golem15/msd-core
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(#774): emit service_tier/model_verbosity in Codex agent TOML + agents/openai.yaml skill chip (#828)

Browse Source 
* feat(#774): emit service_tier/model_verbosity in Codex agent TOML + agents/openai.yaml skill chip

- Add service_tier = "flex" and model_verbosity = "low" to the Codex
  ConfigProfile TOML for light-tier agents (gsd-research-synthesizer,
  gsd-codebase-mapper, gsd-plan-checker, and 8 others identified via
  AGENT_DEFAULT_TIERS). Field names/values verified against Codex schema
  (profile_toml.rs / config_types.rs Verbosity enum). Non-light agents
  are unaffected.

- Add generateCodexSkillMetadataYaml() and writeCodexSkillMetadataFiles():
  after installRuntimeArtifacts, iterate every gsd-* skill directory,
  read the short-description already emitted in the SKILL.md frontmatter
  by convertClaudeCommandToCodexSkill, and write agents/openai.yaml with
  interface.display_name and interface.short_description for the Codex
  TUI skill picker chip.
  - yamlQuote (JSON.stringify) handles all YAML-unsafe chars.
  - User-owned gsd-dev-preferences dir is never overwritten.
  - Errors per-skill are swallowed so a bad SKILL.md can't abort install.
  - agents/openai.yaml is covered by the snapshot/rollback system and
    manifest hash (writeManifest hashes skill dirs recursively).
  - Uninstall symmetry: _removeGsdEntries removes whole gsd-* dirs.

- 21 new tests in codex-config.test.cjs covering service_tier/verbosity
  TOML emission, YAML generation (round-trip via js-yaml), and
  writeCodexSkillMetadataFiles including an e2e integration test.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* fix(#774): correct docs-lint coverage — proper changeset format + USER-GUIDE entry

Rewrite the changeset fragment from old @opengsd/gsd-core:patch format to the
required type:/pr: schema so the docs-lint parser can consume it.  Add a new
"Codex skill picker and agent scheduling (#774)" section to docs/USER-GUIDE.md
describing the flex-tier scheduling and /skills TUI chip enrichments — both are
user-visible and belong in docs rather than behind a docs-exempt marker.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-06-07 18:56:25 -04:00
committed by GitHub
parent dc7f1557c6
commit 19280510fe
4 changed files with 433 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/USER-GUIDE.md
View File

@@ -688,6 +688,16 @@ To assign different models on a non-Claude runtime:
}
```
#### Codex skill picker and agent scheduling (#774)
GSD enriches each Codex install with two additional artifacts:
- **Skill TUI chip** — each installed `gsd-*` skill directory contains an `agents/openai.yaml` file that populates the Codex `/skills` picker with a human-readable display name and a short description, so you can browse and invoke GSD skills from the Codex TUI without typing the full skill name.
- **Flex-tier scheduling** — light-tier agents (haiku-equivalent) emit `service_tier = "flex"` and `model_verbosity = "low"` in their agent TOML. The Codex scheduler routes these agents to the flex tier (lower cost, background processing) and suppresses verbose token output.
Both enrichments are written automatically at install time and require no manual configuration. Requires Codex CLI ≥ 0.130.0.
#### Switching from Claude to Codex with one config change (#2517)
```json