Files
oh-my-pi/packages/coding-agent/test
roboomp 9599689af3 fix(compaction): routed summary oneshots through provider cap
Compaction issued summarization HTTP requests via the default
`completeSimple` transport, bypassing
`wrapStreamFnWithProviderConcurrency` which was only wired into
`Agent.streamFn` / `sideStreamFn`. With the per-LLM-turn bracket
introduced in this PR, multiple ollama-cloud subagents that auto- or
manually compact could issue uncapped summary requests in parallel
and exceed `providers.ollama-cloud.maxConcurrency` (chatgpt-codex
review on #3751).

Added an optional `completeImpl` transport override to
`SummaryOptions` and `GenerateBranchSummaryOptions` and threaded it
into every `instrumentedCompleteSimple` call in compaction +
branch-summarization. Wired `AgentSession.#compactWithFallbackModel`
and the `generateBranchSummary` caller to route through
`#sideStreamFn` — the same limiter-wrapped transport the handoff path
already uses.

Pinned with a coding-agent regression that drives `compact()` end to
end against the wrapped sideStreamFn at maxConcurrency=1 and asserts
peak in-flight stays at 1 across a concurrent unrelated side request.

Fixes #3749
2026-06-28 21:11:48 +00:00
..
2026-06-26 18:43:32 +02:00
2026-05-30 18:08:51 +02:00
2026-06-26 12:24:42 +02:00
2026-05-30 18:08:51 +02:00
2026-06-24 13:44:47 +00:00