mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-17 02:15:31 +02:00
fix(evals): absorb codex/gemini CLI drift; external-service tests go periodic-tier
- codex exec gains --skip-git-repo-check: newer CLIs refuse exec in an untrusted non-git dir (our temp skill dirs) — empirically verified. - gemini: --skip-trust was removed in gemini-cli 0.34 (argv parse error); dropped from the session runner and the benchmark adapter. A present- but-unusable CLI (deprecated individual code-assist auth path) now classifies as SKIP, not a false adapter failure; the benchmark live smoke skips on auth/rate_limit error codes (environmental) while still failing on timeout/unknown (the drift classes it exists to catch). - codex-e2e, gemini-e2e, and benchmark-providers gain the canonical whole-file EVALS_TIER === 'periodic' guard per CLAUDE.md tiering rule 3 (external service -> periodic) — the sharded gate runner now excludes all three (gate: 45 -> 42 shards). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Fable 5
parent
990d54a9e4
commit
bd11416d80
@@ -103,10 +103,10 @@ export function resultFromGeminiStream(
|
||||
* Headless flags always passed:
|
||||
* --output-format stream-json — NDJSON events (message/tool_use/result)
|
||||
* --yolo — auto-approve tools (non-interactive)
|
||||
* --skip-trust — trust cwd for this session; required when
|
||||
* workdir is a temp/untrusted folder (benchmarks
|
||||
* use mkdtemp). Without it headless gemini exits
|
||||
* before calling the model.
|
||||
*
|
||||
* --skip-trust is gone: gemini-cli 0.34 removed the flag ("Unknown arguments:
|
||||
* skip-trust") — folder trust is settings-driven now and headless runs no
|
||||
* longer need a flag for temp workdirs.
|
||||
*/
|
||||
export class GeminiAdapter implements ProviderAdapter {
|
||||
readonly name = 'gemini';
|
||||
@@ -136,10 +136,9 @@ export class GeminiAdapter implements ProviderAdapter {
|
||||
async run(opts: RunOpts): Promise<RunResult> {
|
||||
const start = Date.now();
|
||||
// Default to --yolo (non-interactive) and stream-json output so we can parse
|
||||
// tokens + tool calls. --skip-trust is required for headless/temp workdirs
|
||||
// (gemini CLI otherwise exits: "not running in a trusted directory").
|
||||
// Callers can override via extraArgs.
|
||||
const args = ['-p', opts.prompt, '--output-format', 'stream-json', '--yolo', '--skip-trust'];
|
||||
// tokens + tool calls. Callers can override via extraArgs. (--skip-trust was
|
||||
// removed in gemini-cli 0.34; passing it errors at argv parse.)
|
||||
const args = ['-p', opts.prompt, '--output-format', 'stream-json', '--yolo'];
|
||||
if (opts.model) args.push('--model', opts.model);
|
||||
if (opts.extraArgs) args.push(...opts.extraArgs);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user