Adam Moussa
e7ef4387e6
Two root causes behind 'every task parks, and slowly':
1. SINGLE-SHOT INVOKER: subscription Claude calls ran as 40-turn, tool-enabled
agentic sessions (--max-turns 40, $2 budget) for what are pure reasoning->JSON
completions — minutes-long, and Claude wandered/returned unparseable output.
_DEFAULT_MAX_TURNS 40->1 + allowed_tools=[] -> fast deterministic single turn.
2. PLANNER FEEDBACK KEY MISMATCH: the review stage writes verdict/findings, but
_format_review_feedback read decision/notes/comment (never present) -> the
planner re-planned with EMPTY feedback, re-introduced the rejected flaw
('assumptions persist'), hit the review cap, parked. Now reads verdict/findings
(old keys kept as fallback) so GPT-4.1's objections reach the re-plan.
Plus: park notifications infer the phase the task was IN (review/plan/clarify)
instead of the terminal 'parked'.
Tests: planner real-verdict-keys regression + coordinator phase-inference. 1149 pass.
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| build_verify_subgraph.py | ||
| builders.py | ||
| builders_llm.py | ||
| clarifier.py | ||
| clarifier_llm.py | ||
| dispatch_invoker.py | ||
| fixer.py | ||
| handbook.py | ||
| planner.py | ||
| review_loop.py | ||
| review_loop_llm.py | ||
| verifier.py | ||
| verifier_llm.py | ||