Bump @openai/codex-sdk to 0.146.0: gpt-5.6-sol rejects the vendored 0.142.5 client - #1309
Merged
Merged
Conversation
…er client The server rejects gpt-5.6-sol (shipped default since PR #1301) from the SDK's vendored 0.142.5 codex binary: 'requires a newer version of Codex'. This broke every porch codex-lane consult. The dependency range already allowed 0.146.0; only the lockfile pinned it back. Build green, 106 consult tests pass against the new SDK.
waleedkadous
added a commit
that referenced
this pull request
Jul 31, 2026
Claude REQUEST_CHANGES incorporated. Recommended approach changed to write-then-verify: architect writes the state file before invoking the CLI, which validates synchronously and arms only quiesce -> clear -> reorient. Removes receipt polling from Tower, makes 'no clear without a verified save' true by construction in the self path, and shrinks the clear-after-new-work window from 300s to one quiet window. Original nonce/Tower-armed design kept as Approach 1b with rejection reasons. Also: restated the post-clear monitor-stop as pre-clear (enforceable) plus best-effort reconciliation; replaced the '## Monitors' heading gate with a MONITORS: token the adopted template carries verbatim; added the clear-after-new-work hazard to risks/questions/tests; stopped overclaiming --boundary as a recorded human decision in the self path; added quiescence-against-a-live-TUI as a second inherited unknown; recorded the sendRaw vs sendMessage divergence the shared extraction must preserve; fixed the snapshot ordering that write-then-verify would otherwise have broken. Codex consult pending - its lane is down (vendored codex-sdk binary, PR #1309).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
Every porch codex-lane consult is failing since the shipped-defaults change (PR #1301): the server rejects
gpt-5.6-solfrom old clients with400: The 'gpt-5.6-sol' model requires a newer version of Codex. First hit by the aspir-1307 builder's spec verification; every active builder would wedge at its next review.Why the pre-merge live probe didn't catch it: the probe used the globally installed codex CLI (0.146.0), which the server accepts — but consult's codex lane runs through
@openai/codex-sdk, which vendors its own codex binary, locked at 0.142.5. Two different clients, one probe.Fix
Bump
@openai/codex-sdk^0.142.5→^0.146.0(range already permitted it; only the lockfile pinned it back). No code changes.Testing
ModelReasoningEffortimport unchanged).local-install), scheduled immediately after merge;consult -m codexagainst a trivial prompt is the acceptance check.Lesson (for the record)
A live model-id probe is only as good as client-identity parity: probe through the SAME client the production path uses. Filed mentally against the #1288 verification methodology.
🤖 Generated with Claude Code