2 Commits

Include renames

Author	SHA1	Message	Date
Omar Sobh	f6c3ddbf81	refactor: no feature depends on Gemini any more ... Depleted Gemini prepayment credits took out PDF rendering. The same key was the only thing standing between level-up proposals and the same fate, so both are off it. - `pdf_renderer` is DELETED, not disabled. Nothing sets `render_pdf: true` since markdown became the deliverable (821cbb8), so the worker polled forever for rows that can no longer exist. It was also the only caller of the Gemini MD->HTML conversion. A worker that cannot do anything is worse than absent: it reads as a feature. - `level_up` now resolves its proposer through the provider REGISTRY (`Runtime::resolve_provider`), the same path the evaluator uses, defaulting to `glm:glm-4.7` — the validator this project measured and chose in scripts/judge-eval.sh. `CLAWMATES_LEVEL_UP_MODEL` takes a registry spec (`glm:glm-4.7`, `kimi:k2`, `claude-sonnet-5`), so every provider the platform can already reach works and no single vendor's billing can take it down. The non-obvious part of that swap: Gemini was asked for `response_mime_type: application/json` and obliged, so the old code parsed the raw reply. Anthropic-format models are under no such obligation and wrap objects in prose or a ```json fence. `extract_json_object` brace-counts to the matching close — string-aware, so a `}` inside a value does not end it, and nested (these proposals nest by design). Tested against bare, fenced, nested, brace-in-string and absent. Parsing raw text would have worked in review and failed on the first real proposal. What deliberately still MENTIONS Gemini: `mission_runtime` forwards GEMINI_API_KEY to agent containers alongside GROQ/OPENAI/ZAI/KIMI, and the claw model selector offers it. Those are user options, not platform requirements — the ask was to remove the NEED. Also corrected a comment in mission_delivery that cited `pdf_renderer` as the authority on artifact path resolution. It never was: it joined the mission id first and produced a doubled path that never resolved. 238 lib tests, 20 test binaries.	2026-08-07 13:01:57 -07:00
Omar SobhandClaude Opus 4.7	9b5e63cbb7	slice 8.5: per-agent + per-team level-up endpoints ... Level-up analyzes an agent's brain + recent run outcomes (or a whole team's aggregate state), calls Gemini 2.5 Flash for structured JSON proposals, and persists them as pending level_up_proposals rows. Reviewer approves a subset via /apply; the applier commits only those items. Migration 0052 adds level_up_proposals (id, workspace_id, agent_id XOR team_id via CHECK constraint, status, payload JSONB, applied_items[], model, created_by, approved_by, created_at, applied_at) + workspace/pending/agent/team indexes. Rust surface: - cm_db::repo::level_up::{insert, get, list_pending, mark_applied, mark_rejected} - cm_api::level_up::{propose_agent, propose_team, apply} Item kinds handled by apply(): identity_refinement → UPDATE agents.system_prompt skill_add → agent_skills_ext INSERT skill_candidate → workspace-scoped skills INSERT (deterministic id per (workspace, name)) brain_consolidation → set_agent_md on the brain (unlike brain_seed::ingest, this overwrites) roster_change / mcp_bundle_change — logged as "not auto-applied, human runs team-wizard" (structural changes need human review of side effects). API: - POST /api/claws/{id}/level-up → { proposal_id } - POST /api/teams/{id}/level-up → { proposal_id } - GET /api/level-up-proposals → pending list - GET /api/level-up-proposals/{id} - POST /api/level-up-proposals/{id}/apply { approved_item_ids } - POST /api/level-up-proposals/{id}/reject Uses Gemini 2.5 Flash with response_mime_type: "application/json" so the model returns structured JSON directly (no ```json fence stripping needed). Configurable via CLAWMATES_LEVEL_UP_MODEL. Follow-ups: - Frontend diff-review UI (pick items, approve/reject) - roster_change / mcp_bundle_change appliers (currently manual) - Anthropic + OpenAI proposer variants - Promote workspace-scoped skills to builtin via a curator flow Co-Authored-By: Claude Opus 4.7 <[email protected]>	2026-07-19 16:36:29 -07:00