Pass the PAT only via github-token param. continue-on-error on the
budget step so a missing/expired secret degrades gracefully instead
of failing the whole workflow.
Agent-Session: cowork-reviewer-ab-20260414
- Per-model timeout of 60s so one hung model does not block siblings
- Simplify cost_cents math (cost_usd * 100 directly, no double-rounding)
Defer: fine-grained PAT for CTO_ADMIN_TOKEN (requires manual OAuth device flow).
Agent-Session: cowork-reviewer-ab-20260414
Default GITHUB_TOKEN cannot mutate Repository Variables (always 403).
Use a PAT-backed secret CTO_ADMIN_TOKEN for the budget counter steps.
Also restores formal APPROVE/REQUEST_CHANGES verdicts now that repo
setting can_approve_pull_request_reviews is enabled.
Agent-Session: cowork-reviewer-ab-20260414
Two enhancements to the PR reviewer:
1. Monthly spend cap: tracked in Repo Variables (CTO_REVIEW_MONTH,
CTO_REVIEW_SPEND_CENTS, CTO_REVIEW_CAP_CENTS). Default cap $10/month.
Auto-resets on month rollover. Posts a skip-comment on PRs when cap hit.
2. A/B harness: reviews every PR with 3 models in parallel
(Claude Haiku 4.5, DeepSeek V3.1, Kimi K2 Thinking). Comment shows
all 3 verdicts side-by-side so we can compare quality/cost on real
PRs before picking a permanent default. Drop to 1 model by editing
the MODELS list after A/B window closes.
Agent-Session: cowork-reviewer-ab-20260414
GITHUB_TOKEN cannot formally approve PRs without a repo setting toggle.
Verdict is still prominent in the first line of the review body, and
the human merges based on reading it — no behavior loss.
Agent-Session: cowork-reviewer-fix-20260414
* ci: add main-push audit tripwire
Flags direct pushes to main that did not come from a merged PR.
Free-plan workaround since branch protection requires GitHub Pro.
* docs: add Git Workflow section to CONVENTIONS.md
Documents the PR-gated review process enforced at the agent layer.
Free-plan workaround since branch protection requires GitHub Pro.
* ci: add Claude-powered CTO PR review workflow
Auto-reviews every PR with Claude Haiku 4.5 and posts a structured
review (APPROVE / REQUEST_CHANGES / COMMENT). Does NOT auto-merge — a
human still clicks Merge. Requires ANTHROPIC_API_KEY secret on the repo.
* ci: switch CTO reviewer from Anthropic direct to OpenRouter
Reuses the OPENROUTER_API_KEY secret that already backs the other AI
plugins. Consolidates AI spend on one bill. Model: anthropic/claude-haiku-4.5.
Adds [peptide_directory] shortcode with card grid, category taxonomy (8 terms),
search, pagination, detail modal, and /v1/compounds REST endpoint. Includes 9
new meta fields (half-life, stability, solubility, etc.), admin data tools for
migration/re-enrichment, integration hooks for cross-plugin extensibility,
dark mode support, and full uninstall cleanup. Refactors AI generator into
PSA_OpenRouter + PSA_KB_Builder classes. Adds PHPUnit tests for PostType and
Directory classes. Fixes QA findings: dead JS selector, renderError loading
state, numeric meta validation, prepared SQL in uninstall.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Create PSA_Cost_Tracker class with database table for API call logging
- Log prompt/completion tokens and estimated cost for every OpenRouter API call
- Implement monthly budget system with hard stop (budget of 0 = unlimited)
- Add budget checks in validate_peptide_name() and generate_peptide_content()
- Add dry_run() method to estimate costs before making API calls
- Display monthly usage summary and recent API logs in admin settings
- Add monthly_budget setting to admin interface with number input field
- Update uninstall.php to drop psa_api_logs table on plugin removal
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
