Commit graph

10 commits

Author SHA1 Message Date
acc5a9e7bb ship: fix 7 review findings from Ganymede + Rhea
- auto-deploy.sh: fail hard on checkout error (was silent || true),
  show syntax check errors (was 2>/dev/null), add flock concurrency
  guard, quote rsync excludes, fix agent-state path, add telegram/
  rsync target, add smoke test failure comment
- prune-branches.sh: only delete merged branches (is-ancestor check),
  show delete errors (was 2>/dev/null)
- deploy.sh: show syntax check errors, add telegram/ rsync target
- evaluate-trigger.sh: remove stale ^diagnostics/ pattern
- AGENT-SOP.md: add stderr suppression rule, config.py constants rule

Pentagon-Agent: Ship <1A6F9A42-AC52-4027-B8C5-3CB5FA3F7C28>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 16:14:52 +01:00
dbf9b07c62 ops: add deploy manifest, remove dead code, clean tracked artifacts
- Add deploy manifest template (ops/deploy-manifest.md) — required checklist
  for all PRs touching VPS-deployed code
- Remove agents/logos/ — stale directory from Logos→Theseus rename
- Remove logos/* branch prefix from evaluate-trigger.sh domain routing
- Remove 298 .extraction-debug JSON files from version control
- Update .gitignore: add .extraction-debug/ and __pycache__ patterns

Pentagon-Agent: Theseus <24DE7DA0-E4D5-4023-B1A2-3F736AFF4EEE>
2026-03-28 21:21:26 +00:00
b5927c55d5 theseus: add Ganymede pre-merge code review gate to evaluate trigger
- What: PRs touching code files (ops/, diagnostics/, .py, .sh, etc.) now
  get Ganymede code review in addition to Leo + domain agent
- Why: Ganymede was reviewing ~30% of code PRs after deploy, not before.
  This makes code review 100% pre-merge, matching how Leo already gates claims.
- How: detect_code_pr() checks file patterns, runs Ganymede with code-focused
  prompt, adds VERDICT:GANYMEDE gate to merge eligibility check

Pentagon-Agent: Theseus <24DE7DA0-E4D5-4023-B1A2-3F736AFF4EEE>
2026-03-28 21:01:34 +00:00
Leo
75f1709110 leo: add ingest skill — full X-to-claims pipeline (#103)
Some checks are pending
Sync Graph Data to teleo-app / sync (push) Waiting to run
2026-03-10 10:42:25 +00:00
876a01a4da leo: fix evaluate-trigger.sh — 4 bugs + auto-merge support
- Add foundations/ to always-allowed territory paths so domain agents can propose foundation claims
- Add Astra/space-development to domain routing map
- Fix double check_merge_eligible call by capturing exit code
- Update Leo prompt from 8 to 11 quality criteria (scope, universals, counter-evidence)
- Add auto-merge capability with territory violation checks
- Add --no-merge flag for review-only mode
- Widen domain agent verdict parsing to catch various comment formats

Pentagon-Agent: Leo <B9E87C91-8D2A-42C0-AA43-4874B1A67642>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 19:01:42 +00:00
ad5513ab96 Auto: ops/evaluate-trigger.sh | 1 file changed, 3 insertions(+), 2 deletions(-) 2026-03-07 17:59:11 +00:00
d1fa42bfc5 Fix agent naming: Theseus (not Logos) throughout
Cory confirmed the AI alignment agent is Theseus. Reverted all
Logos references in skill file, evaluate-trigger, and Alex brief.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:42:40 +00:00
4be64979a0 Add contributor skill file and 2-agent evaluation trigger
- .claude/skills/contribute/SKILL.md: installable skill for any Claude Code
  to contribute to Teleo Codex. Covers source ingestion, claim extraction,
  PR workflow, attribution, OPSEC rules.

- ops/evaluate-trigger.sh: upgraded to 2-agent review per PR:
  1. Leo (opus) — quality gates, cross-domain, coherence
  2. Domain agent (sonnet) — domain expertise, duplicates, technical accuracy
  Auto-detects domain from branch prefix or changed files.
  New flags: --leo-only, --dry-run shows detected agents.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:39:39 +00:00
05ed5203f1 Add contributor docs, Alex onboarding brief, and evaluate-trigger script
- CONTRIBUTING.md: step-by-step guide for external contributors
- docs/ALEX_BRIEF.md: onboarding brief for Alex — AI alignment domain
- ops/evaluate-trigger.sh: headless Leo evaluation trigger (Ganymede reviewed)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:22:25 +00:00
24fd456a09 Auto: 35 files | 35 files changed, 10533 insertions(+) 2026-03-07 15:10:14 +00:00