models: Pareto role assignments from live catalogs; gpt-5.4-mini sidecar fallback#286
Open
Zpankz wants to merge 1 commit into
Open
models: Pareto role assignments from live catalogs; gpt-5.4-mini sidecar fallback#286Zpankz wants to merge 1 commit into
Zpankz wants to merge 1 commit into
Conversation
…sidecar fallback Queried live provider catalogs via wired OAuth creds (Codex backend, Antigravity cloudcode-pa, xAI) instead of relying on stale hardcoded lists. Documented Pareto-optimal model->role assignments for every specialized agent role (primary coding, swarm subagents, memory sidecar, autoreview, autojudge, ambient) in docs/model-role-assignment.md, including a status table, a per-role config example, and reproducible catalog-fetch commands. gpt-5.4-mini is now live (272k ctx, cheaper/faster than gpt-5.4) so it is the Pareto-better OpenAI sidecar fallback for the high-frequency relevance/extraction workload. Added it to ALL_OPENAI_MODELS so the picker/catalog surface it.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Assigns Pareto-optimal models to each specialized agent role, derived from live provider catalogs queried via the wired OAuth credentials (not stale hardcoded lists).
cloudcode-pa(Ultra tier), xAI/Grok.docs/model-role-assignment.md: per-role Pareto picks (primary coding, swarm, memory sidecar, autoreview, autojudge, ambient), config key mapping, a config example, catalog-drift notes, and reproducible fetch commands.gpt-5.4-miniis now live (272k ctx, cheaper/faster thangpt-5.4); switched the OpenAI sidecar OAuth fallback to it and added it toALL_OPENAI_MODELS.Files
docs/model-role-assignment.md(new)crates/jcode-base/src/sidecar.rs—SIDECAR_OPENAI_OAUTH_FALLBACK_MODEL->gpt-5.4-minicrates/jcode-provider-core/src/models.rs— addgpt-5.4-minitoALL_OPENAI_MODELSTesting
cargo build --profile selfdev -p jcode-base -p jcode-provider-coreclean (pre-existing warnings only).Notes
Nonein config (provider-strongest behavior preserved); the doc lists the values to set for the Pareto pick per role.codex-auto-reviewisvisibility=hide; autoreview usesgpt-5.3-codexinstead.