pragent

gitea_admin/pragent

Fork 0

Commit Graph

Author	SHA1	Message	Date
claude	99014a4cd3	chore(gitignore): exclude .worktrees/	2026-08-21 23:39:44 +00:00
Marcos	6f012e9b66	feat(pilot): minimal AI review bot for Gitea Actions Ships a working pragent pilot ahead of the framework build (design doc deferred). Single stdlib-only reviewer script fetched at runtime by a per-repo Gitea Action; reviews fire only on PRs with the AI-REVIEW label; model is glm-5.2:cloud via the on-network headroom proxy; fail-open. - pilot/ai_review.py: fetch PR diff, call model, post review as pragent-bot - pilot/workflow-template.yml: per-repo Gitea Action gated on AI-REVIEW label - pilot/README.md: onboarding (bot collaborator + secret + workflow + label) - tests/pilot/test_ai_review.py: 15 unit tests for pure helpers (no network) - README/design doc: note pilot is the bootstrap; framework build deferred Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-17 18:18:06 +00:00
Marcos	1c0c576e40	docs: initial pragent design and README Extensible PR review framework: CLI-in-CI delivery, pi SDK agent loop, deterministic-plus-LLM tiering, committed repo profile, JSONL/OTel analytics. Design doc records the decisions, cost model, and rollout phases. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011Ye1KNFMkkUtmzTypHXkoK	2026-08-04 16:35:35 +00:00

Author

SHA1

Message

Date

claude

99014a4cd3

chore(gitignore): exclude .worktrees/

2026-08-21 23:39:44 +00:00

Marcos

6f012e9b66

feat(pilot): minimal AI review bot for Gitea Actions

Ships a working pragent pilot ahead of the framework build (design doc
deferred). Single stdlib-only reviewer script fetched at runtime by a per-repo
Gitea Action; reviews fire only on PRs with the AI-REVIEW label; model is
glm-5.2:cloud via the on-network headroom proxy; fail-open.

- pilot/ai_review.py: fetch PR diff, call model, post review as pragent-bot
- pilot/workflow-template.yml: per-repo Gitea Action gated on AI-REVIEW label
- pilot/README.md: onboarding (bot collaborator + secret + workflow + label)
- tests/pilot/test_ai_review.py: 15 unit tests for pure helpers (no network)
- README/design doc: note pilot is the bootstrap; framework build deferred

Co-Authored-By: Claude <noreply@anthropic.com>

2026-08-17 18:18:06 +00:00

Marcos

1c0c576e40

docs: initial pragent design and README

Extensible PR review framework: CLI-in-CI delivery, pi SDK agent loop,
deterministic-plus-LLM tiering, committed repo profile, JSONL/OTel analytics.
Design doc records the decisions, cost model, and rollout phases.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011Ye1KNFMkkUtmzTypHXkoK

2026-08-04 16:35:35 +00:00

3 Commits