crossbar/docs/plans/v2.1/README.md

v2.1 implementation plan: fixes found while running v2

For the implementing model: do not work from this file. The owner gives you one task file at a time. This file is the index for the owner and the reviewer.

Goal: close the two defects and one gap found while v2 ran, without new features.

• 01-cancel-record — a delivered response is never recorded as a 499; cancellation is what the reverse proxy observed. Found 2026-09-25 by the intermittent Errors:2 in TestQueueFullIs503; verified with a diagnostic build; the given internal/proxy/served_test.go reproduces it on every run.
• 02-props-loaded-only (to be written after v2 merges) — the poller asks /props?model=X only for models /v1/models lists as loaded, because llama-server's router autoloads a model named in that query (models_autoload). See the v2 README's note of 2026-09-25.
• 03-timing-margins (to be written) — the remaining sleep-ordered assertions in v1 and v2 given tests move to state-based waits, as TestQueueFullIs503 and TestParallelAndQueue did.

How this plan was made: acceptance tests first; no reference implementation. The given test for task 01 was run against the v2 tree (fails six of six) and against a throwaway fix that follows the task's rule (passes four full package runs with the v1 cancel tests); the throwaway was discarded.

Global constraints

• Everything in AGENTS.md. Branch v2.1 from master after v2 merges. One task, one fresh OpenCode session, one commit. Given files are copied and never edited.

Changes during the run

(none yet)