Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(reasoning): unify reasoning extraction across providers

Browse Source 
Reasoning surfacing was split across three branches in runner.py plus
two separate streaming buffers (loop hook and runner progress stream),
with three independent display-side gates in the CLI. This collapsed
the policy into one source of truth and fixed two real bugs:

- Structured `reasoning_content` was suppressed whenever the answer was
  streamed, because the runner gated emission on `streamed_content`.
  Providers don't stream `reasoning_content`; it only arrives on the
  final response, so the answer stream and the reasoning channel are
  independent. Added `streamed_reasoning` to `AgentHookContext` to track
  the right bit.
- `channels.showReasoning` was subordinated to `sendProgress`. They are
  orthogonal — turning off progress streaming shouldn't silence
  reasoning. Reworked the CLI gates accordingly.

Single-helper consolidation:

- `extract_reasoning(reasoning_content, thinking_blocks, content)`
  returns `(reasoning_text, cleaned_content)` with a defined fallback
  order: dedicated field → Anthropic thinking_blocks → inline
  `<think>`/`<thought>` tags. Models that expose none of these
  short-circuit to `(None, content)` — zero overhead.
- `IncrementalThinkExtractor` replaces the ad-hoc `emit_incremental_think`
  function and its hand-rolled "emitted cursor" state in both the loop
  hook and the runner progress stream.

Also documented the new `showReasoning` channel option in
docs/configuration.md and noted its independence from sendProgress.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Xubin Ren
2026-05-12 17:14:19 +00:00
co-authored by Cursor
parent 3a851f8f8d
commit 352aaf0627
9 changed files with 281 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/configuration.md
+1
View File
@@ -677,6 +677,7 @@ Global settings that apply to all channels. Configure under the `channels` secti
|---------|---------|-------------|
| `sendProgress` | `true` | Stream agent's text progress to the channel |
| `sendToolHints` | `false` | Stream tool-call hints (e.g. `read_file("…")`) |
| `showReasoning` | `false` | Surface model reasoning/thinking content (DeepSeek-R1 `reasoning_content`, Anthropic `thinking_blocks`, inline `<think>` tags). Independent of `sendProgress`. |
| `sendMaxRetries` | `3` | Max delivery attempts per outbound message, including the initial send (0-10 configured, minimum 1 actual attempt) |
| `transcriptionProvider` | `"groq"` | Voice transcription backend: `"groq"` (free tier, default) or `"openai"`. API key is auto-resolved from the matching provider config. |
| `transcriptionLanguage` | `null` | Optional ISO-639-1 language hint for audio transcription, e.g. `"en"`, `"ko"`, `"ja"`. |