@lesliechan721/agent-skill-eval 0.1.0-beta.8 → 0.1.0-beta.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/bin.js +149 -39
- package/dist/bin.js.map +1 -1
- package/dist/codex-eval-app-server.d.ts +199 -0
- package/dist/codex-eval-app-server.js +1366 -0
- package/dist/codex-eval-app-server.js.map +1 -0
- package/dist/codex-eval-cases.d.ts +43 -0
- package/dist/codex-eval-cases.js +327 -0
- package/dist/codex-eval-cases.js.map +1 -0
- package/dist/codex-eval-isolation.d.ts +61 -0
- package/dist/codex-eval-isolation.js +318 -0
- package/dist/codex-eval-isolation.js.map +1 -0
- package/dist/codex-eval-process-tree.d.ts +38 -0
- package/dist/codex-eval-process-tree.js +803 -0
- package/dist/codex-eval-process-tree.js.map +1 -0
- package/dist/codex-eval-runtime-config.d.ts +43 -0
- package/dist/codex-eval-runtime-config.js +607 -0
- package/dist/codex-eval-runtime-config.js.map +1 -0
- package/dist/codex-trigger-eval.d.ts +82 -0
- package/dist/codex-trigger-eval.js +789 -0
- package/dist/codex-trigger-eval.js.map +1 -0
- package/dist/codex-workflow.d.ts +188 -0
- package/dist/codex-workflow.js +1790 -0
- package/dist/codex-workflow.js.map +1 -0
- package/dist/credentials.d.ts +5 -0
- package/dist/credentials.js +30 -0
- package/dist/credentials.js.map +1 -0
- package/dist/custom-process.d.ts +58 -0
- package/dist/custom-process.js +409 -0
- package/dist/custom-process.js.map +1 -0
- package/dist/eval-audit.d.ts +38 -0
- package/dist/eval-audit.js +71 -0
- package/dist/eval-audit.js.map +1 -0
- package/dist/eval-file.d.ts +9 -0
- package/dist/eval-file.js +15 -0
- package/dist/eval-file.js.map +1 -0
- package/dist/eval-result.d.ts +64 -0
- package/dist/eval-result.js +144 -0
- package/dist/eval-result.js.map +1 -0
- package/dist/eval-run.d.ts +23 -0
- package/dist/eval-run.js +539 -0
- package/dist/eval-run.js.map +1 -0
- package/dist/eval-spec.d.ts +57 -0
- package/dist/eval-spec.js +120 -0
- package/dist/eval-spec.js.map +1 -0
- package/dist/eval-suite-binding.d.ts +4 -0
- package/dist/eval-suite-binding.js +19 -0
- package/dist/eval-suite-binding.js.map +1 -0
- package/dist/index.d.ts +34 -9
- package/dist/index.js +18 -6
- package/dist/index.js.map +1 -1
- package/dist/json-schema.js +75 -5
- package/dist/json-schema.js.map +1 -1
- package/dist/output-path.js +2 -2
- package/dist/process-tree.d.ts +19 -1
- package/dist/process-tree.js +321 -65
- package/dist/process-tree.js.map +1 -1
- package/dist/process.d.ts +0 -2
- package/dist/process.js +76 -25
- package/dist/process.js.map +1 -1
- package/dist/provider-doctor.d.ts +33 -0
- package/dist/provider-doctor.js +86 -0
- package/dist/provider-doctor.js.map +1 -0
- package/dist/providers.d.ts +82 -0
- package/dist/providers.js +630 -0
- package/dist/providers.js.map +1 -0
- package/dist/run-paths.d.ts +8 -0
- package/dist/run-paths.js +71 -0
- package/dist/run-paths.js.map +1 -0
- package/dist/runtime-skill.d.ts +6 -0
- package/dist/runtime-skill.js +87 -3
- package/dist/runtime-skill.js.map +1 -1
- package/dist/schemas/digests.json +3 -3
- package/dist/schemas/eval-audit.schema.json +64 -0
- package/dist/schemas/eval-result.schema.json +202 -0
- package/dist/schemas/eval-spec.schema.json +109 -0
- package/dist/schemas.d.ts +1 -3
- package/dist/schemas.js +0 -17
- package/dist/schemas.js.map +1 -1
- package/dist/selected-cases.d.ts +30 -0
- package/dist/selected-cases.js +388 -0
- package/dist/selected-cases.js.map +1 -0
- package/dist/types.d.ts +2 -34
- package/package.json +6 -1
- package/dist/bundle.d.ts +0 -93
- package/dist/bundle.js +0 -216
- package/dist/bundle.js.map +0 -1
- package/dist/capabilities.d.ts +0 -2
- package/dist/capabilities.js +0 -38
- package/dist/capabilities.js.map +0 -1
- package/dist/plan.d.ts +0 -79
- package/dist/plan.js +0 -285
- package/dist/plan.js.map +0 -1
- package/dist/run.d.ts +0 -2
- package/dist/run.js +0 -592
- package/dist/run.js.map +0 -1
- package/dist/schemas/aw-skill-eval-execution-plan.schema.json +0 -220
- package/dist/schemas/eval-run-bundle.schema.json +0 -408
- package/dist/schemas/eval-runtime-capabilities.schema.json +0 -85
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
import { type CodexEvalProcessManagementEvidence } from './codex-eval-app-server.js';
|
|
2
|
+
import { type CodexEvalRuntimeConfig } from './codex-eval-runtime-config.js';
|
|
3
|
+
import { type AwSkillEvalTriggerCase, type AwSkillEvalTriggerSuiteCaseContract } from './codex-eval-cases.js';
|
|
4
|
+
interface TriggerObservation {
|
|
5
|
+
loaded: boolean;
|
|
6
|
+
spawned: boolean;
|
|
7
|
+
loadEvidence: string | null;
|
|
8
|
+
spawnEvidence: string | null;
|
|
9
|
+
}
|
|
10
|
+
export interface TriggerRunEvidence {
|
|
11
|
+
loaded: boolean;
|
|
12
|
+
first_loaded_skill: string | null;
|
|
13
|
+
all_loaded_skills: string[];
|
|
14
|
+
load_evidence_by_skill: Record<string, string>;
|
|
15
|
+
spawned: boolean;
|
|
16
|
+
load_evidence: string | null;
|
|
17
|
+
spawn_evidence: string | null;
|
|
18
|
+
spawn_calls: Array<Record<string, unknown>>;
|
|
19
|
+
termination: string;
|
|
20
|
+
exit_code: number | null;
|
|
21
|
+
signal: NodeJS.Signals | null;
|
|
22
|
+
execution_error: boolean;
|
|
23
|
+
fixture_unchanged: boolean;
|
|
24
|
+
request_user_input_called: boolean;
|
|
25
|
+
waiting_on_user_input: boolean;
|
|
26
|
+
final_response_emitted: boolean;
|
|
27
|
+
stderr?: string;
|
|
28
|
+
final_message: string | null;
|
|
29
|
+
duration_ms: number;
|
|
30
|
+
usage: unknown;
|
|
31
|
+
event_trace: unknown[];
|
|
32
|
+
diagnostics: string[];
|
|
33
|
+
}
|
|
34
|
+
interface TriggerCaseSummary {
|
|
35
|
+
id: string;
|
|
36
|
+
split: AwSkillEvalTriggerCase['split'];
|
|
37
|
+
query: string;
|
|
38
|
+
expected: {
|
|
39
|
+
load_skill?: boolean;
|
|
40
|
+
loaded_skills?: string[];
|
|
41
|
+
first_loaded_skill?: string;
|
|
42
|
+
spawn_agent?: boolean;
|
|
43
|
+
};
|
|
44
|
+
observed: {
|
|
45
|
+
load_rate: number;
|
|
46
|
+
skill_load_rates: Record<string, number>;
|
|
47
|
+
route_match_rate?: number;
|
|
48
|
+
first_route_match_rate?: number;
|
|
49
|
+
route_counts?: Record<string, number>;
|
|
50
|
+
multiple_skill_loads: number;
|
|
51
|
+
spawn_rate?: number;
|
|
52
|
+
execution_errors: number;
|
|
53
|
+
};
|
|
54
|
+
complete: boolean;
|
|
55
|
+
passed: boolean;
|
|
56
|
+
runs: TriggerRunEvidence[];
|
|
57
|
+
}
|
|
58
|
+
export declare function inspectTriggerAppServerFrame(frame: Record<string, unknown>, skillPath: string): Partial<TriggerObservation> & {
|
|
59
|
+
finalMessage?: string;
|
|
60
|
+
usage?: unknown;
|
|
61
|
+
turnStatus?: string;
|
|
62
|
+
spawnCall?: Record<string, unknown>;
|
|
63
|
+
requestUserInput?: boolean;
|
|
64
|
+
};
|
|
65
|
+
export declare function inspectTriggerAppServerConfigWarning(frame: Record<string, unknown>): string | null;
|
|
66
|
+
export declare function runCodexTriggerProviderCase(options: {
|
|
67
|
+
suite: AwSkillEvalTriggerSuiteCaseContract;
|
|
68
|
+
evalCase: AwSkillEvalTriggerCase;
|
|
69
|
+
subjectRoot: string;
|
|
70
|
+
fixtureRoot: string;
|
|
71
|
+
codexBin: string;
|
|
72
|
+
model?: string;
|
|
73
|
+
codexRuntime: CodexEvalRuntimeConfig;
|
|
74
|
+
sourceEnv?: NodeJS.ProcessEnv;
|
|
75
|
+
processManagement?: CodexEvalProcessManagementEvidence;
|
|
76
|
+
workRoot?: string;
|
|
77
|
+
manageTimeout?: boolean;
|
|
78
|
+
signal?: AbortSignal;
|
|
79
|
+
timeoutMs?: number;
|
|
80
|
+
}): Promise<TriggerRunEvidence>;
|
|
81
|
+
export declare function summarizeTriggerCase(suite: AwSkillEvalTriggerSuiteCaseContract, evalCase: AwSkillEvalTriggerCase, runs: TriggerRunEvidence[]): TriggerCaseSummary;
|
|
82
|
+
export {};
|