niceeval 0.13.0 → 0.13.2-canary.35
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/INDEX.md +1 -0
- package/README.md +9 -10
- package/README.zh.md +9 -10
- package/dist/agents/ai-sdk.cjs.map +1 -1
- package/dist/agents/ai-sdk.d.cts +1 -1
- package/dist/agents/ai-sdk.d.mts +1 -1
- package/dist/agents/ai-sdk.d.ts +1 -1
- package/dist/agents/coding-cli-versions.cjs +10 -1
- package/dist/agents/coding-cli-versions.cjs.map +1 -1
- package/dist/agents/coding-cli-versions.d.cts +8 -3
- package/dist/agents/coding-cli-versions.d.mts +8 -3
- package/dist/agents/coding-cli-versions.d.ts +8 -3
- package/dist/agents/coding-cli-versions.js +18 -12
- package/dist/agents/deepseek-harness.cjs +103 -0
- package/dist/agents/deepseek-harness.cjs.map +1 -0
- package/dist/agents/deepseek-harness.d.cts +12 -0
- package/dist/agents/deepseek-harness.d.mts +12 -0
- package/dist/agents/deepseek-harness.d.ts +12 -0
- package/dist/agents/deepseek-harness.js +7 -0
- package/dist/agents/deepseek-harness.js.map +1 -0
- package/dist/agents/index.cjs +5 -1
- package/dist/agents/index.cjs.map +1 -1
- package/dist/agents/index.d.cts +4 -0
- package/dist/agents/index.d.mts +4 -0
- package/dist/agents/index.d.ts +4 -0
- package/dist/agents/index.js +54 -50
- package/dist/agents/index.mjs +54 -50
- package/dist/agents/omp.cjs +170 -0
- package/dist/agents/omp.cjs.map +1 -0
- package/dist/agents/omp.d.cts +14 -0
- package/dist/agents/omp.d.mts +14 -0
- package/dist/agents/omp.d.ts +14 -0
- package/dist/agents/omp.js +7 -0
- package/dist/agents/omp.js.map +1 -0
- package/dist/agents/types.cjs.map +1 -1
- package/dist/agents/types.d.cts +2 -2
- package/dist/agents/types.d.mts +2 -2
- package/dist/agents/types.d.ts +2 -2
- package/dist/analysis/api.cjs +9 -1
- package/dist/analysis/api.cjs.map +1 -1
- package/dist/analysis/api.d.cts +21 -0
- package/dist/analysis/api.d.mts +21 -0
- package/dist/analysis/api.d.ts +21 -0
- package/dist/analysis/api.js +8 -6
- package/dist/cli.cjs +10 -1
- package/dist/cli.cjs.map +1 -1
- package/dist/i18n/en.cjs +7 -2
- package/dist/i18n/en.cjs.map +1 -1
- package/dist/i18n/en.d.cts +7 -2
- package/dist/i18n/en.d.mts +7 -2
- package/dist/i18n/en.d.ts +7 -2
- package/dist/o11y/parsers/hermes.cjs +1 -1
- package/dist/o11y/parsers/hermes.cjs.map +1 -1
- package/dist/report/built-in/analysis-values.cjs +21 -5
- package/dist/report/built-in/analysis-values.cjs.map +1 -1
- package/dist/report/built-in/analysis-values.d.cts +11 -9
- package/dist/report/built-in/analysis-values.d.mts +11 -9
- package/dist/report/built-in/analysis-values.d.ts +11 -9
- package/dist/report/built-in/overview.cjs +1 -0
- package/dist/report/built-in/overview.cjs.map +1 -1
- package/dist/report/built-in/result-components.cjs +58 -12
- package/dist/report/built-in/result-components.cjs.map +1 -1
- package/dist/report/built-in/result-components.d.cts +15 -0
- package/dist/report/built-in/result-components.d.mts +15 -0
- package/dist/report/built-in/result-components.d.ts +15 -0
- package/dist/report/built-in/run-membership-overview.cjs +100 -4
- package/dist/report/built-in/run-membership-overview.cjs.map +1 -1
- package/dist/report/built-in/standard.cjs +1 -0
- package/dist/report/built-in/standard.cjs.map +1 -1
- package/dist/report/built-in/standard.d.cts +1 -0
- package/dist/report/built-in/standard.d.mts +1 -0
- package/dist/report/built-in/standard.d.ts +1 -0
- package/dist/report/components/entity-lists/compute.cjs +40 -3
- package/dist/report/components/entity-lists/compute.cjs.map +1 -1
- package/dist/report/components/entity-lists/compute.d.cts +8 -6
- package/dist/report/components/entity-lists/compute.d.mts +8 -6
- package/dist/report/components/entity-lists/compute.d.ts +8 -6
- package/dist/report/components/entity-lists/content.cjs +31 -6
- package/dist/report/components/entity-lists/content.cjs.map +1 -1
- package/dist/report/components/entity-lists/index.cjs +3 -2
- package/dist/report/components/entity-lists/index.cjs.map +1 -1
- package/dist/report/components/entity-lists/index.d.cts +1 -1
- package/dist/report/components/entity-lists/index.d.mts +1 -1
- package/dist/report/components/entity-lists/index.d.ts +1 -1
- package/dist/report/definition/cell.cjs +3 -0
- package/dist/report/definition/cell.cjs.map +1 -1
- package/dist/report/definition/cell.d.cts +2 -0
- package/dist/report/definition/cell.d.mts +2 -0
- package/dist/report/definition/cell.d.ts +2 -0
- package/dist/report/definition/primitives.cjs +9 -2
- package/dist/report/definition/primitives.cjs.map +1 -1
- package/dist/report/execution/machine.cjs +1 -1
- package/dist/report/execution/machine.cjs.map +1 -1
- package/dist/report/host/execute.cjs +14 -4
- package/dist/report/host/execute.cjs.map +1 -1
- package/dist/report/host/execute.d.cts +5 -0
- package/dist/report/host/execute.d.mts +5 -0
- package/dist/report/host/execute.d.ts +5 -0
- package/dist/report/host/from-record.cjs +6 -1
- package/dist/report/host/from-record.cjs.map +1 -1
- package/dist/report/host/from-record.d.cts +5 -0
- package/dist/report/host/from-record.d.mts +5 -0
- package/dist/report/host/from-record.d.ts +5 -0
- package/dist/report/runtime/resolved-page.cjs +16 -6
- package/dist/report/runtime/resolved-page.cjs.map +1 -1
- package/dist/report/runtime/resolved-page.d.cts +3 -0
- package/dist/report/runtime/resolved-page.d.mts +3 -0
- package/dist/report/runtime/resolved-page.d.ts +3 -0
- package/dist/report/runtime/text.cjs +1 -0
- package/dist/report/runtime/text.cjs.map +1 -1
- package/dist/report/runtime/text.d.cts +4 -0
- package/dist/report/runtime/text.d.mts +4 -0
- package/dist/report/runtime/text.d.ts +4 -0
- package/dist/runner/feedback/human.cjs +180 -16
- package/dist/runner/feedback/human.cjs.map +1 -1
- package/dist/runner/run.cjs +43 -0
- package/dist/runner/run.cjs.map +1 -1
- package/dist/sample/capability.cjs +93 -0
- package/dist/sample/capability.cjs.map +1 -1
- package/dist/sample/capability.d.cts +3 -1
- package/dist/sample/capability.d.mts +3 -1
- package/dist/sample/capability.d.ts +3 -1
- package/dist/sample/capability.js +8 -6
- package/dist/sandbox/docker-agent-image.cjs +5 -1
- package/dist/sandbox/docker-agent-image.cjs.map +1 -1
- package/dist/sandbox/docker-agent-image.d.cts +2 -0
- package/dist/sandbox/docker-agent-image.d.mts +2 -0
- package/dist/sandbox/docker-agent-image.d.ts +2 -0
- package/dist/sandbox/docker-agent-image.js +14 -10
- package/dist/sandbox/index.cjs +4 -2
- package/dist/sandbox/index.cjs.map +1 -1
- package/dist/sandbox/index.d.cts +1 -1
- package/dist/sandbox/index.d.mts +1 -1
- package/dist/sandbox/index.d.ts +1 -1
- package/dist/sandbox/index.js +120 -116
- package/dist/sandbox/index.mjs +120 -116
- package/docs-site/images/hitl-handshake-zh.svg +3 -3
- package/docs-site/zh/examples/integrations/ai-sdk-v7.mdx +3 -3
- package/docs-site/zh/examples/integrations/claude-sdk.mdx +3 -3
- package/docs-site/zh/examples/integrations/codex-sdk.mdx +5 -5
- package/docs-site/zh/examples/integrations/langgraph.mdx +3 -3
- package/docs-site/zh/examples/integrations/pi-sdk.mdx +5 -5
- package/docs-site/zh/explanation/adapter.mdx +5 -5
- package/docs-site/zh/explanation/assert.mdx +1 -1
- package/docs-site/zh/explanation/drive.mdx +3 -1
- package/docs-site/zh/explanation/evals.mdx +3 -1
- package/docs-site/zh/explanation/hitl.mdx +7 -7
- package/docs-site/zh/explanation/runner.mdx +2 -2
- package/docs-site/zh/index.mdx +2 -2
- package/docs-site/zh/reference/builtin-agents.mdx +4 -4
- package/docs-site/zh/reference/capabilities.mdx +1 -1
- package/docs-site/zh/reference/cli.mdx +14 -14
- package/docs-site/zh/reference/events.mdx +11 -11
- package/docs-site/zh/reference/official-adapters.mdx +1 -1
- package/docs-site/zh/reference/results-data.mdx +6 -0
- package/docs-site/zh/troubleshooting/debugging.mdx +2 -2
- package/docs-site/zh/tutorials/agent-feedback-loop.mdx +2 -2
- package/docs-site/zh/tutorials/ci-integration.mdx +1 -1
- package/docs-site/zh/tutorials/connect-your-agent.mdx +2 -2
- package/docs-site/zh/tutorials/custom-reports.mdx +4 -4
- package/docs-site/zh/tutorials/deploy-report-site.mdx +3 -3
- package/docs-site/zh/tutorials/docker-in-docker.mdx +3 -0
- package/docs-site/zh/tutorials/experiments.mdx +2 -2
- package/docs-site/zh/tutorials/handle-execution-failures.mdx +1 -1
- package/docs-site/zh/tutorials/install-custom-sandbox-agent.mdx +1 -1
- package/docs-site/zh/tutorials/nixos-managed-dind.mdx +160 -0
- package/docs-site/zh/tutorials/publish-report.mdx +4 -4
- package/docs-site/zh/tutorials/reporters.mdx +1 -1
- package/docs-site/zh/tutorials/rerun-and-cache.mdx +16 -0
- package/docs-site/zh/tutorials/viewing-results.mdx +28 -10
- package/docs-site/zh/tutorials/write-send.mdx +7 -6
- package/package.json +1 -1
package/dist/sandbox/index.mjs
CHANGED
|
@@ -25,120 +25,124 @@ const __niceevalExport10 = __niceevalCanonical["NICEEVAL_CLAUDE_CODE_DOCKER_IMAG
|
|
|
25
25
|
export { __niceevalExport10 as NICEEVAL_CLAUDE_CODE_DOCKER_IMAGE };
|
|
26
26
|
const __niceevalExport11 = __niceevalCanonical["NICEEVAL_CODEX_DOCKER_IMAGE"];
|
|
27
27
|
export { __niceevalExport11 as NICEEVAL_CODEX_DOCKER_IMAGE };
|
|
28
|
-
const __niceevalExport12 = __niceevalCanonical["
|
|
29
|
-
export { __niceevalExport12 as
|
|
30
|
-
const __niceevalExport13 = __niceevalCanonical["
|
|
31
|
-
export { __niceevalExport13 as
|
|
32
|
-
const __niceevalExport14 = __niceevalCanonical["
|
|
33
|
-
export { __niceevalExport14 as
|
|
34
|
-
const __niceevalExport15 = __niceevalCanonical["
|
|
35
|
-
export { __niceevalExport15 as
|
|
36
|
-
const __niceevalExport16 = __niceevalCanonical["
|
|
37
|
-
export { __niceevalExport16 as
|
|
38
|
-
const __niceevalExport17 = __niceevalCanonical["
|
|
39
|
-
export { __niceevalExport17 as
|
|
40
|
-
const __niceevalExport18 = __niceevalCanonical["
|
|
41
|
-
export { __niceevalExport18 as
|
|
42
|
-
const __niceevalExport19 = __niceevalCanonical["
|
|
43
|
-
export { __niceevalExport19 as
|
|
44
|
-
const __niceevalExport20 = __niceevalCanonical["
|
|
45
|
-
export { __niceevalExport20 as
|
|
46
|
-
const __niceevalExport21 = __niceevalCanonical["
|
|
47
|
-
export { __niceevalExport21 as
|
|
48
|
-
const __niceevalExport22 = __niceevalCanonical["
|
|
49
|
-
export { __niceevalExport22 as
|
|
50
|
-
const __niceevalExport23 = __niceevalCanonical["
|
|
51
|
-
export { __niceevalExport23 as
|
|
52
|
-
const __niceevalExport24 = __niceevalCanonical["
|
|
53
|
-
export { __niceevalExport24 as
|
|
54
|
-
const __niceevalExport25 = __niceevalCanonical["
|
|
55
|
-
export { __niceevalExport25 as
|
|
56
|
-
const __niceevalExport26 = __niceevalCanonical["
|
|
57
|
-
export { __niceevalExport26 as
|
|
58
|
-
const __niceevalExport27 = __niceevalCanonical["
|
|
59
|
-
export { __niceevalExport27 as
|
|
60
|
-
const __niceevalExport28 = __niceevalCanonical["
|
|
61
|
-
export { __niceevalExport28 as
|
|
62
|
-
const __niceevalExport29 = __niceevalCanonical["
|
|
63
|
-
export { __niceevalExport29 as
|
|
64
|
-
const __niceevalExport30 = __niceevalCanonical["
|
|
65
|
-
export { __niceevalExport30 as
|
|
66
|
-
const __niceevalExport31 = __niceevalCanonical["
|
|
67
|
-
export { __niceevalExport31 as
|
|
68
|
-
const __niceevalExport32 = __niceevalCanonical["
|
|
69
|
-
export { __niceevalExport32 as
|
|
70
|
-
const __niceevalExport33 = __niceevalCanonical["
|
|
71
|
-
export { __niceevalExport33 as
|
|
72
|
-
const __niceevalExport34 = __niceevalCanonical["
|
|
73
|
-
export { __niceevalExport34 as
|
|
74
|
-
const __niceevalExport35 = __niceevalCanonical["
|
|
75
|
-
export { __niceevalExport35 as
|
|
76
|
-
const __niceevalExport36 = __niceevalCanonical["
|
|
77
|
-
export { __niceevalExport36 as
|
|
78
|
-
const __niceevalExport37 = __niceevalCanonical["
|
|
79
|
-
export { __niceevalExport37 as
|
|
80
|
-
const __niceevalExport38 = __niceevalCanonical["
|
|
81
|
-
export { __niceevalExport38 as
|
|
82
|
-
const __niceevalExport39 = __niceevalCanonical["
|
|
83
|
-
export { __niceevalExport39 as
|
|
84
|
-
const __niceevalExport40 = __niceevalCanonical["
|
|
85
|
-
export { __niceevalExport40 as
|
|
86
|
-
const __niceevalExport41 = __niceevalCanonical["
|
|
87
|
-
export { __niceevalExport41 as
|
|
88
|
-
const __niceevalExport42 = __niceevalCanonical["
|
|
89
|
-
export { __niceevalExport42 as
|
|
90
|
-
const __niceevalExport43 = __niceevalCanonical["
|
|
91
|
-
export { __niceevalExport43 as
|
|
92
|
-
const __niceevalExport44 = __niceevalCanonical["
|
|
93
|
-
export { __niceevalExport44 as
|
|
94
|
-
const __niceevalExport45 = __niceevalCanonical["
|
|
95
|
-
export { __niceevalExport45 as
|
|
96
|
-
const __niceevalExport46 = __niceevalCanonical["
|
|
97
|
-
export { __niceevalExport46 as
|
|
98
|
-
const __niceevalExport47 = __niceevalCanonical["
|
|
99
|
-
export { __niceevalExport47 as
|
|
100
|
-
const __niceevalExport48 = __niceevalCanonical["
|
|
101
|
-
export { __niceevalExport48 as
|
|
102
|
-
const __niceevalExport49 = __niceevalCanonical["
|
|
103
|
-
export { __niceevalExport49 as
|
|
104
|
-
const __niceevalExport50 = __niceevalCanonical["
|
|
105
|
-
export { __niceevalExport50 as
|
|
106
|
-
const __niceevalExport51 = __niceevalCanonical["
|
|
107
|
-
export { __niceevalExport51 as
|
|
108
|
-
const __niceevalExport52 = __niceevalCanonical["
|
|
109
|
-
export { __niceevalExport52 as
|
|
110
|
-
const __niceevalExport53 = __niceevalCanonical["
|
|
111
|
-
export { __niceevalExport53 as
|
|
112
|
-
const __niceevalExport54 = __niceevalCanonical["
|
|
113
|
-
export { __niceevalExport54 as
|
|
114
|
-
const __niceevalExport55 = __niceevalCanonical["
|
|
115
|
-
export { __niceevalExport55 as
|
|
116
|
-
const __niceevalExport56 = __niceevalCanonical["
|
|
117
|
-
export { __niceevalExport56 as
|
|
118
|
-
const __niceevalExport57 = __niceevalCanonical["
|
|
119
|
-
export { __niceevalExport57 as
|
|
120
|
-
const __niceevalExport58 = __niceevalCanonical["
|
|
121
|
-
export { __niceevalExport58 as
|
|
122
|
-
const __niceevalExport59 = __niceevalCanonical["
|
|
123
|
-
export { __niceevalExport59 as
|
|
124
|
-
const __niceevalExport60 = __niceevalCanonical["
|
|
125
|
-
export { __niceevalExport60 as
|
|
126
|
-
const __niceevalExport61 = __niceevalCanonical["
|
|
127
|
-
export { __niceevalExport61 as
|
|
128
|
-
const __niceevalExport62 = __niceevalCanonical["
|
|
129
|
-
export { __niceevalExport62 as
|
|
130
|
-
const __niceevalExport63 = __niceevalCanonical["
|
|
131
|
-
export { __niceevalExport63 as
|
|
132
|
-
const __niceevalExport64 = __niceevalCanonical["
|
|
133
|
-
export { __niceevalExport64 as
|
|
134
|
-
const __niceevalExport65 = __niceevalCanonical["
|
|
135
|
-
export { __niceevalExport65 as
|
|
136
|
-
const __niceevalExport66 = __niceevalCanonical["
|
|
137
|
-
export { __niceevalExport66 as
|
|
138
|
-
const __niceevalExport67 = __niceevalCanonical["
|
|
139
|
-
export { __niceevalExport67 as
|
|
140
|
-
const __niceevalExport68 = __niceevalCanonical["
|
|
141
|
-
export { __niceevalExport68 as
|
|
142
|
-
const __niceevalExport69 = __niceevalCanonical["
|
|
143
|
-
export { __niceevalExport69 as
|
|
28
|
+
const __niceevalExport12 = __niceevalCanonical["NICEEVAL_DEEPSEEK_HARNESS_DOCKER_IMAGE"];
|
|
29
|
+
export { __niceevalExport12 as NICEEVAL_DEEPSEEK_HARNESS_DOCKER_IMAGE };
|
|
30
|
+
const __niceevalExport13 = __niceevalCanonical["NICEEVAL_HERMES_DOCKER_IMAGE"];
|
|
31
|
+
export { __niceevalExport13 as NICEEVAL_HERMES_DOCKER_IMAGE };
|
|
32
|
+
const __niceevalExport14 = __niceevalCanonical["NICEEVAL_OMP_DOCKER_IMAGE"];
|
|
33
|
+
export { __niceevalExport14 as NICEEVAL_OMP_DOCKER_IMAGE };
|
|
34
|
+
const __niceevalExport15 = __niceevalCanonical["NICEEVAL_OPENCLAW_DOCKER_IMAGE"];
|
|
35
|
+
export { __niceevalExport15 as NICEEVAL_OPENCLAW_DOCKER_IMAGE };
|
|
36
|
+
const __niceevalExport16 = __niceevalCanonical["NICEEVAL_OPENCODE_DOCKER_IMAGE"];
|
|
37
|
+
export { __niceevalExport16 as NICEEVAL_OPENCODE_DOCKER_IMAGE };
|
|
38
|
+
const __niceevalExport17 = __niceevalCanonical["SANDBOX_BUILD_ACTIVITY"];
|
|
39
|
+
export { __niceevalExport17 as SANDBOX_BUILD_ACTIVITY };
|
|
40
|
+
const __niceevalExport18 = __niceevalCanonical["SandboxCommandExitError"];
|
|
41
|
+
export { __niceevalExport18 as SandboxCommandExitError };
|
|
42
|
+
const __niceevalExport19 = __niceevalCanonical["assertComposeBlacklist"];
|
|
43
|
+
export { __niceevalExport19 as assertComposeBlacklist };
|
|
44
|
+
const __niceevalExport20 = __niceevalCanonical["assertPureDataIdentity"];
|
|
45
|
+
export { __niceevalExport20 as assertPureDataIdentity };
|
|
46
|
+
const __niceevalExport21 = __niceevalCanonical["buildComposeOverlay"];
|
|
47
|
+
export { __niceevalExport21 as buildComposeOverlay };
|
|
48
|
+
const __niceevalExport22 = __niceevalCanonical["buildFailureOrigin"];
|
|
49
|
+
export { __niceevalExport22 as buildFailureOrigin };
|
|
50
|
+
const __niceevalExport23 = __niceevalCanonical["checkout"];
|
|
51
|
+
export { __niceevalExport23 as checkout };
|
|
52
|
+
const __niceevalExport24 = __niceevalCanonical["collectComposeBuilds"];
|
|
53
|
+
export { __niceevalExport24 as collectComposeBuilds };
|
|
54
|
+
const __niceevalExport25 = __niceevalCanonical["command"];
|
|
55
|
+
export { __niceevalExport25 as command };
|
|
56
|
+
const __niceevalExport26 = __niceevalCanonical["computeBuildKey"];
|
|
57
|
+
export { __niceevalExport26 as computeBuildKey };
|
|
58
|
+
const __niceevalExport27 = __niceevalCanonical["computeCaseKey"];
|
|
59
|
+
export { __niceevalExport27 as computeCaseKey };
|
|
60
|
+
const __niceevalExport28 = __niceevalCanonical["createCheckpoint"];
|
|
61
|
+
export { __niceevalExport28 as createCheckpoint };
|
|
62
|
+
const __niceevalExport29 = __niceevalCanonical["createDockerExecutionProfileV1"];
|
|
63
|
+
export { __niceevalExport29 as createDockerExecutionProfileV1 };
|
|
64
|
+
const __niceevalExport30 = __niceevalCanonical["createDockerProfileRegistry"];
|
|
65
|
+
export { __niceevalExport30 as createDockerProfileRegistry };
|
|
66
|
+
const __niceevalExport31 = __niceevalCanonical["credentialIdentityContribution"];
|
|
67
|
+
export { __niceevalExport31 as credentialIdentityContribution };
|
|
68
|
+
const __niceevalExport32 = __niceevalCanonical["decodeDockerExecutionProfileV1"];
|
|
69
|
+
export { __niceevalExport32 as decodeDockerExecutionProfileV1 };
|
|
70
|
+
const __niceevalExport33 = __niceevalCanonical["defineSandbox"];
|
|
71
|
+
export { __niceevalExport33 as defineSandbox };
|
|
72
|
+
const __niceevalExport34 = __niceevalCanonical["defineSandboxCase"];
|
|
73
|
+
export { __niceevalExport34 as defineSandboxCase };
|
|
74
|
+
const __niceevalExport35 = __niceevalCanonical["defineSandboxCommand"];
|
|
75
|
+
export { __niceevalExport35 as defineSandboxCommand };
|
|
76
|
+
const __niceevalExport36 = __niceevalCanonical["dockerComposeBuildProvider"];
|
|
77
|
+
export { __niceevalExport36 as dockerComposeBuildProvider };
|
|
78
|
+
const __niceevalExport37 = __niceevalCanonical["dockerComposeSandbox"];
|
|
79
|
+
export { __niceevalExport37 as dockerComposeSandbox };
|
|
80
|
+
const __niceevalExport38 = __niceevalCanonical["dockerExecutionProfileSemanticPolicyRevisionOf"];
|
|
81
|
+
export { __niceevalExport38 as dockerExecutionProfileSemanticPolicyRevisionOf };
|
|
82
|
+
const __niceevalExport39 = __niceevalCanonical["dockerExecutionProfileV1Digest"];
|
|
83
|
+
export { __niceevalExport39 as dockerExecutionProfileV1Digest };
|
|
84
|
+
const __niceevalExport40 = __niceevalCanonical["dockerProfileDigestOf"];
|
|
85
|
+
export { __niceevalExport40 as dockerProfileDigestOf };
|
|
86
|
+
const __niceevalExport41 = __niceevalCanonical["dockerProfileError"];
|
|
87
|
+
export { __niceevalExport41 as dockerProfileError };
|
|
88
|
+
const __niceevalExport42 = __niceevalCanonical["dockerProfilePublicSummaryOf"];
|
|
89
|
+
export { __niceevalExport42 as dockerProfilePublicSummaryOf };
|
|
90
|
+
const __niceevalExport43 = __niceevalCanonical["dockerProfileSemanticPolicyRevisionOf"];
|
|
91
|
+
export { __niceevalExport43 as dockerProfileSemanticPolicyRevisionOf };
|
|
92
|
+
const __niceevalExport44 = __niceevalCanonical["dockerSandbox"];
|
|
93
|
+
export { __niceevalExport44 as dockerSandbox };
|
|
94
|
+
const __niceevalExport45 = __niceevalCanonical["e2bSandbox"];
|
|
95
|
+
export { __niceevalExport45 as e2bSandbox };
|
|
96
|
+
const __niceevalExport46 = __niceevalCanonical["findComposeBlacklistViolations"];
|
|
97
|
+
export { __niceevalExport46 as findComposeBlacklistViolations };
|
|
98
|
+
const __niceevalExport47 = __niceevalCanonical["indexDockerProfiles"];
|
|
99
|
+
export { __niceevalExport47 as indexDockerProfiles };
|
|
100
|
+
const __niceevalExport48 = __niceevalCanonical["inspectComposeYaml"];
|
|
101
|
+
export { __niceevalExport48 as inspectComposeYaml };
|
|
102
|
+
const __niceevalExport49 = __niceevalCanonical["installTool"];
|
|
103
|
+
export { __niceevalExport49 as installTool };
|
|
104
|
+
const __niceevalExport50 = __niceevalCanonical["isDockerExecutionProfileV1"];
|
|
105
|
+
export { __niceevalExport50 as isDockerExecutionProfileV1 };
|
|
106
|
+
const __niceevalExport51 = __niceevalCanonical["leakGateHintsFromComposeFile"];
|
|
107
|
+
export { __niceevalExport51 as leakGateHintsFromComposeFile };
|
|
108
|
+
const __niceevalExport52 = __niceevalCanonical["localSandbox"];
|
|
109
|
+
export { __niceevalExport52 as localSandbox };
|
|
110
|
+
const __niceevalExport53 = __niceevalCanonical["looksLikeDigestRef"];
|
|
111
|
+
export { __niceevalExport53 as looksLikeDigestRef };
|
|
112
|
+
const __niceevalExport54 = __niceevalCanonical["makeDockerExecutionProfileV1"];
|
|
113
|
+
export { __niceevalExport54 as makeDockerExecutionProfileV1 };
|
|
114
|
+
const __niceevalExport55 = __niceevalCanonical["materializeDockerComposeProviderCase"];
|
|
115
|
+
export { __niceevalExport55 as materializeDockerComposeProviderCase };
|
|
116
|
+
const __niceevalExport56 = __niceevalCanonical["normalizeSandboxCapture"];
|
|
117
|
+
export { __niceevalExport56 as normalizeSandboxCapture };
|
|
118
|
+
const __niceevalExport57 = __niceevalCanonical["parseDockerExecutionProfile"];
|
|
119
|
+
export { __niceevalExport57 as parseDockerExecutionProfile };
|
|
120
|
+
const __niceevalExport58 = __niceevalCanonical["parseDockerExecutionProfileV1"];
|
|
121
|
+
export { __niceevalExport58 as parseDockerExecutionProfileV1 };
|
|
122
|
+
const __niceevalExport59 = __niceevalCanonical["parseDockerProfileRegistry"];
|
|
123
|
+
export { __niceevalExport59 as parseDockerProfileRegistry };
|
|
124
|
+
const __niceevalExport60 = __niceevalCanonical["prepareSandboxBuilds"];
|
|
125
|
+
export { __niceevalExport60 as prepareSandboxBuilds };
|
|
126
|
+
const __niceevalExport61 = __niceevalCanonical["registerSandboxContent"];
|
|
127
|
+
export { __niceevalExport61 as registerSandboxContent };
|
|
128
|
+
const __niceevalExport62 = __niceevalCanonical["resolveDockerExecutionProfile"];
|
|
129
|
+
export { __niceevalExport62 as resolveDockerExecutionProfile };
|
|
130
|
+
const __niceevalExport63 = __niceevalCanonical["resolveDockerProfile"];
|
|
131
|
+
export { __niceevalExport63 as resolveDockerProfile };
|
|
132
|
+
const __niceevalExport64 = __niceevalCanonical["resolveDockerProfileAlias"];
|
|
133
|
+
export { __niceevalExport64 as resolveDockerProfileAlias };
|
|
134
|
+
const __niceevalExport65 = __niceevalCanonical["resolveDockerProfileSelector"];
|
|
135
|
+
export { __niceevalExport65 as resolveDockerProfileSelector };
|
|
136
|
+
const __niceevalExport66 = __niceevalCanonical["resolveFloatingImageTag"];
|
|
137
|
+
export { __niceevalExport66 as resolveFloatingImageTag };
|
|
138
|
+
const __niceevalExport67 = __niceevalCanonical["restoreCheckpoint"];
|
|
139
|
+
export { __niceevalExport67 as restoreCheckpoint };
|
|
140
|
+
const __niceevalExport68 = __niceevalCanonical["sandboxLayer"];
|
|
141
|
+
export { __niceevalExport68 as sandboxLayer };
|
|
142
|
+
const __niceevalExport69 = __niceevalCanonical["shell"];
|
|
143
|
+
export { __niceevalExport69 as shell };
|
|
144
|
+
const __niceevalExport70 = __niceevalCanonical["startSandboxBuilds"];
|
|
145
|
+
export { __niceevalExport70 as startSandboxBuilds };
|
|
146
|
+
const __niceevalExport71 = __niceevalCanonical["vercelSandbox"];
|
|
147
|
+
export { __niceevalExport71 as vercelSandbox };
|
|
144
148
|
//# sourceMappingURL=index.mjs.map
|
|
@@ -58,9 +58,9 @@
|
|
|
58
58
|
<path d="M 674 282 H 206" class="returnArrow" />
|
|
59
59
|
|
|
60
60
|
<!-- ③ eval 侧检查(不触发 send) -->
|
|
61
|
-
<rect x="40" y="308" width="
|
|
62
|
-
<text x="54" y="331" class="codeSm">t.
|
|
63
|
-
<text x="
|
|
61
|
+
<rect x="40" y="308" width="430" height="32" rx="8" class="pill" />
|
|
62
|
+
<text x="54" y="331" class="codeSm">t.check(turn.status, equals("waiting"))</text>
|
|
63
|
+
<text x="490" y="331" class="muted">断言这一轮确实停下了</text>
|
|
64
64
|
|
|
65
65
|
<rect x="40" y="350" width="500" height="32" rx="8" class="pill" />
|
|
66
66
|
<text x="54" y="373" class="codeSm">t.requireInputRequest({ action: "deploy" })</text>
|
|
@@ -94,7 +94,7 @@ ai-sdk-v7/
|
|
|
94
94
|
<div className="gd-file">
|
|
95
95
|
<div className="gd-head"><span className="gd-name">{"evals/hitl-approve.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+24"}</span></span></div>
|
|
96
96
|
<div className="gd-body">
|
|
97
|
-
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// calculate 工具声明了 needsApproval:true(AI SDK 自己的 tool loop 停轮机制)。这条验证批准"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 分支:approve 之后工具正常执行,calledTool 的 status 是 \"completed\"。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 提示词不提\"审批\"——不同模型看到提示词里的\"审批\"字样,有的会倾向于用文字反问用户"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// \"可以吗\"而不是真的发起工具调用(在 pi-sdk / claude-sdk / langgraph 的接入里都复现过);"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 审批门是 SDK 自动挂的,跟用户怎么问无关。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"HITL:calculate 经批准后正常执行\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"draft"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(draft.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"approved"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"approve\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" approved."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{" }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"
|
|
97
|
+
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals, pattern, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// calculate 工具声明了 needsApproval:true(AI SDK 自己的 tool loop 停轮机制)。这条验证批准"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 分支:approve 之后工具正常执行,calledTool 的 status 是 \"completed\"。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 提示词不提\"审批\"——不同模型看到提示词里的\"审批\"字样,有的会倾向于用文字反问用户"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// \"可以吗\"而不是真的发起工具调用(在 pi-sdk / claude-sdk / langgraph 的接入里都复现过);"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 审批门是 SDK 自动挂的,跟用户怎么问无关。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"HITL:calculate 经批准后正常执行\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"draft"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(draft.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"approved"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"approve\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" approved."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{" }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(approved.message, "}</span><span className="gdt5">{"pattern"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"126"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"24"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
|
|
98
98
|
</div>
|
|
99
99
|
</div>
|
|
100
100
|
|
|
@@ -108,14 +108,14 @@ ai-sdk-v7/
|
|
|
108
108
|
<div className="gd-file">
|
|
109
109
|
<div className="gd-head"><span className="gd-name">{"evals/session-isolation.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+20"}</span></span></div>
|
|
110
110
|
<div className="gd-body">
|
|
111
|
-
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { includes, excludes } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 专门验证跨轮记忆的两半承诺:同一 session 里第二轮记得住第一轮说的名字"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// (客户端重放完整历史续接成功——这个应用服务端零状态,续接完全靠 adapter 按 sessionId 存取"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 完整 UIMessage[] 并原样重发);t.newSession() 造出的新 session 不共享历史。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"测试跨轮记忆与 newSession() 隔离\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"我叫小明,帮我记住这个名字。\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"recall"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"我刚才说我叫什么名字?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" recall."}</span><span className="gdt5">{"
|
|
111
|
+
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { includes, excludes } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 专门验证跨轮记忆的两半承诺:同一 session 里第二轮记得住第一轮说的名字"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// (客户端重放完整历史续接成功——这个应用服务端零状态,续接完全靠 adapter 按 sessionId 存取"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 完整 UIMessage[] 并原样重发);t.newSession() 造出的新 session 不共享历史。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"测试跨轮记忆与 newSession() 隔离\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"我叫小明,帮我记住这个名字。\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"recall"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"我刚才说我叫什么名字?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(recall.message, "}</span><span className="gdt5">{"includes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"小明\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(t.reply, "}</span><span className="gdt5">{"includes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"小明\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"fresh"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"newSession"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" fresh."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"我叫什么名字?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(fresh.reply, "}</span><span className="gdt5">{"excludes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"小明\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
|
|
112
112
|
</div>
|
|
113
113
|
</div>
|
|
114
114
|
|
|
115
115
|
<div className="gd-file">
|
|
116
116
|
<div className="gd-head"><span className="gd-name">{"evals/weather-tool.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+23"}</span></span></div>
|
|
117
117
|
<div className="gd-body">
|
|
118
|
-
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { jsonMatch, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 遇到实时天气问题时会调 get_weather,而不是直接编一个答案。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 工具断言完全来自 UI Message Stream 协议帧直构(uiMessageStreamAgent 内置),adapter 没有为它写一行帧映射。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" judge: "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"测试 agent 在天气问题中正确调用 get_weather 并基于结果作答\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"北京今天天气怎么样?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"调用 get_weather 且城市正确\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"get_weather\""}</span><span className="gdt0">{", { input: "}</span><span className="gdt5">{"jsonMatch"}</span><span className="gdt0">{"({ city: "}</span><span className="gdt2">{"\"北京\""}</span><span className="gdt0">{" }) }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"
|
|
118
|
+
<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { jsonMatch, pattern, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 遇到实时天气问题时会调 get_weather,而不是直接编一个答案。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 工具断言完全来自 UI Message Stream 协议帧直构(uiMessageStreamAgent 内置),adapter 没有为它写一行帧映射。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" judge: "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" description: "}</span><span className="gdt2">{"\"测试 agent 在天气问题中正确调用 get_weather 并基于结果作答\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"北京今天天气怎么样?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"调用 get_weather 且城市正确\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"get_weather\""}</span><span className="gdt0">{", { input: "}</span><span className="gdt5">{"jsonMatch"}</span><span className="gdt0">{"({ city: "}</span><span className="gdt2">{"\"北京\""}</span><span className="gdt0">{" }) }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(turn.message, "}</span><span className="gdt5">{"pattern"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"°C"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"气温"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"天气"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"晴"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"多云"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"雨"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"阴"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" turn.judge.autoevals"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" ."}</span><span className="gdt5">{"closedQA"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"助手是否给出了具体的天气数据(温度或天气状况),而不是拒绝回答或含糊其辞?\""}</span><span className="gdt0">{")"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" ."}</span><span className="gdt5">{"gate"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"0.7"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{" },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
|
|
119
119
|
</div>
|
|
120
120
|
</div>
|
|
121
121
|
|