fix(server): OpenCode ChatGPT usage limits keep their reset time by abdfattahz · Pull Request #26264 · pingdotgg/t3code

abdfattahz · 2026-10-28T03:02:02Z

Problem

When OpenCode runs an OpenAI model through a ChatGPT subscription and the Codex usage window is exhausted, the turn now fails as usage_limit (since https://git.cafe/pingdotgg/t3code/pulls/18315) but without resetAt. The thread shows "Reset time unavailable; retry manually", the resume-at-reset and snooze actions are hidden, and auto-resume never arms.

ChatGPT already says when the limit lifts. Its 429 body is:

{"error":{"type":"usage_limit_reached","message":"The usage limit has been reached","plan_type":"plus","resets_at":1788753614,"resets_in_seconds":57361}}

OpenCode 2 forwards that body on session.execution.failed as error.response.body, but the adapter ignored it.

Change

When the OpenCode 2 adapter classifies a failure as a usage limit, it decodes error.resets_at (Unix seconds) from response.body and passes it as resetAt to makeProviderFailure, which already validates it and keeps it only for usage_limit. Claude limits keep the message-based reset from https://git.cafe/pingdotgg/t3code/pulls/29301, which takes precedence. Other bodies without that field (OpenCode Go, Zen, other providers) still produce no reset time, as before. No contract, client, or orchestration changes; the existing reset UI and auto-resume worker pick it up.

Scope and approval

Fixes https://git.cafe/pingdotgg/t3code/issues/26265.

Follow-up to https://git.cafe/pingdotgg/t3code/issues/16366, which was closed by https://git.cafe/pingdotgg/t3code/pulls/18315 with the note that "OpenCode doesn't send a reset time in these events, so none is shown yet". For ChatGPT-backed models it does send one, in the response body. This is a small, focused fix in one adapter branch: it fills a field the failure contract already has, for the one provider shape that reports it. Separate from the Codex-provider fix in https://git.cafe/pingdotgg/t3code/pulls/18721 / https://git.cafe/pingdotgg/t3code/issues/14169.

Verification

Added a ChatGPT 429 row to the existing classifies $name as $failureClass table in OpenCode2AdapterV2.test.ts, expecting resetAt: "2026-10-27T15:25:41.000Z". With the adapter change stashed it fails on exactly that row (missing resetAt); the other rows pass. With the change, the file passes (89/89 after merging current main).
vp run check:changed: format, lint, knip, typecheck (36 packages), and the changed test file all pass.
Payload shape: taken from a real ChatGPT Plus usage-limit 429 recorded in my local OpenCode store (responseBody on an OpenCode 1.x message). I confirmed that OpenCode 2.1.3's execution-failure mapper includes response: { body } when the HTTP error has a body, and the @opencode/schema 2.0.28 Session.StructuredError used here declares response.body.
Not checked: a live end-to-end ChatGPT quota refusal through T3. My quota had already reset when I wrote this, and I couldn't get OpenCode 2 to route to a local mock 429 endpoint. Server-only change, so there are no screenshots.

Implementation, tests, and PR: Claude Opus 5.5 via Claude Code in T3 Code.

🤖 Generated with Claude Code

Fixes #26265

ChatGPT-backed OpenAI models answer usage limits with a 429 whose body carries error.resets_at. Read it from the failure's response body so the usage-limit failure gets a resetAt, enabling resume and snooze at reset. Co-Authored-By: Claude Opus 5.5 <[email protected]>

chatgpt-codex-connector · 2026-10-28T03:02:13Z

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	⚠️ Failed 2026-10-28T03:03:34.169508Z We couldn’t complete this review. Comment `@codex review` to try again.	`b5e2a29`	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

macroscopeapp · 2026-10-28T03:03:39Z

Approvability

Verdict: Approved at b5e2a29

Macroscope's review found this PR approvable — Preserves provider-reported usage-limit reset times for existing display and recovery flows. Invalid timestamps are ignored, and automatic recovery remains controlled by existing preferences, disabled by default.

^{You can add or adjust custom eligibility rules. Learn more.}

coderabbitai · 2026-10-28T03:10:32Z

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Last reviewed commit: 7500e4b
Latest commit, not reviewed: cc57970

Use the following commands to manage reviews:

@coderabbitai resume to resume automatic reviews.
@coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

Resume reviews
Trigger review

No actionable comments were generated in the recent review.

Walkthrough

The OpenCode 2 adapter parses a reset timestamp from a usage-limit response body and uses it when no Claude-specific reset time is available. A test covers a ChatGPT quota error and checks the expected reset time.

Changes: OpenCode 2 reset-time handling

Layer / File(s)	Summary
Parse and attach reset time `packages/provider-opencode/src/server/v2/adapter.ts`, `apps/server/src/orchestration-v2/Adapters/OpenCode2AdapterV2.test.ts`	The adapter converts a finite Unix-seconds `resets_at` value to an ISO timestamp. It returns `null` if decoding or date conversion fails, and uses the parsed timestamp when a Claude-specific reset time is unavailable. The test checks the ChatGPT quota-error case and conditionally expects `resetAt`.

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Bug fix · Severity of issue fixed: Medium

Suggested reviewers: juliusmarminge, fixfon

Merge Risk: Minimal · previous review 7500e

OpenCode ChatGPT usage-limit failures now keep their reset time, so the reset UI and auto-resume can use it. Other failures behave as before. No merge-blocking risk was found.

Pre-merge checks: 4

Check name	Status	Explanation
Title check		The title names the main change: OpenCode ChatGPT usage-limit failures now keep their reset time, which matches the adapter change that reads error.resets_at from the response body and passes it as re…
Description check		The description follows the template's sections (Problem, Change, Scope, Verification) and fills each one with specific content. It explains the failure, the 429 payload shape, the adapter fix, and th…
Linked Issues check		Issue `#26265` requires OpenCode 2 ChatGPT usage-limit failures to carry the reset time from the 429 body. The whole-PR diff (merge base to reviewed head `7500e4b`) in `packages/provider-opencode/src/ser…
Out of Scope Changes check		The whole-PR diff changes two files: `packages/provider-opencode/src/server/v2/adapter.ts` (the `usageLimitResetAt` helper and the `resetAt` fallback in the usage-limit branch) and `apps/server/src/or…

Full details: Title check

Explanation

The title names the main change: OpenCode ChatGPT usage-limit failures now keep their reset time, which matches the adapter change that reads error.resets_at from the response body and passes it as resetAt. It follows conventional commit format and is specific.

Full details: Description check

Explanation

The description follows the template's sections (Problem, Change, Scope, Verification) and fills each one with specific content. It explains the failure, the 429 payload shape, the adapter fix, and the precedence with the Claude reset path. It links the issue and the prior work. It gives focused test results and states what was not checked. The template's agent attribution line is present, and the description notes that the change is server-only, so no screenshots are needed. The description is mostly complete and clear.

Full details: Linked Issues check

Explanation

Issue #26265 requires OpenCode 2 ChatGPT usage-limit failures to carry the reset time from the 429 body. The whole-PR diff (merge base to reviewed head 7500e4b) in packages/provider-opencode/src/server/v2/adapter.ts adds decodeUsageLimitBody, which decodes error.resets_at (Finite, Unix seconds) from response.body with Schema.decodeUnknownOption. usageLimitResetAt converts it to ISO with DateTime.make and DateTime.formatIso, and returns null when the body or field is absent or invalid. The usage-limit failure now sets resetAt: claudeLimit?.resetAt ?? usageLimitResetAt(response?.body), so the Claude message-based reset keeps precedence. The previous review also confirmed a ChatGPT provider.quota 429 row in OpenCode2AdapterV2.test.ts expecting resetAt: "2026-10-27T15:25:41.000Z", which matches 1793114741 Unix seconds. The head changed through a merge of main. The current adapter diff matches the earlier reviewed logic. The test diff was not re-read at this head. The UI and auto-resume paths were not re-verified in this review; the PR states they are unchanged and read the field.

Full details: Out of Scope Changes check

Explanation

The whole-PR diff changes two files: packages/provider-opencode/src/server/v2/adapter.ts (the usageLimitResetAt helper and the resetAt fallback in the usage-limit branch) and apps/server/src/orchestration-v2/Adapters/OpenCode2AdapterV2.test.ts (one ChatGPT row, and a runner that passes resetAt only when a row defines it). All changes serve issue #26265. No contract, client, orchestration, or unrelated provider changes appear in the reviewed evidence. The adapter diff at this head shows no import change, so the Option and DateTime references rely on imports already present at the merge base.

Finishing Touches

Generate unit tests (beta)

Create a new PR

Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Recent review info

Run configuration

Source mode: Auto

Repository: pingdotgg/t3code

Branch: main

File: .coderabbit.config.ts

Commit: 0d51d5b

Layers: Repository TS config

Review profile: CHILL

Plan: Advanced

Run ID: `1fd8c57e-33df-47b6-b6ec-6d18737f555f`

Commits

Reviewing files that changed from the base of the PR and between `513453f` and `7500e4b`.

Files selected for processing: 2

`apps/server/src/orchestration-v2/Adapters/OpenCode2AdapterV2.test.ts`

`packages/provider-opencode/src/server/v2/adapter.ts`

Included review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 9 remain after this review.

…usage-limit-reset

abdfattahz · 2026-10-30T06:55:06Z

Note

Claude Code (Claude Opus 5.5) is posting this comment for the PR author.

I merged current main into the branch (29c81724). The diff against main is still the same two files, +31/−2.

The earlier Agent context budget failure (claudeSystemAppendBytes: 5135 -> 5258) came from the PR being 254 commits behind. main had shrunk agentContextBudget.json since this branch was created, and this PR doesn't touch agent context. On the new head, Agent Context Budget, CI, Mobile Fingerprint, PR Vouch and PR Size all pass, and the branch merges cleanly.

The pr:gate-failed label seems to be left over from that run. Could a maintainer clear it? The bug report is #26265.

…usage-limit-reset # Conflicts: # apps/server/src/orchestration-v2/Adapters/OpenCode2AdapterV2.test.ts # packages/provider-opencode/src/server/v2/adapter.ts

…usage-limit-reset

…usage-limit-reset # Conflicts: # packages/provider-opencode/src/server/v2/adapter.ts

AI-assisted; verified with the tests and tools listed above.

…usage-limit-reset

juliusmarminge · 2026-11-12T23:58:24Z

The automated pipeline stopped on this pull request and will not merge it:

the fix is written and reviewed, but proving it needs something no worker has:

Permanent blocker: verification requires OpenCode 2.x connected through first-party OpenAI OAuth to a ChatGPT subscription with an exhausted usage window; first-party ChatGPT OAuth usage, limit, and renewal flows are unavailable on every VM. This prevents observing reset-time retention, Resume at reset, Snooze until reset, and automatic recovery on both commits. Replay cannot substitute because the scenario runner excludes provider-specific behavior and usage-limit stops.

It stays open for a person to finish or close.

github-actions Bot added vouch:unvouched Author is not yet trusted in the VOUCHED list. size:S 10-29 changed lines (additions + deletions). labels Oct 28, 2026

macroscopeapp Bot approved these changes Oct 28, 2026

View reviewed changes

abdfattahz mentioned this pull request Oct 28, 2026

[Bug]: OpenCode ChatGPT usage-limit failures drop the reset time, so auto-resume never arms #26265

Open

2 tasks done

juliusmarminge added bugfix Fix PR opened by an issue lead; enters the PR loop pr:gate-failed A land gate failed labels Oct 28, 2026

Merge remote-tracking branch 'origin/main' into fix/opencode-chatgpt-…

29c8172

…usage-limit-reset

This was referenced Oct 31, 2026

fix(server): limited threads through CLIProxyAPI resume when the hub refills #27214

Closed

fix(opencode): show usage-limit warnings while OpenCode 2 retries #28375

Open

unsync mentioned this pull request Nov 2, 2026

[Bug]: Claude via OpenCode loses usage-limit classification and reset time #29289

Closed

2 tasks done

abdfattahz added 2 commits November 3, 2026 09:44

Merge remote-tracking branch 'origin/main' into fix/opencode-chatgpt-…

d4c9def

…usage-limit-reset # Conflicts: # apps/server/src/orchestration-v2/Adapters/OpenCode2AdapterV2.test.ts # packages/provider-opencode/src/server/v2/adapter.ts

Merge remote-tracking branch 'origin/main' into fix/opencode-chatgpt-…

513453f

…usage-limit-reset

This was referenced Nov 4, 2026

OpenCode free-tier usage limit shows no reset time in T3 Code #31088

Open

fix(opencode): free-tier usage limits show when they reset #31089

Open

coderabbitai Bot mentioned this pull request Nov 10, 2026

fix(provider-pi): Pi usage-limit failures now arm usage-limit recovery #33283

Open

juliusmarminge added 3 commits November 12, 2026 21:13

Merge remote-tracking branch 'origin/main' into fix/opencode-chatgpt-…

0abb9a1

…usage-limit-reset # Conflicts: # packages/provider-opencode/src/server/v2/adapter.ts

fix(server): drop duplicate Option import after merging main

7500e4b

AI-assisted; verified with the tests and tools listed above.

Merge remote-tracking branch 'origin/main' into fix/opencode-chatgpt-…

cc57970

…usage-limit-reset

Navigation Menu

Repository navigation

fix(server): OpenCode ChatGPT usage limits keep their reset time - #26264

fix(server): OpenCode ChatGPT usage limits keep their reset time#26264
abdfattahz wants to merge 7 commits into
pingdotgg:mainfrom
abdfattahz:fix/opencode-chatgpt-usage-limit-reset

abdfattahz commented Oct 28, 2026 •

edited by juliusmarminge

Loading

Uh oh!

chatgpt-codex-connector Bot commented Oct 28, 2026 •

edited

Loading

Uh oh!

macroscopeapp Bot commented Oct 28, 2026

Uh oh!

coderabbitai Bot commented Oct 28, 2026 •

edited

Loading

Reviews paused

Uh oh!

abdfattahz commented Oct 30, 2026

Uh oh!

juliusmarminge commented Nov 12, 2026

Uh oh!

This branch has not been deployed

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

abdfattahz commented Oct 28, 2026 • edited by juliusmarminge Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Problem

Change

Scope and approval

Verification

Uh oh!

chatgpt-codex-connector Bot commented Oct 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codex Review Summary

Uh oh!

macroscopeapp Bot commented Oct 28, 2026

Approvability

Uh oh!

coderabbitai Bot commented Oct 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reviews paused

Uh oh!

abdfattahz commented Oct 30, 2026

Uh oh!

juliusmarminge commented Nov 12, 2026

Uh oh!

This branch has not been deployed

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

abdfattahz commented Oct 28, 2026 •

edited by juliusmarminge

Loading

chatgpt-codex-connector Bot commented Oct 28, 2026 •

edited

Loading

coderabbitai Bot commented Oct 28, 2026 •

edited

Loading