Repository navigation
fix(acp): backport the session-reliability fixes to release/0.8.0 - #15635
Conversation
#14699, #15300) Backport of #14699, #15300 to release/0.8.0, cherry-picked in main's merge order. * fix(chat): keep an unconfirmed send pending instead of offering Resume (#14699) (cherry picked from commit e8959f4) * fix: stop the nudge loop on kiro-cli's oversized-request refusal (#15300) (cherry picked from commit eab6ee2) Backport adaptation for release/0.8.0: acp/transport_errors.py does not exist here (it was split out of acp/client.py by #15153, not backported), so its four hunks are applied verbatim to the same code in acp/client.py; the test import of _raise_acp_error and one doc path follow it there. The characterization row for test/test_acp_refactor_error_surface.py is dropped: that table is main-only.
Design Review (Fable 5) — ✅ PASSDesign-level review of Design-Verdict: PASS Spot-check the #15300 adaptation against main — same hunks in [DESIGN-REVIEWED] 9bf86b0 |
UX Review (Fable 5) — 🔴 BLOCKUX-level review of UX-Verdict: BLOCK Cannot evaluate: missing screenshots of the pending-send UI — blind read not performed because the PR attaches no image. Evidence gaps
[UX-REVIEWED] 9bf86b0 |
First Principles Review (Fable 5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Verify the #15300 adaptation: the four hunks relocated into What this change shipsInventory (10 items) — 10 justifiedIntent: backport three merged session-reliability fixes (#11717, #15300, #14699) from main to release/0.8.0 — a FIX.
[FIRST-PRINCIPLES-REVIEWED] 9bf86b0 |
GPT 5.6 Review — 🔴 changes requested (blocking)GPT 5.6 found at least one blocking issue that must be resolved before merging This comment is updated in place on each push. BLOCKING -- website/src/pages/ChatPage.tsx:3045 -- A timed-out Queue send discards the only copy of the message (origin: validation) Adjudication (Opus 5) — is blocking on each finding proportionate?F1 — HIGH: the typed message is the only copy and its loss is visible-but-unrecoverable (no draft, no bubble, no stash). False positive or not applicable? A repository writer can comment: |
Opus 5 Review — ✅ no blocking findingsReviewed Review detailsNo findings. FINDING — src/kiro_crew/dashboard/chat_runner.py:10550 — the bare [OPUS-REVIEWED] 9bf86b0 Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
Problem / Motivation
Goal: On a 0.8.0.x build, a session survives one unsupported historical image, a self-driving loop stops re-firing kiro-cli's oversized-request refusal, and a timed-out send stays pending instead of offering a Resume that drops the typed text.
mainalready does all three.Backport of 3 P1 session-reliability fixes, all merged on
main:max_cycles. Needs fix: recover from unsupported image history #11717's image-format regex.#13998 was in this batch's plan but is not here: Joe Guo already backported it in #15614 (with #15177 via #15574), which is merged on
release/0.8.0.Why it matters
These are known 0.8.0.x pains (oversized-request loop, empty context after Resume), and insider.3 / 0.8.0.4 are built from this branch.
Not a goal
transport_errors.pysplit, not fix(acp): retry the MCP settings read when it fails transiently #13998 (already on release), no version bump.What changed (motivation → approach → change)
git cherry-pick -xinmain's merge order (#14699 → #11717 → #15300) onto the currentrelease/0.8.0, keeping authorship. These are two commits under PR Hygiene's cap: pstarkgit's #11717, then Stan's #14699 + #15300. #14699 is frontend-only, so the regrouped tree is byte-identical to the merge-order tree. Merge commits: e8959f4, dbaee46, eab6ee2.#14699 and #11717 picked cleanly. #15300 is adapted:
acp/transport_errors.pydoes not exist on release (main's #15153 split it out ofacp/client.py). The same functions (_RE_IMAGE_FORMAT_UNSUPPORTED,_is_transient_raw_error,_raise_acp_error) still live inacp/client.pyhere, with identical context, so #15300's four hunks applied there verbatim (same lines, offset only). The new test intest_recovery_l1_chat_runner.pyimports_raise_acp_errorfromkiro_crew.acp.clientinstead ofkiro_crew.acp.transport_errors, and one doc path inlearn-cron-dashboard.mdnamesacp/client.py. The characterization row #15300 adds totest/test_acp_refactor_error_surface.pyis dropped, because that table ismain-only (also from #15153). The behaviour is covered by #15300'stest_acp_error_surface.pyandtest_recovery_l1_chat_runner.pytests, carried as-is. The same approach as #15575 (#15278).Backwards compatibility
Same as the source PRs.
Tests
vitest runon fix(chat): keep an unconfirmed send pending instead of offering Resume #14699's 4 test files: 437 passed. With fix(chat): keep an unconfirmed send pending instead of offering Resume #14699's 4 source files reverted: 26 fail.tsc --noEmitclean.Related Issues
Backport of #11717, #15300 and #14699 to
release/0.8.0.Pattern harvest
Not generalizable here: each source PR carries its own harvest.
Checklist
feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)Contribution License Agreement