fix(orchestration): raise verifier_timeout_secs default to 120s#6367
Merged
Conversation
github-actions
Bot
added
documentation
bug-ops
enabled auto-merge (squash)
July 17, 2026 02:56
orchestration.verifier_timeout_secs defaulted to 30s, too short for PlanVerifier::verify()'s LLM round-trip against local 20B+ Ollama models (e.g. gemma4:26b, the model class the grounding fix's own playbook recommends for reproduction). On timeout the fail-open path marks the task Completed without ever calling ground(), silently skipping the entire tool-call grounding safety net added by #6278/ Closes #6366
bug-ops
force-pushed
the
fix/6366-verifier-timeout-default
branch
from
July 17, 2026 02:57
5465793 to
9ff574d
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
orchestration.verifier_timeout_secsdefaulted to 30s, which reliably timed outPlanVerifier::verify()'s LLM call against local 20B+ Ollama models (e.g.gemma4:26b, the model class the orchestration: task verifier accepts hallucinated tool-call completions from sub-agents with no matching execution #6278/orchestration: whole-plan verify_plan() aggregated-output verification remains ungrounded #6287 grounding fix's own playbook recommends for reproduction)Completedwithout ever callingground()— silently defeating the tool-call grounding safety net in exactly the deployment shape it was built forconfig/default.tomlCloses #6366
Test plan
cargo nextest run -p zeph-config -p zeph-orchestration --features llm-planning— 1383/1383 passedorchestration_config_default_verifier_timeout_secs_is_120asserting the new defaultcargo +nightly fmt --check,cargo clippy --profile ci --workspace --all-targets --features "desktop,ide,server,chat,pdf,scheduler,testing" -- -D warnings,cargo nextest run --config-file .github/nextest.toml --workspace --features "desktop,ide,server,chat,pdf,scheduler" --lib --bins(13968 passed), rustdoc gate,gitleaks protect --staged— all cleanCHANGELOG.mdandconfig/default.toml