* docs: add gutchapa-opencode-telegram to projects
* chore: fill in kind, topics and compat for data/projects/gutchapa-opencode-telegram.yaml
---------
Co-authored-by: gutchapa <[email protected]>
Pin reusable workflow to a440b485d779b9177b1602c4d4f7f58cff0483a2 (main). Drop unknown with: inputs (llm_url/llm_model/use_anthropic not in workflow_call schema). Adopt pull_request_target + standard comment gates, guarded concurrency, minimal permissions, secrets: inherit.
Co-authored-by: John Smith <[email protected]>
Output of the OpenCode backlog review loop (scripts/review/run-review-loop.py):
per-item verdicts for 463 PRs plus issues (review_results.json and
review_state.json), the running summary table, and the issue #15 report.
Co-authored-by: John Smith <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
A fresh runner has no `opencode auth` store and the API key prompt needs
a TTY, so the run failed with provider.no-route. Write a CI-only config
mapping opencode-go/opencode to their secret env vars (with the read-only
permission rules repeated as a second layer), and surface OpenCode error
events in run and selftest output.
Co-authored-by: John Smith <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
* feat: advisory AI review of needs-human and scout PRs with OpenCode V2
A scheduled workflow runs `opencode run` (V2, pinned and checksummed)
with a read-only catalog-reviewer agent over evidence bundles for open
PRs labeled needs-human or scout and for unreviewed scout candidates.
PRs get one verdict comment and an ai-* label; confident scout accepts
get a bot PR. It never merges or closes.
The model runs in a job with no GitHub token; the agent may only read,
glob and grep inside the repository (a self-test proves it before each
run); verdicts are schema-validated and rendered by our own code.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
* fix(ai-review): address CodeQL and SonarCloud security findings
Enforce HTTPS on the OpenCode download, run opencode by absolute path,
escape summary cells with escapeCell, rely on HTML escaping instead of
comment-stripping regexes, validate item IDs before routing API calls,
and bound verdict parsing on runaway output.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
---------
Co-authored-by: John Smith <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
* docs: add Agent Relay plugin
* docs: use public desktop releases
* docs: update Agent Relay for OpenCode V2
* chore: bring the entry up to the current catalog schema
README.md and dist/registry.json are generated from data/ now.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EHYZtiXaVB71TSBhHnynk4
---------
Co-authored-by: khaliqgant <[email protected]>
Co-authored-by: John Smith <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
* docs: add openrouter-websearch to plugins
* chore: fill in kind, topics and compat for data/plugins/openrouter-websearch.yaml
---------
Co-authored-by: pichenka007gd <[email protected]>
* docs: add OpenCode Model Router to plugins
* docs: state OpenCode v2.x requirement in model router listing
* chore: fill in kind, topics and compat for data/plugins/opencode-model-router.yaml
---------
Co-authored-by: sertdisk <[email protected]>
Co-authored-by: sertdisk <[email protected]>
* docs: add open-memex to plugins
* chore: fill in kind, topics and compat for data/plugins/open-memex.yaml
---------
Co-authored-by: stone <[email protected]>
* docs: add opencode-kevin to plugins
* chore: fill in kind, topics and compat for data/plugins/opencode-kevin.yaml
---------
Co-authored-by: jmtrinchan <[email protected]>
* docs: add opencode-autopilot-logbook to plugins
Auto-generates daily logbooks on session idle with secret masking,
throttle window and file-based daily limit. Repo https://github.com/smapira/opencode-autopilot-logbook is public and maintained (1.1.1 published to npm).
* docs: rewrite description
* chore: fill in kind, topics and compat for data/plugins/opencode-autopilot-logbook.yaml
---------
Co-authored-by: smapira <[email protected]>
* docs: add opencode-prewalk to plugins
* chore: fill in kind, topics and compat for data/plugins/opencode-prewalk.yaml
---------
Co-authored-by: vivekascoder <[email protected]>
* docs: add async-prompt-injector to plugins
* chore: fill in kind, topics and compat for data/plugins/async-prompt-injector.yaml
---------
Co-authored-by: Nik <[email protected]>
* docs: add aerovato-operator-memory to plugins
* chore: fill in kind, topics and compat for data/plugins/aerovato-operator-memory.yaml
---------
Co-authored-by: kevinMEH <[email protected]>
* docs: add opencode-cursor to plugins
* chore: fill in kind, topics and compat for data/plugins/opencode-cursor.yaml
---------
Co-authored-by: ephraimduncan <[email protected]>
* docs: add ai-project-tracker to plugins
* chore: fill in kind, topics and compat for data/plugins/ai-project-tracker.yaml
---------
Co-authored-by: Mehr Deepseek <[email protected]>
* docs: add Cursor Provider to plugins
* chore: fill in kind, topics and compat for data/plugins/cursor-opencode-provider.yaml
---------
Co-authored-by: o.akimov <[email protected]>
github-actions[bot]