New table-driven tests raise branch coverage on ContextWindowTokens,
extractModelName, isDigits, rateLimitInfo, normalizeOpenAICompatibleChatURL,
stop-reason normalization and the OpenAI, Anthropic and Gemini tool-choice
converters, covering date-suffix stripping, malformed URLs and default arms.
Test-only, no source changes.
New table-driven tests raise branch coverage on the timeout, curl/wget,
env and recovery-point canonicalization helpers in internal/ai/tools,
exercising previously uncovered flag-parsing arms, mutation-method
detection and numeric-detail type cases. Test-only, no source changes.
New white-box table tests over the pure resource-resolution helpers in
internal/ai/tools/current_resource.go, taking canonicalQueryTypeForResolvedResource,
canonicalQueryIDForResolvedResource and resolvedResourceKindMatchesLocation from
partial to full branch coverage. Every kind switch arm, the provider-uid then
resource-id then alias fallback chain, and the nil guards are pinned to exact
output.
One file, tests only, no source changes. Gates green with go test, gofmt and go
vet, plus an adversarial GLM review scoring three KEEP and zero reject.
New white-box table tests over the pure error classifiers in
internal/ai/patrol_runtime_failure.go, taking ClassifyProviderConnectionFailure
from 18 percent to full coverage and closing the residual branches in
patrolRuntimeFailureFromError and summarizePatrolRuntimeFailureDetail. Every
reachable switch arm is pinned to its exact diagnostic output, and the four
grouped causes that only preflight and readiness state can set are documented
as out of reach from a plain error input rather than faked.
One file, tests only, no source changes. Gates green with go test, gofmt and
go vet, plus an adversarial GLM review scoring two KEEP, one WEAK and zero
reject.
New white-box table tests over the pure validators, predicates and readme
renderer in internal/ai/qualification/contribution.go, covering
ValidateContributionChallenge, validateContributionIdentity,
everyRunChallengeBound, observationsPassedOrEmpty, reportPhasePassed,
ContributionBundle.Validate and renderContributionReadme.
One file, tests only, no source changes. Gates green with go test, gofmt
and go vet, plus an adversarial GLM review scoring seven KEEP and zero
reject.
New white-box table tests over previously-untested pure functions in
internal/ai (patrol run recency, patrol findings JSON validation),
internal/ai/tools (read-only violation hints, VM config parsing, node
target matching), internal/ai/qualification (compare predicate,
percentile and model summary, runner helpers), internal/ai/chat
(investigation run error, session compaction formatting) and
internal/agentcapabilities (path parameter substitution, markdown
helpers).
Twelve files, tests only, no source changes. All gates green with go
test, gofmt and go vet, plus an adversarial GLM review scoring twelve
KEEP and zero reject.
Thinking models served through OpenAI-compatible endpoints (qwen3 via
Ollama >=0.31, DeepSeek) spend most of a turn streaming per-token
reasoning deltas before any content. The stream reader wrapped the whole
turn in a wall-clock deadline at the configured request timeout, so a
live, visibly-thinking stream was killed mid-thought with 'AI response
timed out before completion' (#1576, second symptom).
The timeout's job is stall detection, not turn budgeting. It now bounds
only how long Pulse waits for the stream to start: the response-header
wait (Ollama holds headers while a cold model loads) and the first-chunk
wait both honor the configured timeout, completing what 1c0648451
started. Once deltas flow, the 12s inter-chunk stall bound and caller
cancellation are the only limits, matching the native Ollama provider's
long-standing design.
Verified live against Ollama 0.31.1 / qwen3:8b: with a 15s configured
timeout, a turn streaming 10k chars of reasoning over 4m17s completes
and delivers the answer; previously it died at the timeout.
Ollama's /api/chat returns reasoning in message.thinking, but the native
provider had no field for it: thinking models like qwen3 (the quickstart
default) showed dead air in the Assistant drawer for the whole reasoning
phase. Decode the field, stream it as thinking events (matching the
OpenAI provider's reasoning handling), carry it on the non-streaming
response as ReasoningContent, round-trip prior-turn reasoning on
assistant history messages, and make SupportsThinking tell the truth.
Verified live against Ollama 0.31.1 with qwen3:8b: first stream event is
now thinking (1137 thinking chunks before content), and non-streaming
Chat returns the reasoning text.
The OpenAI-compatible stream reader bounded every chunk wait at 12s.
Local backends (LM Studio, llama.cpp) legitimately spend minutes on
prompt processing before the first SSE chunk, so raising the provider
timeout in Settings changed nothing and Pulse dropped the stream with
'AI response timed out' (discussion #1571). The wait for first bytes now
uses the configured request timeout; the 12s bound still applies to
inter-chunk gaps once the stream is flowing.
A follow-up sent during an active run now offers itself to the running
agentic loop via POST /api/ai/sessions/{id}/steer. Accepted steers join
the loop at its next turn boundary (the abort-check site) as plain user
messages, are announced with a steer_applied stream event so the drawer
settles the pending row, and persist through the end-of-run save. A
steer carries prompt text only: no route, control-level, or autonomy
changes, no turn-budget extension, system sessions rejected, and the
per-session inbox is bounded (steer_backlog overflow). Delivery is not
guaranteed by acceptance: a run that ends first discards the inbox and
the row drains as an ordinary queued turn, so pre-steering queue
semantics remain the fallback. Steering rows lose edit/remove once
accepted.
