Fixes from the first live session of the new loop
Found live on 2026-10-07 (bring-up on nisse-testing-operator/nisse-bringup,
Opus as driver):
- The driver's prose nudge went into the system prompt, so the retry ended
on the model's own reply. Opus 5.5 refuses that ("does not support
assistant message prefill. The conversation must end with a user
message"). The nudge is now a harness fact in the conversation. The
delegation harness's prose path did the same and is fixed likewise.
- A helper's first request ended with its own delegation_started event,
rendered as an assistant message: every delegation would have failed on
Opus. The helper now sees it as the harness handing over its task.
- model_contract checks that every request ends on the user's side, so
scripted tests catch this from now on (each fix is mutation-checked).
- `status` (and `details`) in an item's thread were taken as replies: they
woke the driver and cancelled a bug's countdown. They now answer at once
and change nothing.
- The driver had no way to answer a remark without changing the item, so it
answered in prose. Every run woken by a message (or a review comment) now
offers `reply`, which answers where asked and returns to the very wait
that was interrupted.
Also: scripts/bringup-repo.sh makes the bring-up's test repository
(make_repo/delete_repo, split out of fresh_repo), and made repositories get
the agent's labels (bug, discuss, design).
Tests: test_loop_live_fixes.py (one per finding); the walk sends `status`
into threads (status_changes_nothing) and its scripted driver sometimes
answers remarks with reply.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
1 parent
572bd9f8eb
commit
659915d309
9 files changed
+341
-42
No files matched your search
@@ -33,6 +33,7 @@ from nisse_dev.canonical import (
|
||||
AssistantText,
|
||||
DelegationCompleted,
|
||||
DelegationStarted,
|
||||
Fact,
|
||||
PlanSubmitted,
|
||||
StoredEvent,
|
||||
ToolCall,
|
||||
@@ -414,6 +415,15 @@ class Delegation:
|
||||
# and its tree state is unknown. Treat it as a failure rather
|
||||
# than inventing a handback on its behalf.
|
||||
if any(isinstance(e, AssistantText) for e in produced):
|
||||
# Said something but did nothing: told so, as the
|
||||
# harness, so the next request ends on the user's side
|
||||
# (models refuse assistant prefill).
|
||||
transcript.as_actor("orchestrator").append(
|
||||
Fact(
|
||||
text="Your last reply was prose. Use your tools to "
|
||||
"do the work, then call hand_back."
|
||||
)
|
||||
)
|
||||
continue
|
||||
return DelegationResult(
|
||||
"failed",
|
||||
|
||||
Reference in new issue
Block a user