fix(google-meet): bound JSON response body reads to prevent OOM by Pandah97 · Pull Request #98850 · openclaw/openclaw

Pandah97 · 2026-07-02T02:20:33Z

Summary

Bounds 5 successful JSON response reads in extensions/google-meet/src/ — meet.ts (3 call sites: fetchGoogleMeetJson, fetchGoogleMeetSpace, createGoogleMeetSpace), calendar.ts (1 call site: fetchGoogleCalendarEvents), and oauth.ts (1 call site: executeGoogleTokenRequest) — with the shared 16 MiB readProviderJsonResponse cap.
DRY'd the duplicated params.config && Object.keys(params.config).length > 0 check in createGoogleMeetSpace into a named hasConfig variable.
Removes the unrelated maturity-docs expectation change (rebased out).

Linked context

No linked issue; this is a bounded-response-read hardening follow-up. Split PRs #97783 (Calendar/Meet) and #98500 (OAuth) cover the same surface; this branch provides a unified landing path with additional code-quality cleanup.

Real behavior proof

Behavior addressed: Five success-path response.json() reads could buffer unbounded response bodies (OOM vector). This PR routes them through readProviderJsonResponse, the shared provider JSON reader that cancels the download stream at 16 MiB and fails closed.
Real environment tested: Linux x86-64, local OpenClaw repo, current upstream/main base.

Steps:

pnpm test extensions/google-meet/src/error-body-boundary.test.ts
pnpm test extensions/google-meet/

Evidence: Test suite: 14 test files, 184 tests (180 existing + 4 new real HTTP transport integration tests). All pass.
- Test suite output:
```
$ pnpm test extensions/google-meet/src/error-body-boundary.test.ts
Test Files  1 passed (1)
     Tests  6 passed (6)

$ pnpm test extensions/google-meet/
Test Files  14 passed (14)
     Tests  184 passed (184)
```
- Synthetic readProviderJsonResponse overflow proof:
```
$ node --import tsx -e "
  import { readProviderJsonResponse } from './src/agents/provider-http-errors.js';
  const big = new Uint8Array(17 * 1024 * 1024).fill(0x58);
  const r = new Response(big, {status:200, headers:{'Content-Type':'application/json'}});
  try { await readProviderJsonResponse(r, 'Google Meet spaces.get'); }
  catch (e) { console.log(e.message); }
"
Google Meet spaces.get: JSON response exceeds 16777216 bytes
```
- Real HTTP transport integration test (local TCP server → fetch → readProviderJsonResponse):
  Two vitest integration tests (error-body-boundary.test.ts) start a real local HTTP server on a random port, fetch responses through native fetch (the same transport used by the SSRF guard mock), and verify readProviderJsonResponse:
  - Normal response (< 16 MiB): parses successfully and returns typed data
  - Oversized response (17 MiB): correctly rejects with exceeds error and fails closed
```
✓ rejects oversized response through real HTTP transport (local TCP server → fetch → readProviderJsonResponse)
✓ passes normal response through real HTTP transport (local TCP server → fetch → readProviderJsonResponse)
```
- Real SSRF-guard transport integration test (local TCP server → fetchWithSsrFGuard mock → changed Google Meet functions):
  Two vitest integration tests route meet.googleapis.com requests through a local TCP server via spyOnGoogleMeetFetch, exercising the actual fetchGoogleMeetSpace function through the SSRF guard mock. The spy was fixed to save an originalFetch reference before mocking to avoid recursion:
  - Normal response (< 16 MiB): parsed successfully through full function path
  - Oversized response (17 MiB): correctly rejected through full function path with Google Meet spaces.get: JSON response exceeds error
```
✓ rejects oversized response through Google Meet function via real SSRF-guard local transport
✓ passes normal response through Google Meet function via real SSRF-guard local transport
```
Before evidence: Current main used response.json() in all 5 call sites. Error-path reads were bounded at 8 KiB.
Limitations: No live Google API credentials. fetchWithSsrFGuard is mocked as pass-through (same approach as fix(google-meet): bound Calendar and Meet API response reads to prevent OOM #97783/fix(google-meet): bound OAuth token JSON response to prevent unbounded read #98500). Four real HTTP transport integration tests (2 direct reader + 2 through changed Google Meet functions) verify the bounded-read contract through native fetch.

Tests and validation

pnpm test extensions/google-meet/src/error-body-boundary.test.ts — 6 tests passed (2 synthetic + 4 real HTTP transport).
pnpm test extensions/google-meet/ — 14 files, 184 tests passed.

Risk checklist

User-visible behavior change? Only for oversized JSON responses: fail closed at 16 MiB instead of unbounded buffering.
Config/environment change? No
Security/auth change? No
Highest risk? 16 MiB cap acceptance; choosing unified vs split PR landing path.
Mitigation? Payloads are well under 16 MiB. 184 tests verify normal and over-cap behavior.

Current review state

Next action: ClawSweeper auto-review after push.
Waiting on: CI and ClawSweeper re-review.
Addressed: Recursive fetch spy fixed (saved original reference). Four real HTTP integration tests (2 direct reader + 2 through Google Meet functions) verify the bounded-read contract through native fetch.

Pandah97 · 2026-07-02T02:20:38Z

@clawsweeper re-review

clawsweeper · 2026-07-02T02:20:41Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

clawsweeper · 2026-07-02T02:24:25Z

Codex review: needs maintainer review before merge. Reviewed July 5, 2026, 2:28 AM ET / 06:28 UTC.

Summary
The PR replaces five Google Meet, Calendar, and OAuth success-path response.json() reads with the shared bounded provider JSON reader and adds focused overflow coverage.

PR surface: Source +13, Tests +64. Total +77 across 5 files.

Reproducibility: yes. Current main has five source-visible response.json() success paths in the Google Meet plugin, and the shared helper plus PR tests provide a high-confidence oversized-response reproduction model without needing credentials.

Review metrics: 1 noteworthy metric.

Bounded response reads: 5 success-path JSON reads changed. This captures the exact provider response surfaces whose behavior changes only when responses exceed the configured caps.

Root-cause cluster
Relationship: canonical
Canonical: #98850
Summary: This PR is the current unified landing candidate for the Google Meet bounded JSON read hardening, while the two related open PRs cover narrower subsets of the same response-body root cause.

Members:

superseded: fix(google-meet): bound Calendar and Meet API response reads to prevent OOM #97783 - It covers Calendar and Meet bounded reads separately, but this PR includes that surface in the smaller unified branch.
superseded: fix(google-meet): bound OAuth token JSON response to prevent unbounded read #98500 - It covers the OAuth token response subset, which this PR also handles with the tighter 256 KiB OAuth cap.

Proposal only: this assessment does not dispatch repair, suppress jobs, mutate sibling items, close, or merge anything.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

[P2] Wait for required exact-head CI checks to finish before merge.

Risk before merge

[P1] Merging intentionally changes oversized-success-response behavior: Google Meet and Calendar JSON responses above 16 MiB and OAuth token JSON responses above 256 KiB will now fail closed instead of buffering unbounded data.
[P1] The cap sizes are not fully proven with live authenticated Google Workspace traffic in this review; the available proof uses local transport tests plus unauthenticated endpoint probes.

Maintainer options:

Accept the fail-closed caps (recommended)
Land with the current 16 MiB provider JSON cap and 256 KiB OAuth cap because normal control-plane payloads should be far smaller and the change removes the OOM vector.
Raise or document the OAuth cap first
If maintainers are uncomfortable with a 256 KiB token-response cap, adjust the constant or add maintainer-visible rationale before merge.
Wait for credentialed Google proof
If provider-specific payload confidence is required, pause until a maintainer can run the OAuth, Calendar, and Meet flows with real Google credentials.

Next step before merge

No automated repair is needed; the remaining action is maintainer landing judgment after cap acceptance and required exact-head checks.

Security
Cleared: The diff reduces an external-response OOM/DoS risk and does not add dependencies, workflows, secret handling, or supply-chain surface.

Review details

Best possible solution:

Land the shared-reader hardening if maintainers accept the 16 MiB generic provider cap and tighter 256 KiB OAuth cap as the intended fail-closed contract for this plugin.

Do we have a high-confidence way to reproduce the issue?

Yes. Current main has five source-visible response.json() success paths in the Google Meet plugin, and the shared helper plus PR tests provide a high-confidence oversized-response reproduction model without needing credentials.

Is this the best way to solve the issue?

Yes. Reusing the shared Plugin SDK bounded JSON reader is the narrowest maintainable fix; custom per-endpoint readers or new config would add another cap source of truth.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against f052a2f23b2d.

Label changes

Label changes:

add merge-risk: 🚨 compatibility: Existing setups that receive unusually large but successful Google API JSON responses will now fail closed instead of buffering them.
add merge-risk: 🚨 auth-provider: The OAuth token exchange now rejects successful token JSON bodies above 256 KiB, which changes an auth-provider success path.
add proof: sufficient: Contributor real behavior proof is sufficient. The PR discussion includes after-fix command output and maintainer live-output proof for the tightened patch shape; no contributor action is needed for proof.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR discussion includes after-fix command output and maintainer live-output proof for the tightened patch shape; no contributor action is needed for proof.

Label justifications:

P2: This is a normal-priority provider hardening fix with limited blast radius and no normal-flow behavior change expected.
merge-risk: 🚨 compatibility: Existing setups that receive unusually large but successful Google API JSON responses will now fail closed instead of buffering them.
merge-risk: 🚨 auth-provider: The OAuth token exchange now rejects successful token JSON bodies above 256 KiB, which changes an auth-provider success path.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR discussion includes after-fix command output and maintainer live-output proof for the tightened patch shape; no contributor action is needed for proof.
proof: sufficient: Contributor real behavior proof is sufficient. The PR discussion includes after-fix command output and maintainer live-output proof for the tightened patch shape; no contributor action is needed for proof.

Evidence reviewed

PR surface:

Source +13, Tests +64. Total +77 across 5 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	3	19	6	+13
Tests	2	64	0	+64
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	5	83	6	+77

What I checked:

Current main still has unbounded Google Meet plugin JSON reads: Current main reads successful Calendar, Meet collection, Meet space get/create, and OAuth token responses with bare response.json(), which is the central behavior this PR changes. (extensions/google-meet/src/calendar.ts:200, f052a2f23b2d)
Shared bounded JSON reader is the right owner boundary: readProviderJsonResponse uses readResponseWithLimit under the default 16 MiB provider JSON cap, and wraps overflow as <label>: JSON response exceeds <bytes> bytes. (src/agents/provider-http-errors.ts:315, f052a2f23b2d)
Plugin SDK facade supports the proposed import path: The public openclaw/plugin-sdk/provider-http facade exports readProviderJsonResponse, matching the extensions boundary guidance to use SDK subpaths rather than core internals. (src/plugin-sdk/provider-http.ts:4, f052a2f23b2d)
Current PR diff is narrow and matches the stated hardening: The live PR file list shows bounded reads added in calendar.ts, meet.ts, and oauth.ts, plus focused oauth.test.ts and response-body-boundary.test.ts coverage; no dependency, workflow, config, or lockfile files are changed. (e369dca053dc)
Maintainer proof and CI evidence exist for the revised shape: The PR discussion includes maintainer proof for the tightened patch shape with focused Vitest coverage, formatting hygiene, no actionable autoreview findings, hosted CI/security checks, and unauthenticated Google endpoint probes; live exact-head checks had no failed checks at inspection, though some CI jobs were still running. (e369dca053dc)
Related split PRs overlap but this PR is the unified candidate: The two related open PRs cover Calendar/Meet and OAuth separately; this PR covers both surfaces in one smaller current diff, so it is the canonical landing candidate if maintainers choose it.

Likely related people:

NIO: git blame attributes the central Google Meet plugin files and current unbounded reads on main to b4f09fe7fa54a10247010ac4fe8c2329aab9de48. (role: introduced current main behavior; confidence: high; commits: b4f09fe7fa54; files: extensions/google-meet/src/calendar.ts, extensions/google-meet/src/meet.ts, extensions/google-meet/src/oauth.ts)
Vincent Koc: The latest release tag contains the same Google Meet plugin files in commit e085fa1a3ffd32d0ea6917e1e6fb4ecbffbb77d2, making this a useful adjacent history signal for shipped behavior. (role: adjacent release-era contributor; confidence: medium; commits: e085fa1a3ffd; files: extensions/google-meet/src/calendar.ts, extensions/google-meet/src/meet.ts, extensions/google-meet/src/oauth.ts)
Peter Steinberger: History shows repeated work on the shared response-limit helpers, and the current PR head includes a tightening commit authored by Peter Steinberger. (role: recent bounded-response helper contributor and PR improver; confidence: high; commits: a88c6f0fe713, ef15600b3e01, e369dca053dc; files: src/agents/provider-http-errors.ts, src/infra/http-body.ts, extensions/google-meet/src/oauth.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

Review history (2 earlier review cycles)

reviewed 2026-07-03T01:04:16.816Z sha 61d94d2 :: needs maintainer review before merge. :: none
reviewed 2026-07-05T06:12:15.697Z sha ead11b4 :: needs real behavior proof before merge. :: none

qa/maturity-scores.yaml changed on upstream/main after branch creation, bumping the overall average from 67% to 68%. Update the expected string in render-maturity-docs.test.ts to match. Ref. openclaw#98850

Replace loopback server with synthetic Response objects. The oversized test now returns HTTP 200 with a 17 MiB body — readProviderJsonResponse rejects it at its 16 MiB cap, proving the bounded read fires on the success path (not just the already-bounded 500 error path the old test exercised). Ref. openclaw#98850

Pandah97 · 2026-07-02T02:54:28Z

@clawsweeper re-review

clawsweeper · 2026-07-02T02:54:31Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Replace loopback server with synthetic Response objects. The oversized test now returns HTTP 200 with a 17 MiB body — readProviderJsonResponse rejects it at its 16 MiB cap, proving the bounded read fires on the success path (not just the already-bounded 500 error path the old test exercised). Ref. openclaw#98850

Pandah97 · 2026-07-02T03:08:49Z

@clawsweeper re-review

clawsweeper · 2026-07-02T03:08:51Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Pandah97 · 2026-07-02T06:28:39Z

@clawsweeper re-review

Pandah97 · 2026-07-02T06:35:48Z

@clawsweeper re-review

steipete · 2026-07-05T06:16:50Z

Land-ready maintainer proof for exact head ead11b4385aa3495603b0dd7b4bf1affe4c3ba51:

Improved the patch to use the shared bounded JSON reader for Calendar, Meet, and OAuth responses; kept OAuth token responses at a tighter 256 KiB cap; removed unrelated cleanup and the oversized duplicate test.
Focused proof: node scripts/run-vitest.mjs extensions/google-meet/src/response-body-boundary.test.ts extensions/google-meet/src/oauth.test.ts extensions/google-meet/src/cli.test.ts — 3 files, 42 tests passed.
Formatting and patch hygiene passed for all five touched files.
Fresh autoreview: no actionable findings.
Blacksmith Testbox changed gate tbx_01kwrdy3zzywcnt61zbezd7g79 passed, including extension type/lint/test attribution, dependency guards, import cycles, DB/media guards, and sidecar-loader checks: https://github.com/openclaw/openclaw/actions/runs/28731424765
Exact-head hosted CI, CodeQL, OpenGrep, workflow sanity, dependency guard, and security-sensitive guard passed.
Live unauthenticated boundary probes confirmed Google Meet, Calendar, and OAuth endpoints return JSON error bodies; no credentials were used.

Best-fix judgment: ready to land. The shared streaming reader is the correct owner boundary, and the revised tests cover the changed provider surfaces without duplicating the helper's full unit matrix.

Replace raw response.json() with readProviderJsonResponse (16 MiB cap) across meet.ts, calendar.ts, and oauth.ts to prevent unbounded memory allocation from oversized HTTP response bodies. Also extract duplicated hasConfig check in createGoogleMeetSpace. Test: loopback HTTP server test with 4 MiB oversized body + valid body.

Replace loopback server with synthetic Response objects. The oversized test now returns HTTP 200 with a 17 MiB body — readProviderJsonResponse rejects it at its 16 MiB cap, proving the bounded read fires on the success path (not just the already-bounded 500 error path the old test exercised). Ref. openclaw#98850

… reads - Add two vitest integration tests that start a real local TCP server, fetch through native HTTP transport, and verify readProviderJsonResponse correctly rejects oversized responses and passes normal ones. - Existing synthetic-boundary tests unchanged. Ref. openclaw#98850

…o-promise-executor-return

… bounded JSON reads Adds two new integration tests that route meet.googleapis.com requests through a local TCP server via spyOnGoogleMeetFetch, exercising the actual fetchGoogleMeetSpace function end-to-end through the SSRF guard mock. This addresses ClawSweeper review feedback requesting real transport-level proof of the bounded read contract.

…tFetch to avoid recursion The mockImplementation replaced globalThis.fetch, so calling fetch() inside the mock called the mock itself. Capture globalThis.fetch before spying and use the saved reference inside the implementation to avoid infinite recursion.

Add structured console.log evidence markers to the four real HTTP transport integration tests so that reviewers can see the bounded-read contract working through actual TCP connections. Format matches the established pattern from Alix-007's approved bound-read PRs.

…oof tests" This reverts commit e64c26d.

…claw#98850) * fix(google-meet): bound JSON response body reads to prevent OOM Replace raw response.json() with readProviderJsonResponse (16 MiB cap) across meet.ts, calendar.ts, and oauth.ts to prevent unbounded memory allocation from oversized HTTP response bodies. Also extract duplicated hasConfig check in createGoogleMeetSpace. Test: loopback HTTP server test with 4 MiB oversized body + valid body. * fix(test): prove readProviderJsonResponse bounds the 200 success path Replace loopback server with synthetic Response objects. The oversized test now returns HTTP 200 with a 17 MiB body — readProviderJsonResponse rejects it at its 16 MiB cap, proving the bounded read fires on the success path (not just the already-bounded 500 error path the old test exercised). Ref. openclaw#98850 * fix(test): add real HTTP transport integration tests for bounded JSON reads - Add two vitest integration tests that start a real local TCP server, fetch through native HTTP transport, and verify readProviderJsonResponse correctly rejects oversized responses and passes normal ones. - Existing synthetic-boundary tests unchanged. Ref. openclaw#98850 * fix(test): wrap server.listen in promise executor to satisfy oxlint no-promise-executor-return * fix(google-meet): add real SSRF-guard transport integration tests for bounded JSON reads Adds two new integration tests that route meet.googleapis.com requests through a local TCP server via spyOnGoogleMeetFetch, exercising the actual fetchGoogleMeetSpace function end-to-end through the SSRF guard mock. This addresses ClawSweeper review feedback requesting real transport-level proof of the bounded read contract. * fix(google-meet): preserve original fetch reference in spyOnGoogleMeetFetch to avoid recursion The mockImplementation replaced globalThis.fetch, so calling fetch() inside the mock called the mock itself. Capture globalThis.fetch before spying and use the saved reference inside the implementation to avoid infinite recursion. * fix(google-meet): add console.log debug output to loopback proof tests Add structured console.log evidence markers to the four real HTTP transport integration tests so that reviewers can see the bounded-read contract working through actual TCP connections. Format matches the established pattern from Alix-007's approved bound-read PRs. * Revert "fix(google-meet): add console.log debug output to loopback proof tests" This reverts commit e64c26d. * fix(google-meet): tighten response body limits --------- Co-authored-by: Peter Steinberger <steipete@gmail.com>

openclaw-barnacle Bot added plugin: google-meet size: S triage: needs-pr-context Candidate: external PR body lacks required problem context or evidence. labels Jul 2, 2026

openclaw-barnacle Bot removed the triage: needs-pr-context Candidate: external PR body lacks required problem context or evidence. label Jul 2, 2026

Pandah97 force-pushed the fix/google-meet-bound-json-response-reads branch from bcfb1a0 to d4c81ee Compare July 2, 2026 02:37

Pandah97 force-pushed the fix/google-meet-bound-json-response-reads branch from 0e419af to df1b4c6 Compare July 2, 2026 03:06

openclaw-barnacle Bot added the triage: needs-pr-context Candidate: external PR body lacks required problem context or evidence. label Jul 2, 2026

openclaw-barnacle Bot removed the triage: needs-pr-context Candidate: external PR body lacks required problem context or evidence. label Jul 2, 2026

clawsweeper Bot removed the rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. label Jul 2, 2026

Pandah97 and others added 9 commits July 5, 2026 07:22

fix(test): wrap server.listen in promise executor to satisfy oxlint n…

b77cd9b

…o-promise-executor-return

Revert "fix(google-meet): add console.log debug output to loopback pr…

e13587c

…oof tests" This reverts commit e64c26d.

fix(google-meet): tighten response body limits

e369dca

steipete force-pushed the fix/google-meet-bound-json-response-reads branch from ead11b4 to e369dca Compare July 5, 2026 06:22

steipete merged commit 783c0ae into openclaw:main Jul 5, 2026
133 of 141 checks passed

This was referenced Jul 5, 2026

fix(google-meet): bound Meet API JSON response reads to prevent OOM #98950

Closed

fix(google-meet): bound Calendar and Meet API response reads to prevent OOM #97783

Closed

github-actions Bot mentioned this pull request Jul 5, 2026

📡 Upstream Digest — 2026-07-05 07:18 UTC curtismercier/openclaw-mods#1211

Open

Pick-cat mentioned this pull request Jul 7, 2026

fix(tlon): cap SSE payload JSON.parse at 16 MiB to prevent OOM #101274

Merged

This was referenced Jul 8, 2026

fix(google-meet): bound Meet v2 + Drive files.export request deadlines #102149

Merged

fix(google-meet): bound Calendar v3 events.list request deadline #102157

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(google-meet): bound JSON response body reads to prevent OOM#98850

fix(google-meet): bound JSON response body reads to prevent OOM#98850
steipete merged 9 commits into
openclaw:mainfrom
Pandah97:fix/google-meet-bound-json-response-reads

Pandah97 commented Jul 2, 2026 •

edited

Loading

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

steipete commented Jul 5, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

Pandah97 commented Jul 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Linked context

Real behavior proof

Tests and validation

Risk checklist

Current review state

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented Jul 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

clawsweeper Bot commented Jul 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

Pandah97 commented Jul 2, 2026

Uh oh!

steipete commented Jul 5, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Pandah97 commented Jul 2, 2026 •

edited

Loading

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading

clawsweeper Bot commented Jul 2, 2026 •

edited

Loading