mirror of
https://github.com/rcourtman/Pulse.git
synced 2026-10-19 10:33:29 +00:00
eb665b2a0d
Some checks failed
Build and Test / Secret Scan (push) Waiting to run
Build and Test / Frontend & Backend (push) Waiting to run
Canonical Governance / governance (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 1/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 2/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 3/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 4/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 5/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 6/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 7/8) (push) Waiting to run
Core E2E Tests / Playwright Core E2E (shard 8/8) (push) Waiting to run
Core E2E Tests / Agent registration lifecycle (push) Waiting to run
Core E2E Tests / E2E verdict (push) Blocked by required conditions
Patrol Qualification Regression / Catalog, scorer, and replay regression (push) Has been cancelled
The readiness advisor failed capable local models for adapter and probe
defects rather than model incapability (#1624 Ollama, #1614 llama.cpp):
- Send num_ctx sized to the haystack fixtures (clamped to the model's
trained window) so Ollama no longer truncates ~25KB prompts at its
4096-token server default; the trained-window guard alone passed while
the runtime request was being truncated.
- Forward an explicitly pinned temperature 0 instead of dropping it to
Ollama's 0.8 default against a nonce-exact validator (ChatRequest gains
TemperatureSet; Ollama options temperature is now a pointer).
- Raise the probe generation cap from 256 to 2048 tokens so qwen3-style
<think> reasoning cannot exhaust the budget before the tool call, and
surface the provider done_reason when validation fails.
- Synthesise tool-call IDs in the OpenAI-compatible adapter (streaming
finalizer and buffered path) when the server omits them, as llama.cpp
commonly does, mirroring the Ollama adapter instead of failing tool
protocol 0/3 on transport shape.
- Probe with the Patrol loop's 60s stream stall allowance instead of the
12s chat default (chat.PatrolProviderStreamIdleTimeout is now exported).
- Stop discarding probe and validator errors: log them, carry them in a
new PatrolModelReadinessResult.Details field surfaced through the API
snapshot and Settings UI, and keep a transport-level probe failure's
specific diagnosis instead of overwriting it with the generic
capability wording.
Builds on
|
||
|---|---|---|
| .. | ||
| anthropic.go | ||
| anthropic_test.go | ||
| context_limits.go | ||
| context_limits_branchcov_test.go | ||
| context_limits_test.go | ||
| factory.go | ||
| factory_test.go | ||
| gemini.go | ||
| gemini_stream_test.go | ||
| gemini_test.go | ||
| integration_test.go | ||
| issue1614_openai_toolcall_id_test.go | ||
| issue1624_ollama_probe_options_test.go | ||
| notable_models.go | ||
| notable_models_test.go | ||
| ollama.go | ||
| ollama_test.go | ||
| openai.go | ||
| openai_compatibility_test.go | ||
| openai_helpers_branchcov_test.go | ||
| openai_test.go | ||
| provider.go | ||
| provider_contract_test.go | ||
| provider_normalize_branchcov0719pm_test.go | ||
| rate_limit.go | ||
| rate_limit_branchcov_test.go | ||
| subscription_agent.go | ||
| subscription_agent_live_test.go | ||
| subscription_agent_test.go | ||
| tool_choice_branchcov_test.go | ||