Files
pulse/internal/ai
rcourtman 7a1e41bcf9 Let flowing AI streams outlive the configured request timeout
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.
2026-07-14 11:57:26 +01:00
..
2026-07-01 10:38:57 +01:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-03-18 16:06:30 +00:00
2026-07-12 13:29:21 +01:00
2026-03-18 16:06:30 +00:00