[congvc-bot-x99]

Status

Draft. Layer A3 of CHE-1803 (DM auto-compact). A1 (PR #281) and A2 (PR #282) are merged to main. The repair PR #290 (CHE-1824) is merged to main as 2b135399996d8072c5a99deb88ef55edb62f49b4; it renumbered the context migration to 630. PR #289 was closed without merging. This PR targets main; origin/main is merged into the branch, so the visible diff is A3 only. Merge stays Cheese's gate.

Conditions

• Auto-compact needs a daemon that reports context (A1). Old daemons leave NULL, and their runs never trigger it.
• The trigger covers web DMs only. A channel-bound chat is skipped.
• A compaction keeps the active-state set the design review required (CHE-1804 P1): queued, dispatched, running, waiting_local_directory, deferred. Send rejection and duplicate suppression are tested in each of the five.
• Mobile needs no change: it shows the 409 under its existing send-failure rule. Not run on a device.
• The stuck-task sweeper path is covered through SettleTerminalTaskState, the single entry point of every terminal path. The tests drive completed, failed and cancelled. A swept task is not driven separately.
• Retrospective tests, added with the implementation and not first: the service resolver and boundary tests. One red test fixture was repaired: a second fixture in one test reused an agent name and now runs as a subtest.

Change

• Migration 655: agent_task_queue.task_kind, compact_reason, compact_trigger_tokens.
• After a completed run, the server queues one compaction task when the run's last prompt reached the threshold (agent override over workspace over 80%). The task owns no user input. The claim sets its prompt to the compact command, so the workspace and agent Compact prompt apply.
• The server writes the reason into the old DM as a compact_notice row: Auto-compacted: context 164k of 200k tokens (82%) reached the 80% threshold. Continuing in a new DM. The new DM's summary starts with the same reason line. The notice never enters a prompt.
• A send while a compaction is active returns 409 chat_compacting. The check runs under the session lock. A manual /compact is marked at enqueue and locks sends the same way. Cancelling the compaction unlocks sends.
• Failure guard: an automatic compaction that ends without continuing the DM posts Auto-compact failed (<status>). Type /compact to retry. A new attempt waits until the context grows 10% past the failed trigger. A failed manual compaction suppresses nothing.
• GET /chat/sessions and /chat/sessions/{id} return compacting. The chat:session_updated event carries it.
• Web: the composer is disabled with "Compacting…" and keeps the draft. The notice renders as a muted note. A 409 shows a toast. All five locales are updated.

Correction after review (Sol, P2)

While a DM compacts, a preserved nonempty or /fork draft hid Stop and showed a disabled Queue Send. Commit 5945fb0 adds runtime regression tests first (2 failed, 1 passed against the parent, matching Sol's probe: ordinary and /fork drafts had no Stop button; the empty-draft control passed). Commit 0b667ec makes ChatInput show Stop whenever compacting is set, and the same tests pass. Both chat surfaces use this input. The draft stays in the editor and nothing is sent. Migration SQL is unchanged. Prefix audit on main 2b135399996d8072c5a99deb88ef55edb62f49b4: 627, 628, 629 (other work), 630 (context), 653, 655 (compaction) are unique, and TestMigrationNumericPrefixesAreUnique and the sqlc diff are clean.

Acceptance coverage added (retrospective)

Commit b95365c adds handler tests that all pass with no production change: cancelling an auto compaction in each of the five active states (queued, dispatched, running, waiting_local_directory, deferred) unlocks sends and posts Auto-compact failed (cancelled); the stuck-task sweeper (queued expiry, dispatched and running stale, followed by the retry handler) posts Auto-compact failed (failed), leaves no active compaction behind, unlocks sends and holds the 1.1x re-arm rule. waiting_local_directory and deferred are excluded from the stale sweep by design, so only cancel drives them. No test exposed a defect, so there is no new red.

Evidence

Test-First Gate: commit 8ae363b is tests-only and fails against its parent for the stated behavior (runtime failures, not compile errors). Commit fae0b75 implements it. A later test commit dfc453d and fix commit 36a9ad1 disable the chat page composer, which the first pass missed. The merge commit 80e936d brings A1 in first.

Red at 8ae363b. Go: every new handler test failed, for example column "task_kind" does not exist (SQLSTATE 42703) and session response has no compacting field. Web:

⎯⎯⎯⎯⎯⎯⎯ Failed Tests 2 ⎯⎯⎯⎯⎯⎯⎯
AssertionError: expected 'This session is archived' to be 'Compacting…' // Object.is equality
TestingLibraryElementError: Unable to find an accessible element with the role "note"
      Tests  2 failed | 119 passed (121)

Green at fae0b75. These pass:

• go test ./internal/handler ./internal/service (full packages);
• the full views chat, locales and settings web tests (1040 tests);
• go vet, and the views and core typecheck.

Not clean on this X99 runtime: cmd/server TestSweepDispatchedStaleTask failed once in this run and also failed once on A1's CI. It passes when run alone. It is not caused by this PR, which does not touch the sweeper. CI is the authority.

Changelog: Web DMs now compact themselves into a new DM when their context reaches the configured share of the window, and say why.

Closes CHE-1807
Refs CHE-1803