Brief P4: enforce the thinking cap through reasoning_control

Approved 2026-09-17. Evidence is in docs/decisions.md. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 00:38:32 -07:00
parent 59666e0130
commit 367573b11e
2 changed files with 5 additions and 2 deletions
@@ -104,7 +104,10 @@ ordinary outbound networking can reach the whole tailnet and the internet as the
   processing produces events. The timeout is "no bytes for N seconds", never a total-request
   deadline. Progress events count as bytes.
 8. **Runaway control.** Per-turn thinking-token cap, per-turn tool-iteration cap, detection of
-   repeated identical tool calls.
+   repeated identical tool calls. `loopd` enforces the thinking cap: it counts streamed reasoning
+   tokens and ends the block with the server's `reasoning_control` mechanism
+   (`POST /v1/chat/completions/control`, action `reasoning_end`). M2 exercises this on straylight
+   before relying on it.
 9. **Startup self-test.** On boot `loopd` checks: tool-call round trip parses, turn-2 prompt
   processing count shows a cache hit, configured context matches what the server reports.
   It refuses to start if any check fails.