feat(turn): halt a turn stuck repeating one identical tool call
Ports grok-build's action stationarity breaker. A polling loop looks like progress from inside the turn — every step succeeds — so nothing stops it and it burns the whole budget re-reading one file. Nudge at 8 identical batches, halt at 16, halt a pure no-op run at 4. Three defects were found and fixed before this landed, none of which the gates caught: - The check runs AFTER execute_tool_calls, not before. Before it, the assistant's tool_calls are recorded with no results, so pushing the nudge triggers repair_dangling_tool_calls: synthetic "cancelled by the user" results get spliced in, the real results land after a user message, and dedup misses them — the orphan tool_result shape that draws a provider 400. It is Ok-gated too, since one `?` inside can leave a call resultless. - `TurnOutcome::StationarityHalted` is its own variant grouped with Completed, not a reuse of Cancelled. As a cancellation it would report StopReason::Cancelled, fire the abort lifecycle, kill the turn's subagents, grow the goal harness back-off streak until three halts paused a running goal, and let completion-requirement recovery re-run the very turn halted for looping. - The no-op gate is size-based, not name-based. kigi registers the shell tool as `run_terminal_cmd` and renames it `run_terminal_command`, so matching on "bash" silently disabled the tighter ceiling while every test still passed.
This commit is contained in:
1 parent
a07d889ad9
commit
ac23ebc9a1
8 files changed
+429
-5
No files matched your search
@@ -121,6 +121,8 @@ mod model_switch;
|
||||
mod prompt_queue;
|
||||
#[path = "acp_session_impl/slash_exec.rs"]
|
||||
mod slash_exec;
|
||||
#[path = "acp_session_impl/stationarity_seam.rs"]
|
||||
mod stationarity_seam;
|
||||
#[path = "acp_session_impl/swarm.rs"]
|
||||
mod swarm;
|
||||
use super::PromptOrigin;
|
||||
|
||||
Reference in new issue
Block a user