3a118e5df0
The existing intent-signal re-prompt fires only when tools are armed and the response is short. Models often stop mid-plan in other shapes too: a trailing "Let me clone the repo.", a "Let me ...:" header followed by a numbered list, or a bare trailing colon. When this happens the turn ends with the structured workload only partially delivered. Add a neutral "Continue." nudge that runs alongside the tool-coercive re-prompt: - _TRAILING_PLAN_INTENT, _TRAILING_PLAN_LIST, _TRAILING_PLAN_COLON cover the three observed shapes, scanned over the last 600 chars. - _trailing_plan_hit() returns True if any of them match. - _MAX_CONTINUES (3) is independent of _MAX_REPROMPTS so the two paths cannot starve each other. - _continue_count threads through the agentic loop; auto-continue fires with "Continue." regardless of tool armament. Regex tested against the patterns above plus negative controls (complete sentences, benign "let me" earlier in the buffer) before landing. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _html_to_md.py | ||
| anthropic_compat.py | ||
| audio_codecs.py | ||
| defaults.py | ||
| external_provider.py | ||
| inference.py | ||
| key_exchange.py | ||
| llama_cpp.py | ||
| llama_server_args.py | ||
| mlx_inference.py | ||
| orchestrator.py | ||
| providers.py | ||
| tools.py | ||
| worker.py | ||