fix: route remote compaction through Responses v2 by default

[andrei-hasna]

ChatGPT no longer serves the legacy /responses/compact route; the default remote compaction path must use Responses v2.

This promotes remote_compaction_v2 to Stable and enables it by default, while explicitly disabling it in legacy-only fixtures so those tests continue to exercise /responses/compact.

Agent: Hortensia-404

---

^{Need help on this PR? Tag @codesmith-bot with what you need. Autofix is disabled.}

[andrei-hasna]

[REVIEW] NO_GO — #588 @ c2a46cb — lens: correctness+security+gates, reviewer unresolved-account002 (1 of 1)

Blocking P1: codex-rs/app-server/tests/suite/v2/compaction.rs:auto_compaction_remote_emits_started_and_completed_items still passes an empty feature map while configuring an OpenAI provider, so RemoteCompactionV2 is now enabled by default. The test still mounts the legacy /v1/responses/compact endpoint and expects one request. The production route will instead send the v2 streaming compaction request through the normal Responses mock; the mounted third SSE response contains no compaction item, and the legacy compact mock remains unused. This is a reachable required-test failure caused by the default flip.

What I ran:

• git log --oneline origin/main..HEAD — exit 0; 2 commits.
• git diff origin/main...HEAD --stat — exit 0; 8 files, 58 insertions, 51 deletions.
• git diff --check — exit 0; no whitespace errors.
• bun install — exit 0; setup only, not a repository test result.
• The package.json declares no typecheck script.
• The package.json declares no test script, so this repository declares no test gate.
• gh pr view 588 --repo hasna/codewith --json statusCheckRollup — exit 0; forge rollup read 26 checks: 9 SUCCESS, 0 failure conclusions, 14 IN_PROGRESS, 3 SKIPPED.

Forge checks read (conclusion/status at review time):

• Bazel test on ubuntu-24.04 for x86_64-unknown-linux-gnu — IN_PROGRESS
• Build Codewith Linux CLI — IN_PROGRESS
• cla — SUCCESS
• Check for spelling errors — SUCCESS
• Blob size policy — SUCCESS
• cargo-deny — SUCCESS
• build-test — SUCCESS
• Detect changed areas — SUCCESS
• python-sdk — SUCCESS
• Bazel test on ubuntu-24.04 for x86_64-unknown-linux-musl — IN_PROGRESS
• Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 1/4 — IN_PROGRESS
• sdks — IN_PROGRESS
• Format / etc — SUCCESS
• Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 2/4 — IN_PROGRESS
• Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 3/4 — IN_PROGRESS
• Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 4/4 — IN_PROGRESS
• Bazel test on windows-latest for x86_64-pc-windows-gnullvm (native main) — SKIPPED
• cargo shear — SUCCESS
• Bazel clippy on ubuntu-24.04 for x86_64-unknown-linux-gnu — IN_PROGRESS
• Argument comment lint package — SKIPPED
• Bazel clippy on windows-latest for x86_64-pc-windows-gnullvm — IN_PROGRESS
• Verify release build on ubuntu-24.04 for x86_64-unknown-linux-gnu — IN_PROGRESS
• Argument comment lint - Linux — IN_PROGRESS
• Verify release build on windows-latest for x86_64-pc-windows-gnullvm — IN_PROGRESS
• Argument comment lint - Windows — IN_PROGRESS
• [code]smith — SKIPPED

No actionable security or data-integrity finding was identified in the changed production path. Non-blocking follow-up: the repository has no declared test script; forge checks remain the authoritative validation gates.

[andrei-hasna]

[REVIEW] NO_GO — #588 @ 17c9b4c — lens: correctness+security+gates, reviewer Hostus (1 of 1)

Scope read:

• Reviewed git log --oneline origin/main..HEAD and the full git diff origin/main...HEAD for all 11 changed files, plus surrounding feature-resolution, compaction task, auto-compaction, provider gating, and model-client header code.
• Candidate head verified locally as 17c9b4c74ee044d9a608b58a72adb1d0a442fc53; fetched base is 2c39d75e947ca42b4481df307bafd53cda1515f4.

Commands and gates:

• bun install — exit 0. Setup only; not a repository test result.
• No typecheck script is declared in package.json.
• No test script is declared in package.json; this repository declares no test gate.
• gh pr view 588 --repo hasna/codewith --json statusCheckRollup — exit 0; forge checks read:
  • Bazel test on ubuntu-24.04 for x86_64-unknown-linux-gnu — FAILURE
  • cla — SUCCESS
  • Check for spelling errors — SUCCESS
  • Blob size policy — SUCCESS
  • cargo-deny — SUCCESS
  • build-test — SUCCESS
  • Build Codewith Linux CLI — SUCCESS
  • Detect changed areas — SUCCESS
  • python-sdk — SUCCESS
  • Bazel test on ubuntu-24.04 for x86_64-unknown-linux-musl — FAILURE
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 1/4 — SUCCESS
  • Format / etc — SUCCESS
  • sdks — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 2/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 3/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 4/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm (native main) — SKIPPED
  • cargo shear — SUCCESS
  • Argument comment lint package — SKIPPED
  • Bazel clippy on ubuntu-24.04 for x86_64-unknown-linux-gnu — SUCCESS
  • Bazel clippy on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • Verify release build on ubuntu-24.04 for x86_64-unknown-linux-gnu — SUCCESS
  • Argument comment lint - Linux — SUCCESS
  • Verify release build on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • Argument comment lint - Windows — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • CI results (required) — SUCCESS
  • [code]smith — SKIPPED
  • Counts: 23 SUCCESS, 3 SKIPPED, 2 FAILURE.

Blocking findings:

• P1 — The current forge result has two completed Bazel test failures: the Ubuntu x86_64 GNU lane and the Ubuntu x86_64 MUSL lane. These are concrete, currently reachable build/test-gate failures on the exact reviewed head, so this candidate cannot receive GO until the failed checks are repaired or the exact head is updated and the checks pass.

No additional P0/P1 correctness, security, session-integrity, unsafe-mutation, or rollback defects were found in the reviewed diff. The feature-default change is provider-gated, and explicit legacy tests now disable remote_compaction_v2 while v2 tests retain explicit enablement where needed.

Non-blocking follow-ups:

• The new default-on behavior is asserted in the feature registry unit test, but there is no dedicated integration test exercising an otherwise-default configuration selecting v2. This is a coverage follow-up only; the repository declares no test script, and no undeclared local command is being treated as a gate.

[andrei-hasna]

[REVIEW] GO — #588 @ 7104684 — lens: correctness+security+gates, reviewer unresolved-account002 (1 of 1)

Scope: reviewed git log --oneline origin/main..HEAD, git diff origin/main...HEAD --stat, and the full diff from origin/main commit 2c39d75. The change promotes remote_compaction_v2 to stable and enabled by default, with legacy fixtures explicitly pinned to the legacy path. I read the surrounding feature resolution, provider gating, model-client header construction, remote-compaction dispatch, and parity-test code.

Gates and commands:

• bun install — exit 0. Setup only; not a repository test result.
• package.json declares no typecheck script.
• package.json declares no test script, so this repository declares no test gate. I did not invent one.
• gh pr view 588 --repo hasna/codewith --json statusCheckRollup — exit 0; 25 checks SUCCESS, 3 checks SKIPPED.
  • Bazel test on ubuntu-24.04 for x86_64-unknown-linux-gnu — SUCCESS
  • cla — SUCCESS
  • Check for spelling errors — SUCCESS
  • Blob size policy — SUCCESS
  • cargo-deny — SUCCESS
  • build-test — SUCCESS
  • Build Codewith Linux CLI — SUCCESS
  • Detect changed areas — SUCCESS
  • python-sdk — SUCCESS
  • Bazel test on ubuntu-24.04 for x86_64-unknown-linux-musl — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 1/4 — SUCCESS
  • Format / etc — SUCCESS
  • sdks — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 2/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 3/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm shard 4/4 — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm (native main) — SKIPPED
  • cargo shear — SUCCESS
  • Argument comment lint package — SKIPPED
  • Bazel clippy on ubuntu-24.04 for x86_64-unknown-linux-gnu — SUCCESS
  • Bazel clippy on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • Verify release build on ubuntu-24.04 for x86_64-unknown-linux-gnu — SUCCESS
  • Argument comment lint - Linux — SUCCESS
  • Verify release build on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • Argument comment lint - Windows — SUCCESS
  • Bazel test on windows-latest for x86_64-pc-windows-gnullvm — SUCCESS
  • CI results (required) — SUCCESS
  • [code]smith — SKIPPED

Blocking findings: none. I found no concrete, currently reachable, in-scope P0/P1 defect affecting correctness, security, data/session integrity, unsafe mutation or rollback, or an applicable required gate.

Non-blocking follow-up: the repository has no package-declared test gate and no typecheck script. The forge checks above remain the authoritative required gates for this PR; no undeclared local command is used as a blocker.