Conversation
…/stderr llama.cpp's C library writes log output directly to stderr by default. The llama-cpp-2 crate provides send_logs_to_tracing() to redirect this through the tracing framework, but it was never called. This caused llama.cpp output to clutter the terminal when using the goose CLI with the local inference provider. Call send_logs_to_tracing() during InferenceRuntime initialization so all llama.cpp/ggml logs flow through tracing, which the CLI routes exclusively to log files.
DOsinga
approved these changes
Feb 23, 2026
zanesq
added a commit
that referenced
this pull request
Feb 23, 2026
…oviders * 'main' of github.com:block/goose: New navigation settings layout options and styling (#6645) refactor: MCP-compliant theme tokens and CSS class rename (#7275) Redirect llama.cpp logs through tracing to avoid polluting CLI stdout/stderr (#7434) refactor: change open recipe in new window to pass recipe id (#7392) fix: handle truncated tool calls that break conversation alternation (#7424) streamline some github actions (#7430) Enable bedrock prompt cache (#6710) fix: use BEGIN IMMEDIATE to prevent SQLite deadlocks (#7429) Display working dir (#7419) dev: add cmake to hermitized env (#7399) refactor: remove allows_unlisted_models flag, always allow custom model entry (#7255) feat: expose context window utilization to agent via MOIM (#7418) Small model naming (#7394) chore(deps): bump ajv in /documentation (#7416) doc: groq models (#7404) Client settings (#7381) Fix settings tabs getting cut off in narrow windows (#7379) # Conflicts: # ui/desktop/src/components/settings/dictation/DictationSettings.tsx
michaelneale
added a commit
that referenced
this pull request
Feb 23, 2026
…xt-edit * origin/main: (35 commits) docs: generate manpages (#7443) Blog/goose v1 25 0 release (#7433) fix: detect truncated LLM responses in apps extension (#7354) fix: removed unnecessary version for goose acp macro dependency (#7428) add flag to hide select voice providers (#7406) New navigation settings layout options and styling (#6645) refactor: MCP-compliant theme tokens and CSS class rename (#7275) Redirect llama.cpp logs through tracing to avoid polluting CLI stdout/stderr (#7434) refactor: change open recipe in new window to pass recipe id (#7392) fix: handle truncated tool calls that break conversation alternation (#7424) streamline some github actions (#7430) Enable bedrock prompt cache (#6710) fix: use BEGIN IMMEDIATE to prevent SQLite deadlocks (#7429) Display working dir (#7419) dev: add cmake to hermitized env (#7399) refactor: remove allows_unlisted_models flag, always allow custom model entry (#7255) feat: expose context window utilization to agent via MOIM (#7418) Small model naming (#7394) chore(deps): bump ajv in /documentation (#7416) doc: groq models (#7404) ...
lifeizhou-ap
added a commit
that referenced
this pull request
Feb 24, 2026
* main: Simplified custom model flow with canonical models (#6934) feat: simplify the text editor to be more like pi (#7426) docs: add YouTube short embed to Neighborhood extension tutorial (#7456) fix: flake.nix build failure and deprecation warning (#7408) feat(claude-code): add permission prompt routing for approve mode (#7420) docs: generate manpages (#7443) Blog/goose v1 25 0 release (#7433) fix: detect truncated LLM responses in apps extension (#7354) fix: removed unnecessary version for goose acp macro dependency (#7428) add flag to hide select voice providers (#7406) New navigation settings layout options and styling (#6645) refactor: MCP-compliant theme tokens and CSS class rename (#7275) Redirect llama.cpp logs through tracing to avoid polluting CLI stdout/stderr (#7434) refactor: change open recipe in new window to pass recipe id (#7392) fix: handle truncated tool calls that break conversation alternation (#7424) streamline some github actions (#7430) Enable bedrock prompt cache (#6710) fix: use BEGIN IMMEDIATE to prevent SQLite deadlocks (#7429) Display working dir (#7419)
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
2 participants
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.
Problem
When using the
gooseCLI with the local inference provider, llama.cpp output goes directly to stderr, cluttering the text interface and making it harder to use.Root Cause
The
llama-cpp-2Rust bindings providesend_logs_to_tracing()to redirect llama.cpp's C library log output through thetracingframework, but it was never called. This meant llama.cpp used its default behavior of writing to stderr.Fix
Call
llama_cpp_2::send_logs_to_tracing(LogOptions::default())duringInferenceRuntimeinitialization. This redirects all llama.cpp/ggml logs through tracing, which the CLI already routes exclusively to log files (no console layer). When runninggooseddirectly or via the GUI, the tracing subscriber typically includes a console layer, so logs remain visible there.Changes
crates/goose/src/providers/local_inference.rs: Addedsend_logs_to_tracing()call inInferenceRuntime::get_or_init()