard(2000) - supervisor/supervisor-run.sh: Replaced check_memory(2000) with memory_guard(2000) Benefits: - Only one memory check function exists now - All agents use the same function - No dependency on free command - uses /proc/meminfo which is more portable	2026-04-06 09:40:36 +00:00
Agent	0098695644	fix: fix: cron agents (gardener, planner, architect, predictor) never set FORGE_REMOTE (#278)	2026-04-06 09:26:18 +00:00
Agent	38050bc2c3	fix: fix: architect-run.sh missing .profile integration — no lessons, no journal (#222)	2026-04-05 15:17:15 +00:00
Agent	171b9d2ae3	fix: feat(96b): architect formula — research + design fork identification (#100)	2026-04-01 10:22:54 +00:00
Agent	2afb010c20	refactor: simplify architect script to reduce duplicate detection findings	2026-04-01 10:03:54 +00:00
Agent	564e2e774d	fix: feat(96a): architect-bot user + directory + run script scaffold (#99)	2026-04-01 09:53:47 +00:00