Skip to content

Localize Codex session cost estimates in Korean - #3034

Merged
steipete merged 1 commit into
steipete:mainfrom
Yoonkeee:agent/localize-korean-session-cost-estimates
Aug 18, 2026
Merged

Localize Codex session cost estimates in Korean#3034
steipete merged 1 commit into
steipete:mainfrom
Yoonkeee:agent/localize-korean-session-cost-estimates

Conversation

@Yoonkeee

@Yoonkeee Yoonkeee commented Aug 18, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Localize the Codex "Local session cost estimates" title and description in Korean.
  • Add a regression test that resolves the actual provider toggle through the Korean localization bundle.

Scope

  • Korean only.
  • No provider behavior or other locale changes.

Validation

  • swift test --filter CodexLocalSessionCostSettingsTests
  • make check
  • make test (891 selections, 75 groups)
  • Fresh debug app bundle with Korean selected and Keychain access disabled
  • Two independent visual QA passes

Screenshot

Korean localization for Local session cost estimates

References

@clawsweeper

clawsweeper Bot commented Aug 18, 2026

Copy link
Copy Markdown

🦞👀
ClawSweeper picked this up.

Pull request received. I will update this pull request when review starts.

@clawsweeper clawsweeper Bot added P3 Low-risk cleanup, docs, polish, ergonomics, or speculative feature. rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels Aug 18, 2026
@clawsweeper

clawsweeper Bot commented Aug 18, 2026

Copy link
Copy Markdown

Codex review: needs maintainer review before merge. Reviewed August 17, 2026, 11:53 PM ET / August 18, 2026, 03:53 UTC.

ClawSweeper review

What this changes

Adds Korean translations for the Codex local-session cost toggle and its explanatory text, with a regression test that resolves both through the Korean localization bundle.

Merge readiness

⚠️ Ready for maintainer review - 1 item remains

The patch is correctly scoped, has direct Korean-bundle regression coverage, and its screenshot shows the localized toggle and explanatory copy in the actual settings UI. It remains appropriate for ordinary maintainer review.

Priority: P3
Reviewed head: b7b2472efa2d691978b32aa9f16341f9c1b0d22e

Review scores

Measure Result What it means
Overall readiness 🐚 platinum hermit (4/6) A small, well-contained localization patch with direct UI proof and focused production-path coverage.
Proof confidence 🐚 platinum hermit (4/6) ✨ media proof bonus Sufficient (screenshot): A prepared after-fix screenshot directly shows the Korean title and explanatory copy in the Codex settings screen.
Patch quality 🐚 platinum hermit (4/6) No actionable review findings were identified.

Verification

Check Result Evidence
Real behavior Verified Sufficient (screenshot): A prepared after-fix screenshot directly shows the Korean title and explanatory copy in the Codex settings screen.
Evidence reviewed 6 items Existing settings contract: Current main constructs the provider-specific local-session-cost toggle from the exact English title and subtitle keys this PR translates.
Focused branch diff: The branch changes only two Korean resource entries and adds one focused Korean localization test.
Regression coverage: The test locates the real Codex toggle and asserts both title and multiline subtitle through L(..., language: "ko").
Findings None None.
Security None None.

How this fits together

Codex provider settings construct the local-session cost toggle from English source keys. The localization resolver selects the Korean resource bundle and supplies the translated title and subtitle to the settings screen.

flowchart LR
A[Codex settings descriptor] --> B[Source text keys]
B --> C[Localization resolver]
C --> D[Korean strings bundle]
D --> E[Codex settings screen]
Loading

Before merge

  • Complete next step (P2) - No mechanical repair is indicated; the remaining step is ordinary maintainer review.
Agent review details

Security

None.

Review metrics

Metric Value Why it matters
Localized setting coverage 2 Korean resource entries, 1 regression test, 2 files affected The narrow diff translates the complete toggle copy and verifies both rendered strings through the production localization path.

Technical review

Best possible solution:

Keep the existing English source keys and ship these two Korean bundle entries with their direct bundle-level regression test.

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

Not applicable: this PR supplies missing Korean copy rather than repairing a reported runtime failure; the submitted screenshot directly shows the after-change settings UI.

Is this the best way to solve the issue?

Yes. Adding the two missing Korean bundle keys and testing resolution through the actual Codex toggle follows the established localization architecture without changing provider behavior.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 8c113bb03221.

Labels

Label justifications:

  • P3: This is a low-risk, focused localization improvement with no provider-behavior change.
  • 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 (screenshot): A prepared after-fix screenshot directly shows the Korean title and explanatory copy in the Codex settings screen.
  • proof: sufficient: Contributor real behavior proof is sufficient. A prepared after-fix screenshot directly shows the Korean title and explanatory copy in the Codex settings screen.
  • proof: 📸 screenshot: Contributor real behavior proof includes screenshot evidence. A prepared after-fix screenshot directly shows the Korean title and explanatory copy in the Codex settings screen.

Evidence

What I checked:

Likely related people:

  • wicolian: Authored merged PR Add local session cost ledger #2172, which introduced the local Codex session-cost ledger and its settings surface. (role: introduced the adjacent feature; confidence: high; commits: 63215da42575; files: Sources/CodexBar/Providers/Codex/CodexProviderImplementation.swift, Tests/CodexBarTests/CodexLocalSessionCostSettingsTests.swift)

Rating scale

Score Internal tier Crab rank Meaning
6/6 S 🦀 challenger crab Exceptional readiness
5/6 A 🦞 diamond lobster Very strong readiness
4/6 B 🐚 platinum hermit Good normal PR; ordinary maintainer review
3/6 C 🦐 gold shrimp Useful, but confidence is limited
2/6 D 🦪 silver shellfish Proof or implementation needs work
1/6 F 🧂 unranked krab Not merge-ready
N/A NA 🌊 off-meta tidepool Rating does not apply

Overall follows the weaker of proof and patch quality.
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.

Workflow

  • 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.

History

Review history (2 earlier review cycles)
  • reviewed 2026-08-18T03:27:23.364Z sha b7b2472 :: needs real behavior proof before merge. :: none
  • reviewed 2026-08-18T03:32:49.400Z sha b7b2472 :: needs maintainer review before merge. :: none

@clawsweeper clawsweeper Bot added proof: 📸 screenshot Contributor real behavior proof includes screenshot evidence. proof: sufficient Contributor real behavior proof is sufficient. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. and removed rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels Aug 18, 2026
@Yoonkeee
Yoonkeee marked this pull request as ready for review August 18, 2026 03:50
@steipete
steipete merged commit 39427c1 into steipete:main Aug 18, 2026
1 check passed
steipete added a commit that referenced this pull request Aug 18, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

P3 Low-risk cleanup, docs, polish, ergonomics, or speculative feature. proof: 📸 screenshot Contributor real behavior proof includes screenshot evidence. proof: sufficient Contributor real behavior proof is sufficient. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants