fix(memory): skip placeholder short-term promotions by MonkeyLeeT · Pull Request #82028 · openclaw/openclaw

MonkeyLeeT · 2026-05-15T05:24:27Z

Summary

Add a shared short-term promotion guard for markdown placeholder/skeleton snippets.
Apply it when loading the recall store, recording recall/grounded candidates, ranking, applying, and rehydrating promotion candidates.
Add regression coverage for marker-only snippets, heading-only scaffolding, normalized marker-plus-heading placeholders, stale stored placeholders, trailing-colon scaffold headings, and inline heading bullets with durable payloads, including concise and localized heading text.

Verification

node scripts/run-vitest.mjs extensions/memory-core/src/short-term-promotion.test.ts -- --runInBand
node scripts/run-vitest.mjs extensions/memory-core/src/dreaming-phases.test.ts extensions/memory-core/src/short-term-promotion.test.ts -- --runInBand
CI=true pnpm exec oxfmt --check --threads=1 extensions/memory-core/src/short-term-promotion.ts extensions/memory-core/src/short-term-promotion.test.ts
git diff --check

Real behavior proof

Behavior addressed: Short-term promotion could treat markdown placeholders like -, plain heading-only scaffolding like ## Tagesnotizen ## Entscheidungen, trailing-colon scaffold headings like ## Notes:, and previously persisted normalized marker-plus-heading snippets like - ## Entscheidungen as durable memory candidates, allowing empty daily-note scaffolding to rank and eventually append to MEMORY.md. The guard also preserves list-wrapped heading content with durable body text, including localized non-colon headings such as - ## 修复备份轮换.

Real environment tested: Local filesystem-backed OpenClaw memory workspace on macOS, using PR head 519ee06236eca61c78764f59fa1837157efb37bf. The standalone Node run created real temp files under memory/, wrote memory/.dreams/short-term-recall.json, called the production rankShortTermPromotionCandidates and applyShortTermPromotions functions from extensions/memory-core/src/short-term-promotion.ts, and checked the resulting MEMORY.md filesystem state.

Exact steps or command run after this patch: From the repo root, ran node --import tsx - with a standalone script that seeds temp workspaces with persisted short-term recall entries whose snippets are ## Tagesnotizen ## Entscheidungen, ## Notes:, - ## Entscheidungen, and - ## 修复备份轮换, then invokes production ranking and apply paths with thresholds set to zero.

Evidence after fix: Copied terminal output from that real temp-workspace run:

$ node --import tsx -
{"name":"headingOnly","snippet":"## Tagesnotizen ## Entscheidungen","ranked":0,"applied":0,"memoryExists":false,"memoryIncludesSnippet":false}
{"name":"headingWithColon","snippet":"## Notes:","ranked":0,"applied":0,"memoryExists":false,"memoryIncludesSnippet":false}
{"name":"markerHeading","snippet":"- ## Entscheidungen","ranked":0,"applied":0,"memoryExists":false,"memoryIncludesSnippet":false}
{"name":"durableLocalized","snippet":"- ## 修复备份轮换","ranked":1,"applied":1,"memoryExists":true,"memoryIncludesSnippet":true}

Observed result after fix: Heading-only scaffolding, trailing-colon scaffold headings, and normalized marker-plus-heading placeholders ranked zero candidates, applied zero promotions, and did not create MEMORY.md. The durable localized non-colon inline heading bullet - ## 修复备份轮换 ranked, applied once, created MEMORY.md, and appeared in the resulting memory file.

What was not tested: I did not run a full live dreaming cron cycle against a private real workspace; the user-reported failure shape is covered with filesystem-backed promotion fixtures and the standalone temp-workspace OpenClaw promotion run above rather than private memory contents.

clawsweeper · 2026-05-15T05:27:48Z

Codex review: needs changes before merge.

Workflow note: Future ClawSweeper reviews update this same comment in place.

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.

Summary
The PR adds a memory-core guard to reject markdown skeleton short-term promotion snippets during store normalization, candidate recording, ranking, apply/rehydration, with focused regression tests.

Reproducibility: yes. Current main has a source-level reproduction path because non-empty markdown placeholders pass the existing empty/dreaming-contamination filters into ranking/apply; I did not run tests because this review is read-only.

PR rating
Overall: 🦐 gold shrimp
Proof: 🦞 diamond lobster
Patch quality: 🦐 gold shrimp
Summary: The proof is strong and the patch is close, but the current predicate has a concrete P2 correctness gap around trailing-colon template headings.

Rank-up moves:

Fix the trailing-colon skeleton-heading case and add focused coverage.
Have a maintainer confirm the known-heading pruning contract before merge.

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.

Real behavior proof
Sufficient (terminal): The PR body includes terminal output from a real filesystem-backed temp workspace on the PR head showing placeholder candidates skipped and a durable localized heading written to MEMORY.md.

Risk before merge

The current head still permits known template headings with trailing colons, such as '## Notes:', to pass the skeleton guard and promote into MEMORY.md.
The guard intentionally prunes persisted short-term entries matching the skeleton heuristic on the next normalization/write path, so maintainers should accept that session-state behavior before merge.
The proof covers filesystem-backed ranking/apply paths, not a full private live dreaming cron cycle.

Maintainer options:

Fix trailing-colon skeleton labels (recommended)
Add colon stripping and tests for known template headings such as '## Notes:' while preserving durable headings like '## Decision: Move backups to S3'.
Accept the pruning contract after repair
After the colon hole is fixed, maintainers can merge if they agree that known empty daily-note headings should be removed from stored short-term promotion state.
Pause for memory semantics
If known-heading pruning is not the intended memory contract, pause this branch and replace it with a narrower marker-only placeholder filter.

Copy recommended automerge instruction

@clawsweeper automerge

Special instructions:
Add ':' to normalizeMarkdownSkeletonHeadingBody punctuation cleanup, add regression coverage that known skeleton headings with trailing colons such as '## Notes:' and '- ## Decisions:' are unpromotable, and keep durable headings like '## Decision: Move backups to S3' promotable.

Next step before merge
A narrow predicate and test repair can address the blocking finding; maintainers still need to accept the session-state pruning semantics before merge.

Security
Cleared: The diff only changes memory-core filtering logic and colocated tests, with no dependency, workflow, package metadata, secret-handling, or code-execution surface changes.

Review findings

[P2] Strip colons from known skeleton heading labels — extensions/memory-core/src/short-term-promotion.ts:337

Review details

Best possible solution:

Centralize the promotion guard, strip trailing colons from known skeleton labels with regression coverage, and merge only after maintainers accept pruning known template headings from persisted short-term state.

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

Yes. Current main has a source-level reproduction path because non-empty markdown placeholders pass the existing empty/dreaming-contamination filters into ranking/apply; I did not run tests because this review is read-only.

Is this the best way to solve the issue?

No, not quite. The centralized guard is the right shape, but the current predicate misses trailing-colon known skeleton headings, so a narrow normalization/test repair is needed before merge.

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes terminal output from a real filesystem-backed temp workspace on the PR head showing placeholder candidates skipped and a durable localized heading written to MEMORY.md.
add rating: 🦐 gold shrimp: Current PR rating is 🦐 gold shrimp because proof is 🦞 diamond lobster, patch quality is 🦐 gold shrimp, and The proof is strong and the patch is close, but the current predicate has a concrete P2 correctness gap around trailing-colon template headings.
add status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Sufficient (terminal): The PR body includes terminal output from a real filesystem-backed temp workspace on the PR head showing placeholder candidates skipped and a durable localized heading written to MEMORY.md.
remove rating: 🐚 platinum hermit: Current PR rating is rating: 🦐 gold shrimp, so this older rating label is no longer current.
remove status: 👀 ready for maintainer look: Current PR status label is status: ⏳ waiting on author.

Label justifications:

P2: This is a focused memory-quality bug fix with limited blast radius, but it affects durable MEMORY.md promotion behavior.
merge-risk: 🚨 session-state: The PR changes which persisted short-term recall entries survive normalization, ranking, and apply/rehydration.
rating: 🦐 gold shrimp: Current PR rating is 🦐 gold shrimp because proof is 🦞 diamond lobster, patch quality is 🦐 gold shrimp, and The proof is strong and the patch is close, but the current predicate has a concrete P2 correctness gap around trailing-colon template headings.
status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Sufficient (terminal): The PR body includes terminal output from a real filesystem-backed temp workspace on the PR head showing placeholder candidates skipped and a durable localized heading written to MEMORY.md.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes terminal output from a real filesystem-backed temp workspace on the PR head showing placeholder candidates skipped and a durable localized heading written to MEMORY.md.

Full review comments:

[P2] Strip colons from known skeleton heading labels — extensions/memory-core/src/short-term-promotion.ts:337
normalizeMarkdownSkeletonHeadingBody does not remove :, so ## Notes: normalizes to notes: and misses MARKDOWN_SKELETON_HEADING_BODIES. That leaves common daily-note template headings promotable through the new guard; include : in the punctuation cleanup and add a regression case for trailing-colon skeleton labels while preserving durable Decision: headings.
Confidence: 0.91

Overall correctness: patch is incorrect
Overall confidence: 0.89

Acceptance criteria:

node scripts/run-vitest.mjs extensions/memory-core/src/short-term-promotion.test.ts -- --runInBand
CI=true pnpm exec oxfmt --check --threads=1 extensions/memory-core/src/short-term-promotion.ts extensions/memory-core/src/short-term-promotion.test.ts
git diff --check

What I checked:

Current main promotion gate is too narrow: Current main filters empty and dreaming-contaminated snippets before recording/ranking, but has no markdown skeleton placeholder predicate, so non-empty scaffolding can enter the short-term promotion path. (extensions/memory-core/src/short-term-promotion.ts:971, c8a35c4645dc)
Current main ranks stored non-empty placeholders: The ranking loop on current main only rejects dreaming-contaminated snippets before scoring candidates, which supports the linked issue's source-level reproduction path. (extensions/memory-core/src/short-term-promotion.ts:1262, c8a35c4645dc)
PR centralizes the intended guard: The PR adds isMarkdownSkeletonSnippet/isUnpromotableShortTermSnippet and wires it into store normalization, recall and grounded recording, ranking, apply filtering, and rehydration filtering. (extensions/memory-core/src/short-term-promotion.ts:322, 545febdb1e46)
Latest head still misses trailing-colon template headings: The latest review comment correctly points out that normalizeMarkdownSkeletonHeadingBody does not strip ':'; known placeholders such as '## Notes:' normalize to 'notes:' and remain promotable. (extensions/memory-core/src/short-term-promotion.ts:337, 545febdb1e46)
Regression coverage is focused but incomplete: The PR adds tests for marker-only snippets, known heading scaffolds, normalized marker-plus-heading placeholders, and durable concise/localized headings, but not trailing-colon known skeleton labels. (extensions/memory-core/src/short-term-promotion.test.ts:1142, 545febdb1e46)
Documented promotion contract: The CLI docs say promotion re-reads the live daily note before writing to MEMORY.md, matching the PR's rehydration-side guard for stale placeholder snapshots. Public docs: docs/cli/memory.md. (docs/cli/memory.md:140, c8a35c4645dc)

Likely related people:

vignesh07: Authored the merged weighted short-term promotion flow that introduced the ranking/apply surface this PR modifies. (role: feature introducer; confidence: high; commits: 4c1022c73b39; files: extensions/memory-core/src/short-term-promotion.ts, extensions/memory-core/src/short-term-promotion.test.ts)
mbelinky: Authored merged REM preview/replay and grounded backfill changes that expanded the short-term promotion and grounded candidate paths touched here. (role: recent area contributor; confidence: high; commits: 79348f73c8b6, e8209e4cf9b8; files: extensions/memory-core/src/short-term-promotion.ts, extensions/memory-core/src/short-term-promotion.test.ts)
gumadeiras: Authored the merged dreaming self-ingestion guard, the closest existing contamination-filtering precedent in this promotion pipeline. (role: adjacent filtering contributor; confidence: medium; commits: 0c4e0d703023; files: extensions/memory-core/src/short-term-promotion.ts, extensions/memory-core/src/short-term-promotion.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against c8a35c4645dc.

MonkeyLeeT · 2026-05-15T05:53:09Z

Codex review: needs real behavior proof before merge.

Summary The PR adds a shared memory-core predicate to reject markdown placeholder short-term promotion snippets across store load, recording, ranking, relocation, apply, and rehydration paths, with focused regression tests.

Reproducibility: yes. Current main has a source-level reproduction path because non-empty markdown placeholders can pass the existing empty/dreaming-contamination filters and relocation can match structurally meaningless snippets.

Real behavior proof Needs real behavior proof before merge: Needs contributor action: add terminal/live output, a recording, or redacted logs from a real memory workspace or live promotion path; update the PR body to trigger re-review, or ask a maintainer for @clawsweeper re-review if it does not.

Next step before merge This active draft contributor PR needs contributor-supplied real behavior proof and normal PR readiness handling rather than an automated repair branch.

Security Cleared: The diff only changes memory-core filtering logic and colocated tests, with no new dependencies, workflow changes, package metadata changes, secrets handling, or code-execution surface.

Review details

Added real behavior proof

MonkeyLeeT · 2026-05-15T05:53:28Z

@hxy91819 PTAL thanks!

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4e8b549f86

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".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 6c49f02b48

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".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7f9bf5f323

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".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-22T01:40:20Z

+      if (/:\s*\S/.test(headingBody) || headingWords.length >= 4) {
+        return false;


Allow concise heading snippets to be promoted

isMarkdownSkeletonSnippet currently classifies heading lines as placeholders unless they contain a colon or at least 4 words, so concise but durable notes like ## API keys rotated or - ## VPN outage fix are treated as unpromotable. Because isUnpromotableShortTermSnippet now gates store normalization, recording, ranking, and apply paths, these legitimate short-term memories are silently dropped and never make it into MEMORY.md.

Useful? React with 👍 / 👎.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 5f3c21510a

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".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 545febdb1e

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".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-22T02:00:09Z

+
+function normalizeMarkdownSkeletonHeadingBody(raw: string): string {
+  return raw
+    .replace(/[-*+>`_[\](){}|~.,;!?]+/g, " ")


Strip trailing colons from skeleton heading labels

In normalizeMarkdownSkeletonHeadingBody, the punctuation cleanup omits :, so a placeholder heading like ## Notes: normalizes to notes: instead of notes and misses MARKDOWN_SKELETON_HEADING_BODIES; isMarkdownSkeletonSnippet then treats it as promotable content. Because this guard now gates store normalization, recording, ranking, and apply paths, common template headings with trailing colons can still be promoted into MEMORY.md, which undermines the placeholder filter this commit introduces.

Useful? React with 👍 / 👎.

openclaw-barnacle Bot added extensions: memory-core Extension: memory-core size: M triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 15, 2026

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch from c36f825 to 56ca6dc Compare May 15, 2026 05:34

MonkeyLeeT changed the title ~~[codex] fix memory placeholder short-term promotions~~ fix(memory): skip placeholder short-term promotions May 15, 2026

MonkeyLeeT marked this pull request as ready for review May 15, 2026 05:50

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch 2 times, most recently from e85b15e to 4e8b549 Compare May 15, 2026 15:18

chatgpt-codex-connector Bot reviewed May 15, 2026

View reviewed changes

Comment thread extensions/memory-core/src/short-term-promotion.ts Outdated

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch from 18d74b6 to be5a837 Compare May 16, 2026 05:16

clawsweeper Bot mentioned this pull request May 16, 2026

Memory: skip markdown placeholder snippets during short-term promotion #80582

Closed

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch 2 times, most recently from 705b245 to a7a7e7e Compare May 17, 2026 16:45

clawsweeper Bot added P2 Normal backlog priority with limited blast radius. impact:data-loss Can lose, corrupt, or silently drop user/session/config data. impact:session-state Session, memory, transcript, context, or agent state can drift or corrupt. labels May 17, 2026

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch from a7a7e7e to 8b3146c Compare May 18, 2026 15:18

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 18, 2026

MonkeyLeeT added 3 commits May 21, 2026 16:51

fix(memory): catch normalized placeholder headings

0065a88

fix(memory): allow inline heading memories

3e62bff

refactor(memory): trim placeholder guard diff

6c49f02

MonkeyLeeT force-pushed the codex/fix-memory-placeholder-promotions branch from e0788a9 to 6c49f02 Compare May 21, 2026 23:52

chatgpt-codex-connector Bot reviewed May 21, 2026

View reviewed changes

Comment thread extensions/memory-core/src/short-term-promotion.ts Outdated

fix(memory): skip heading-only skeleton snippets

a283dc5

fix(memory): allow non-colon heading memories

7f9bf5f

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

chatgpt-codex-connector Bot reviewed May 22, 2026

View reviewed changes

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

fix(memory): allow concise heading memories

5f3c215

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

chatgpt-codex-connector Bot reviewed May 22, 2026

View reviewed changes

Comment thread extensions/memory-core/src/short-term-promotion.ts Outdated

fix(memory): allow localized heading memories

545febd

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

chatgpt-codex-connector Bot reviewed May 22, 2026

View reviewed changes

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 22, 2026

fix(memory): reject colon-only scaffold headings

519ee06

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(memory): skip placeholder short-term promotions#82028

fix(memory): skip placeholder short-term promotions#82028
MonkeyLeeT wants to merge 9 commits into
openclaw:mainfrom
MonkeyLeeT:codex/fix-memory-placeholder-promotions

MonkeyLeeT commented May 15, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 15, 2026 •

edited

Loading

Uh oh!

MonkeyLeeT commented May 15, 2026

Uh oh!

MonkeyLeeT commented May 15, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 22, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

		if (/:\s*\S/.test(headingBody) \|\| headingWords.length >= 4) {
		return false;

Uh oh!

Uh oh!

Conversation

MonkeyLeeT commented May 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

clawsweeper Bot commented May 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

MonkeyLeeT commented May 15, 2026

Uh oh!

MonkeyLeeT commented May 15, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 22, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 22, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

MonkeyLeeT commented May 15, 2026 •

edited

Loading

clawsweeper Bot commented May 15, 2026 •

edited

Loading