claudomator.git/internal/executor/classifier.go, branch story/task-project-fk

executor: explicit load balancing — code picks agent, classifier picks model

2026-03-10T16:48:15+00:00

pickAgent() deterministically selects the agent with the fewest active tasks, skipping rate-limited agents. The classifier now only selects the model for the pre-assigned agent, so Gemini gets tasks from the start rather than only as a fallback when Claude's quota is exhausted. Co-Authored-By: Claude Sonnet 4.6

executor: strengthen rate-limit avoidance in classifier

2026-03-09T05:50:59+00:00

Updated isQuotaExhausted to detect more Claude quota messages. Added 'rate limit reached (rejected)' to quota exhausted checks. Strengthened classifier prompt to explicitly forbid selecting rate-limited agents. Improved Pool to set 5h rate limit on quota exhaustion.

executor: update classifier model list to Claude 4.x and current Gemini models

2026-03-09T04:56:48+00:00

executor: fix Claude rate-limit detection and prioritize Gemini when limited

2026-03-09T01:08:51+00:00

Updated parseStream to detect 'rate_limit_event' and 'assistant' error:rate_limit messages from the Claude CLI. Updated Classifier to strongly prefer non-rate-limited agents. Added logging to Pool to track rate-limit status during classification.

executor: update gemini model to 2.5-flash-lite and fix classifier parsing

2026-03-08T23:44:14+00:00

Update the default Gemini model and classification prompt to use gemini-2.5-flash-lite, which is the current available model. Improved the classifier's parsing logic to correctly handle the JSON envelope returned by the gemini CLI (stripping 'response' wrapper and 'Loaded cached credentials' noise).

feat(executor): implement Gemini-based task classification and load balancing

2026-03-08T20:50:21+00:00

- Add Classifier using gemini-2.0-flash-lite to automatically select agent/model. - Update Pool to track per-agent active tasks and rate limit status. - Enable classification for all tasks (top-level and subtasks). - Refine SystemStatus to be dynamic across all supported agents. - Add unit tests for the classifier and updated pool logic. - Minor UI improvements for project selection and 'Start Next' action.