Console-first model setup: /keys + /model become the complete, reliable path - #2
Merged
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ
…oice Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this does
Makes the interactive console the complete way to configure CodeCouncil's models —
/keys+/modelalone now always produce a working, intentional setup, for any supported provider key.Four changes (plan:
docs/plans/2026-08-01-console-model-flexibility.md):critic/agent.py,core/config.py): with no model configured, the first configured key picks its provider's default model (KEY_DEFAULT_MODELS, ordered: free NVIDIA first, Anthropic last for decorrelation). Previously onlyNVIDIA_API_KEYauto-defaulted — an OpenAI/OpenRouter key alone fell through to pi's possibly-unauthenticated default./model//proberbeat stale launch flags (codecouncil/main.py): a knob set via the console now resolves from config.json only — a launch-time--modelflag or exportedCOUNCIL_MODELno longer silently overrides the slash command on critic restart (per-knobconsole_settracking)./modelvalidates + informs (codecouncil/console.py,core/config.py): setting a model warns (never blocks) on a missing provider key, malformedprovider/model-id, or single-segment openrouter/nvidia-nim ids that would 404. Bare/modelshows the current resolved model, which layer set it (flag/env/config/auto), and copy-pasteable examples for the keys actually configured./keyschains into model choice: after saving a key, the console reports the model the critic will use, and offers that provider's default when the current model runs on a different key.Docs: README and CLAUDE.md now lead with
/keys(hidden input) instead of theecho ... >> ~/.codecouncil/envpattern, which leaves credentials in shell history.Testing
tests/test_codecouncil.py,tests/test_agent.py): map consistency,check_modelshapes,resolve_with_source, per-knob override resolution, console flows with mockedinput/getpass.ruff==0.15.22clean.🤖 Generated with Claude Code
https://claude.ai/code/session_01A2CMGoziPn6h1vK94rSLeJ