Best possible solution:

Land the narrow parser compatibility shim with its focused CLI regression coverage after normal PR gates complete.

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

Yes. The linked issue gives a concrete failing command, current main passes raw args into Kong, and docs advertise the affected space-separated long-flag form; I did not run the CLI in this read-only review.

Is this the best way to solve the issue?

Yes. Normalizing only known numeric long flags before Kong parsing is a narrow compatibility shim that preserves the documented flag contract without broad parser replacement.

AGENTS.md: not found in the target repository.

Codex review notes: model internal, reasoning high; reviewed against b3fba0220115.

Label changes:

• add P2: The PR fixes a documented CLI parsing bug with limited blast radius and an existing equals-form workaround.
• add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
• add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: This is a ClawSweeper bot autofix PR, so the external-contributor real behavior proof gate does not apply.

Label justifications:

• P2: The PR fixes a documented CLI parsing bug with limited blast radius and an existing equals-form workaround.
• rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: This is a ClawSweeper bot autofix PR, so the external-contributor real behavior proof gate does not apply.

What I checked:

• Current parser path: Current main constructs the Kong parser and passes the original args directly into parseWithExit, so main has not already implemented this normalization. (internal/cli/run.go:54, b3fba0220115)
• Documented flag contract: README documents that long flags accept either space-separated or equals form, which makes the linked negative longitude report a docs-backed CLI contract bug rather than a new feature. (README.md:93, b3fba0220115)
• Patch scope: The PR adds internal/cli/args.go, internal/cli/args_test.go, updates internal/cli/run.go to normalize args before parsing, and adds mock-server regressions in internal/cli/cli_test.go. (internal/cli/run.go:51, 3ffec0431ead)
• GitHub PR state: GitHub reports the PR as mergeable/CLEAN with successful test and audit check runs, and it closes the linked issue. (3ffec0431ead)
• Target policy check: No AGENTS.md was found inside the target goplaces repository. (b3fba0220115)

Likely related people:

• Peter Steinberger: Current-main blame ties the CLI parser setup, numeric coordinate flag definitions, and latest release-tagged CLI behavior to the same commit. (role: introduced behavior and recent area contributor; confidence: high; commits: cb837848f1bb; files: internal/cli/run.go, internal/cli/root.go)

• 🦀 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.

• 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.