jeffusion/archived-gitea-ai-assistant
1
0
Fork 0
mirror of https://github.com/jeffusion/gitea-ai-assistant.git synced 2026-06-07 07:26:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
127 Commits 4 Branches 8 Tags
main
Commit Graph

8 Commits

Author SHA1 Message Date
jeffusion
a9c70ab292 chore(docs): remove internal design docs, add CONTRIBUTING.md 
- Remove docs/design/ directory (notification-service-refactoring,
  pluggable-llm-providers, ui-theme-language) — these are internal
  architecture/refactoring documents that should not be in public
  documentation navigation per project convention
- Extract UI theme conventions from ui-theme-language.md into
  CONTRIBUTING.md as contributor guidelines
- Remove Architecture & design section from docs/README.md and
  docs/README.zh-CN.md index pages
- Update README.md link from Architecture docs to Documentation index
 2026-05-27 10:37:28 +08:00
jeffusion
1e38a0e5e0 refactor: replace fixed review workflow with dynamic agent framework 
- Add agent-kernel runtime (MainAgentRunner with while-true state machine,
  subagent spawning, tool loop, budget control)
- Add review-agent entrypoint with read_file/search_code/spawn_subagent tools
- Add deterministic publish adapter with cross-specialist finding dedup
- Delete old fixed workflow (orchestrator, triage, specialist, judge agents,
  4 domain agents, critic/debate/reflexion agents, learning/memory system)
- Remove legacy ModelRole (planner/specialist/judge) from LLM types, gateway,
  config schema, DB, and frontend RoleAssignment UI
- Replace RoleAssignment with AgentModelSettings for role-based model config
- Add agent config API endpoints (GET/PUT /admin/api/agents/config)
- Add review session detail page with observability/findings/logs tabs
- Add runtime contract tests and review adapter integration tests
- Add E2E mock LLM with scripted behavior support for deterministic testing
- Update E2E test script with subagent and finding assertions
- Add e2e/README.md with real PR review testing guide
- Fix seed.sh to run gitea admin commands as git user (not root)
- Update docs (configuration, review-engines, deployment, README)
- Remove unused feedback controller, qdrant k8s manifest, embedding migration
- Add .omo/ and .opencode/ to .gitignore
 2026-05-27 07:34:59 +08:00
jeffusion
9567501369 chore(deploy): standardize assistant default port to 5174 2026-03-24 13:40:06 +08:00
jeffusion
e40daddf0d feat(notification): replace feishu-only flow with pluggable providers 2026-03-24 13:40:06 +08:00
jeffusion
28d86aff16 fix(ui): align card headers and stabilize themed layout polish 2026-03-24 12:30:13 +08:00
jeffusion
1c0c9afd17 feat(review): remove legacy mode and harden agent/codex pipeline 
Drop legacy runtime paths and role assignments across backend/frontend, and add upgrade-safe DB migration for existing installs. This aligns config, docs, tests, and UI to the agent-first architecture with codex as the only alternate engine.
 2026-03-24 12:30:13 +08:00
jeffusion
0bc147cbc5 refactor: replace master.key file with ENCRYPTION_KEY env var and fix k8s deployment 
- Replace file-based master key (data/master.key) with ENCRYPTION_KEY env var (hex-encoded)
- App now requires ENCRYPTION_KEY to start, removing MASTER_KEY_PATH entirely
- Fix k8s: add missing gitea-assistant-data volume, replace PVC with hostPath for single-node
- Fix k8s: change qdrant from StatefulSet+PVC to Deployment+hostPath
- Add K8s Secret for ENCRYPTION_KEY injection
- Update all tests, .env.example, and documentation
 2026-03-24 12:30:13 +08:00
jeffusion
efc2753e45 docs(design): add pluggable LLM providers design document 
Comprehensive 838-line design specification covering architecture,
provider types, database schema, API endpoints, encryption strategy,
frontend wireframes, and migration plan for the pluggable multi-provider
LLM system.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
 2026-03-24 12:30:13 +08:00