Add local llama reasoning and harden checkpoint recovery - #43
Merged
Merged
Conversation
…effort The OpenAiChatCompletions branch clamped High|XHigh|Max to "high" via the legacy model-name mapping and never consulted catalog model_specs effort levels, so servers whose templates reject unadvertised levels (e.g. a llama.cpp GGUF accepting only xhigh/medium/low) returned HTTP 500 on every request. Resolve reasoning_effort like the AnthropicMessages branch: declared per-model levels first, legacy catalog effort levels for legacy-source specs, then the model-name clamp as fallback.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
reasoning_contentstreaming, current-turn replay, strict local-route detection, and active context accountingSafety and compatibility
Verification
cargo fmt --all -- --checkcargo clippy -p dext --all-targets --all-features --locked --no-deps -- -D warningscargo audit --deny warningscargo deny check licensescargo test -p ratatui-core --lib --lockedcargo build --release --lockedcargo test --release --locked(986 tests plus 4 Linux PTY smoke tests)cargo install --path . --force --locked