repo-harness-gptpro

# repo-harness-gptpro Use this command when the user wants local Codex to consult GPT Pro through the repo-harness ChatGPT Web browser provider. Oracle is the default main path; native is deprecated and kept only for diagnostics. Use GPT Pro language with the user. Treat the `browser-*` command names as implementation details: | User-facing action | Engine command | | --- | --- | | `gptpro consult` | `repo-harness chatgpt browser-consult` | | `gptpro continue` | `repo-harness chatgpt browser-followup` | | `gptpro read` | `repo-harness chatgpt browser-session` | | `gptpro open` | `repo-harness chatgpt browser-open` | | `gptpro list` | `repo-harness chatgpt browser-list` | ## Protocol 1. Confirm the target repo path with `git rev-parse --show-toplevel` or the user's explicit path. Preserve unrelated dirty worktree state. 2. Verify GPT Pro browser readiness before any real consult: `repo-harness chatgpt browser-doctor --repo <repo> --provider oracle --json` 3. If Oracle is missing, install or point to a pinned `oracle` CLI (`--oracle-bin` or `REPO_HARNESS_ORACLE_BIN`) before a real consult. Do not silently fall back to another provider. 4. If Oracle doctor reports `ORACLE_INCOMPATIBLE`, stop and report the missing capabilities from `oracle.missingCapabilities`; do not run a consult that would pass unsupported Oracle flags. 5. If a repo-local ChatGPT profile binding exists, keep it in the Oracle path. The real consult should use the selected profile cookie DB (for example...