gitea_admin/pragent
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity
16 Commits 7 Branches 0 Tags
76b6752f48b9e77899f046c48f2b58727c1bced8
Commit Graph

3 Commits

Author SHA1 Message Date
Marcos 76b6752f48 fix(review): language-tagged suggestion fence for Gitea syntax highlighting 
Gitea 1.26.x has no GitHub-style 'Apply suggestion' button — a ```suggestion
fence is just an unknown-language code block, so chroma does not highlight it
and there is no apply control. Switch inline_comment_body to wrap the suggested
fix in a fence tagged with the file's language (new _lang_for_path helper,
.java→java, .ts→typescript, .py→python, ...), so Gitea syntax-highlights the
code. No capability lost (there was never an apply button on this Gitea
version). Correct the docstrings/skills/README that wrongly claimed an
apply-button was rendered.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-08-18 01:26:37 +00:00
Marcos 8912f6721b deploy: combined opencode image + k8s + docs 
- pilot/Dockerfile: python:3.12-slim + node 20 + opencode-ai@1.3.10 +
  ripgrep + pyright/typescript-language-server/eslint (npm) + ruff (pip).
  Factory + pilot scripts baked at /app. imagePullPolicy: Never (local
  import into microk8s containerd).
- .dockerignore: lean build context.
- ~/k8s/pragent-webhook.yaml: image pragent-webhook:opencode, emptyDir work
  at /tmp/pragent-work, env (PRAGENT_ENGINE, OPENCODE_MODEL, PRAGENT_FACTORY_DIR,
  PRAGENT_OPENCODE_BIN, PRAGENT_WORK_ROOT, PRAGENT_RTK_DIR='', timeout 540),
  resources 200m/512Mi -> 1500m/2Gi. Drops the ConfigMap scripts volume.
- pilot/README-webhook.md + .opencode/README.md: opencode engine section,
  build/import/apply steps, factory guide fixes (parse_review_output, steps).

Image builds (1.62GB, smoke-tested: opencode+LSPs+factory+env all present).
Import into microk8s containerd + apply pending (ctr needs sudo).

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-08-17 23:11:58 +00:00
Marcos 6e3a9eb5b0 feat: opencode review engine + .opencode factory 
Replace the single Python model-call reviewer with an opencode agent
factory. A primary 'pragent' agent reads a brief (title/body/diff/config/
prior reviews), inspects the checked-out repo, runs the repo's own linters
via bash, loads review-methodology + findings-schema skills, and emits a
{summary, findings} JSON with per-finding severity/path/line/problem/fix/
suggestion/reference. Dormant security/tests/perf subagent lenses fan out
only on large/risky diffs (lean by default).

pilot/opencode_review.py: fetches the repo archive at the head sha into a
temp workdir, writes .pragent/brief.md, drops the factory, runs
'opencode run --pure --agent pragent --dir <workdir>' headlessly. Isolates
HOME (shared, warmed), strips ANTHROPIC_* env (leaked host vars caused
ProviderModelNotFoundError), stdin=DEVNULL (opencode blocks on stdin),
maps the bare OLLAMA_MODEL to the provider-prefixed ref. No Gitea I/O —
ai_review.review_pr parses + anchors + posts (reuses all v2 logic/tests).

PRAGENT_ENGINE=opencode (default) selects it; =ollama keeps the legacy
direct-call path. Verified end-to-end: posts a real review with a summary
section, inline [CRITICAL]/[HIGH] comments + apply-able suggestions +
reference links, and the sha dedupe marker. 49 tests pass.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-08-17 23:01:59 +00:00