docs(wiki): clarify examples are snapshots + remove remaining colibri#143 refs #274
2 changed files with 9 additions and 8 deletions
|
|
@ -56,7 +56,7 @@ are NOT yet validated — the API key was a placeholder (DeepSeek returned 401
|
|||
before reaching the agent loop). A re-run with a valid DEEPSEEK_API_KEY is
|
||||
needed to capture a real tool call before the driver can trust those mappings.
|
||||
|
||||
Step 1 of colibri#143 is complete after the real-key re-run below. Steps 2 and 3 are unblocked.
|
||||
Step 1 of the RPC driver implementation is complete after the real-key re-run below. Steps 2 and 3 are unblocked.
|
||||
|
||||
## Real-key transcript (complete tool call, 2026-06-21)
|
||||
|
||||
|
|
@ -117,7 +117,7 @@ Full 61-line transcript is stored on OSA, outside the repository.
|
|||
|
||||
**None.** All 15 real-key event types have valid, non-duplicate mappings.
|
||||
|
||||
**Resolved (colibri#143):** `tool_call` was previously mapped to
|
||||
**Resolved:** `tool_call` was previously mapped to
|
||||
`tool_execution_start` (same as `tool_use_start`), causing a double-fire.
|
||||
The standalone `tool_call` event is now skipped — it returns `None` from the
|
||||
normalizer. `tool_use_start` is the sole entry point for tool execution start.
|
||||
|
|
@ -132,7 +132,7 @@ normalizer. `tool_use_start` is the sole entry point for tool execution start.
|
|||
- `tool_result` carries `is_error` boolean
|
||||
- `usage` carries `cache_read`, `cache_write`, `cost_usd`, `cumulative`
|
||||
|
||||
Step 1 of colibri#143 is complete — wire format and all 15 event types are
|
||||
The wire format work is complete — format and all 15 event types are
|
||||
validated against real output. The `tool_call` double-fire gap is resolved by
|
||||
skipping the duplicate standalone event in Glasspane.
|
||||
|
||||
|
|
|
|||
|
|
@ -279,12 +279,13 @@ git push
|
|||
|
||||
## Examples from Our Project
|
||||
|
||||
**Recent PRs in colibri:**
|
||||
These are illustrative snapshots — the actual branch list changes daily.
|
||||
For the current state, run `git log --oneline -20` on `main`.
|
||||
|
||||
- `feat/eval-harness-phase1` - Added evaluation harness (732 lines changed)
|
||||
- `refactor/rename-golden-to-fixtures` - Renamed golden tests to fixtures (10 files)
|
||||
- `fix/socket-fmt-drift` - Fixed cargo fmt drift in daemon socket code
|
||||
- `feat/dynamic-agent-capabilities` - Auto-detected ollama/blender via probe
|
||||
- `feat/eval-harness-phase1` — Added evaluation harness (732 lines changed)
|
||||
- `refactor/rename-golden-to-fixtures` — Renamed golden tests to fixtures (10 files)
|
||||
- `fix/socket-fmt-drift` — Fixed cargo fmt drift in daemon socket code
|
||||
- `feat/dynamic-agent-capabilities` — Auto-detected ollama/blender via probe
|
||||
|
||||
These all followed the pattern: branch → commit → push → PR → review → merge → cleanup.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue