mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-09 22:48:57 +02:00
Garry TanandClaude Fable 5
a9ca914f43
codex >=0.144 deprecates the legacy --enable-based web_search_cached
spelling (web search is on by default; --enable <FEATURE> now means
-c features.<name>=true, verified against codex 0.147.0's exec --help).
Every gstack codex invocation now passes -c 'web_search="cached"' instead.
The flag previously lived inline at 19 raw sites. Per ENG-OV11a the 10
template-inline sites (autoplan/SKILL.md.tmpl x4, codex/SKILL.md.tmpl x6)
convert to a shared {{CODEX_WEB_SEARCH_FLAG}} token first, so ONE resolver
constant (CODEX_WEB_SEARCH_FLAG in scripts/resolvers/constants.ts) now
covers all sites: review.ts x5, design.ts x3, the token resolver in
utility.ts, and the tool-map helper comment.
codex/SKILL.md.tmpl's web-search prose guarantee is corrected: the -c form
explicitly overrides a top-level web_search config (the legacy flag yielded
to it), and native codex review disables web search regardless of
configuration, so the flag is a no-op on the default Review path.
test/codex-web-search-flag.test.ts is the safety net: repo-wide grep
tripwires assert NO rendered SKILL.md/section/golden and NO source file
carries the deprecated spelling, and that the token resolves in rendered
output.
Fixes #2525
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
83 lines
2.3 KiB
TypeScript
83 lines
2.3 KiB
TypeScript
/**
|
|
* Tool compatibility map across provider CLIs.
|
|
*
|
|
* Not all provider CLIs expose equivalent tools. A benchmark that uses Edit, Glob,
|
|
* or Grep won't run cleanly on CLIs that don't have those. The map answers:
|
|
* "which tools does each provider's CLI expose by default?"
|
|
*
|
|
* When a benchmark is scoped to a tool a provider lacks, the harness records
|
|
* `unsupported_tool` in the result and continues with the other providers.
|
|
*
|
|
* Source-of-truth references:
|
|
* - Claude Code: https://code.claude.com/docs/en/tools
|
|
* - Codex CLI: `codex exec --help` tool listing
|
|
* - Gemini CLI: `gemini --help` (limited tool surface as of 2026-04)
|
|
*/
|
|
|
|
export type ToolName =
|
|
| 'Read'
|
|
| 'Write'
|
|
| 'Edit'
|
|
| 'Bash'
|
|
| 'Agent'
|
|
| 'Glob'
|
|
| 'Grep'
|
|
| 'AskUserQuestion'
|
|
| 'WebSearch'
|
|
| 'WebFetch';
|
|
|
|
export const TOOL_COMPATIBILITY: Record<'claude' | 'gpt' | 'gemini', Record<ToolName, boolean>> = {
|
|
claude: {
|
|
Read: true,
|
|
Write: true,
|
|
Edit: true,
|
|
Bash: true,
|
|
Agent: true,
|
|
Glob: true,
|
|
Grep: true,
|
|
AskUserQuestion: true,
|
|
WebSearch: true,
|
|
WebFetch: true,
|
|
},
|
|
gpt: {
|
|
// Codex CLI has a narrower tool surface: it uses shell + apply_patch.
|
|
// Read/Glob/Grep-style operations happen via shell pipelines.
|
|
Read: true,
|
|
Write: false, // apply_patch handles writes; no standalone Write tool
|
|
Edit: false, // apply_patch handles edits; no standalone Edit tool
|
|
Bash: true,
|
|
Agent: false,
|
|
Glob: false,
|
|
Grep: false,
|
|
AskUserQuestion: false,
|
|
WebSearch: true, // -c 'web_search="cached"' (CODEX_WEB_SEARCH_FLAG, #2525)
|
|
WebFetch: false,
|
|
},
|
|
gemini: {
|
|
// Gemini CLI (as of 2026-04) has a limited tool surface in --yolo mode.
|
|
// Shell access depends on flags; most agentic tools are not exposed.
|
|
Read: true,
|
|
Write: false,
|
|
Edit: false,
|
|
Bash: false,
|
|
Agent: false,
|
|
Glob: false,
|
|
Grep: false,
|
|
AskUserQuestion: false,
|
|
WebSearch: true,
|
|
WebFetch: false,
|
|
},
|
|
};
|
|
|
|
/**
|
|
* Determine which tools from a required-set are missing for a given provider.
|
|
* Empty array means full compatibility.
|
|
*/
|
|
export function missingTools(
|
|
provider: 'claude' | 'gpt' | 'gemini',
|
|
requiredTools: ToolName[]
|
|
): ToolName[] {
|
|
const map = TOOL_COMPATIBILITY[provider];
|
|
return requiredTools.filter(t => !map[t]);
|
|
}
|