Merge branch 'codex/simp-shared-acp-test-launcher' into codex/simp-trim-hook-snapshot-noise

# Conflicts:
#	examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl
This commit is contained in:
Tianyi Cui
2026-07-18 12:00:40 +08:00
657 changed files with 36661 additions and 7468 deletions
+41 -3
View File
@@ -25,7 +25,9 @@ const AGENT = {
// The Code Mode overlay configs (include-patched variants of cordis.yml; the
// replay swap resolves each one's sibling `*cordis.snapshot.yml`).
const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
const CODE_MODE_WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../code-mode-workspace-context.cordis.yml', import.meta.url))
const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cordis.yml', import.meta.url))
const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
@@ -51,6 +53,7 @@ const SCENARIOS: Scenario[] = [
// Its prompt and tool-schema sidecars pin the composed header.
{ name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
{ name: 'bash-spill', hasModelTurn: true, recorded: false, headerClass: 'fs', configPath: FS_CONFIG },
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
@@ -62,12 +65,36 @@ const SCENARIOS: Scenario[] = [
{ name: 'fs-read-window', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
{ name: 'fs-policy-reject', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
{ name: 'multi-turn', hasModelTurn: true, recorded: true },
// ACP exposes the adapter catalog as a session-scoped model select. This
// scenario pins the default flash request, the switch response, and the
// resulting changed request-header snapshot for pro.
{
name: 'model-switching',
hasModelTurn: true,
recorded: true,
pinsHeader: true,
expectedHeaderChanges: 1,
headerClass: 'model-switching',
},
{ name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
// Keyless, authored (like error-finish/cancel): deterministically forcing a
// LIVE model to repeat one call three times is not a stable recording, so
// the fixture scripts five identical todo_write calls and pins BOTH reminder
// tiers (gentle at 3, detailed at 5) as context/message in transcript and log.
{ name: 'repeat-tool-guard', hasModelTurn: true, recorded: false },
// Authored replay: a root AGENTS.md pins the session prefix, then a read in
// nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing
// context/message. The scenario-specific config keeps home/root discovery
// hermetic, and the resulting prefix needs its own pinned header class.
{
name: 'workspace-context',
hasModelTurn: true,
recorded: false,
overridden: true,
pinsHeader: true,
headerClass: 'workspace-context',
configPath: WORKSPACE_CONTEXT_CONFIG,
},
{ name: 'cancel', hasModelTurn: true, recorded: false, overridden: true },
{ name: 'subagent-spawn', hasModelTurn: true, recorded: true },
{ name: 'subagent-multi', hasModelTurn: true, recorded: true },
@@ -112,10 +139,21 @@ const SCENARIOS: Scenario[] = [
// tools:sdk section rides in the prompt, and the program's tool calls land as
// tool/code-dispatch events. Each overlay composes and pins its own header class.
{ name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG },
// A nested fs dispatch inside run_code discovers workspace instructions. The
// context/message must follow the outer result while retaining workspace
// provenance, which proves Code Mode carries deferred tool context end to end.
{
name: 'code-mode-workspace-context',
hasModelTurn: true,
recorded: true,
pinsHeader: true,
headerClass: 'code-workspace-context',
configPath: CODE_MODE_WORKSPACE_CONTEXT_CONFIG,
},
{ name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG },
// The default tree owns the single Permissions select. Snapshot mode starts
// in danger-full-access so established fixtures stay runner-independent;
// these policy scenarios switch to workspace-write in their input scripts.
// The default tree also owns the Permissions select. Snapshot mode starts in
// danger-full-access so established fixtures stay runner-independent; these
// policy scenarios switch to workspace-write in their input scripts.
// Real-kernel confinement remains in escalation.e2e.ts and the sandbox
// packages' e2e suites.
{ name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' },