@tangle-network/agent-eval 0.203.0 → 0.203.1

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.
Files changed (136) hide show
  1. package/CHANGELOG.md +6 -0
  2. package/dist/adapters/http.d.ts +10 -4
  3. package/dist/adapters/http.d.ts.map +1 -1
  4. package/dist/adapters/http.js +43 -38
  5. package/dist/adapters/http.js.map +1 -1
  6. package/dist/{agent-profile-DDfIjdyS.d.ts → agent-profile-EpO0HURy.d.ts} +4 -4
  7. package/dist/{agent-profile-DDfIjdyS.d.ts.map → agent-profile-EpO0HURy.d.ts.map} +1 -1
  8. package/dist/analyst/index.d.ts +12 -12
  9. package/dist/analyst/index.d.ts.map +1 -1
  10. package/dist/analyst/index.js +6 -6
  11. package/dist/{analyze-runs-CPiKLJFs.d.ts → analyze-runs-Q74o4Hfj.d.ts} +2 -2
  12. package/dist/{analyze-runs-CPiKLJFs.d.ts.map → analyze-runs-Q74o4Hfj.d.ts.map} +1 -1
  13. package/dist/{benchmark-command-DFs_i62N.js → benchmark-command-6OBcB0sG.js} +7 -6
  14. package/dist/benchmark-command-6OBcB0sG.js.map +1 -0
  15. package/dist/benchmarks/index.d.ts +4 -4
  16. package/dist/benchmarks/index.js +3 -3
  17. package/dist/campaign/index.d.ts +6 -6
  18. package/dist/campaign/index.js +4 -4
  19. package/dist/{campaign-Btk1yFfw.js → campaign-BbObY2c6.js} +6 -6
  20. package/dist/{campaign-Btk1yFfw.js.map → campaign-BbObY2c6.js.map} +1 -1
  21. package/dist/{chat-client-DUhWNQQS.js → chat-client-5LLl4Ctl.js} +2 -2
  22. package/dist/{chat-client-DUhWNQQS.js.map → chat-client-5LLl4Ctl.js.map} +1 -1
  23. package/dist/{chat-json-call-Dx_sHzqm.js → chat-json-call-Digk-pfF.js} +2 -2
  24. package/dist/{chat-json-call-Dx_sHzqm.js.map → chat-json-call-Digk-pfF.js.map} +1 -1
  25. package/dist/cli.js +3 -3
  26. package/dist/contract/index.d.ts +10 -10
  27. package/dist/contract/index.js +7 -7
  28. package/dist/{default-registry-B-utjsmX.d.ts → default-registry-CxEBVA6W.d.ts} +6 -6
  29. package/dist/{default-registry-B-utjsmX.d.ts.map → default-registry-CxEBVA6W.d.ts.map} +1 -1
  30. package/dist/{default-registry-CpswV_S2.js → default-registry-wInsQWlQ.js} +2 -2
  31. package/dist/{default-registry-CpswV_S2.js.map → default-registry-wInsQWlQ.js.map} +1 -1
  32. package/dist/{define-agent-eval-MAc6BQrq.d.ts → define-agent-eval-BbEXdM3H.d.ts} +7 -7
  33. package/dist/{define-agent-eval-MAc6BQrq.d.ts.map → define-agent-eval-BbEXdM3H.d.ts.map} +1 -1
  34. package/dist/{define-agent-eval-CJN9dTQw.js → define-agent-eval-Da8mHyc7.js} +3 -3
  35. package/dist/{define-agent-eval-CJN9dTQw.js.map → define-agent-eval-Da8mHyc7.js.map} +1 -1
  36. package/dist/diagnosis/index.d.ts +2 -2
  37. package/dist/{dspy-rlm-engine-US8YsYGq.js → dspy-rlm-engine-D0h-P2Mz.js} +2 -2
  38. package/dist/{dspy-rlm-engine-US8YsYGq.js.map → dspy-rlm-engine-D0h-P2Mz.js.map} +1 -1
  39. package/dist/{engine-4_Q4oujc.d.ts → engine-CaSqEVlL.d.ts} +4 -4
  40. package/dist/{engine-4_Q4oujc.d.ts.map → engine-CaSqEVlL.d.ts.map} +1 -1
  41. package/dist/evaluation.d.ts +2 -2
  42. package/dist/{exact-types-KGxBWH4b.d.ts → exact-types-BBMMYk3g.d.ts} +2 -2
  43. package/dist/{exact-types-KGxBWH4b.d.ts.map → exact-types-BBMMYk3g.d.ts.map} +1 -1
  44. package/dist/experiment/index.d.ts +1 -1
  45. package/dist/{external-optimizer-process-KLcw0Vnc.js → external-optimizer-process-CIV4EqiT.js} +2 -2
  46. package/dist/{external-optimizer-process-KLcw0Vnc.js.map → external-optimizer-process-CIV4EqiT.js.map} +1 -1
  47. package/dist/{external-optimizer-subprocess-CkyUUV7h.js → external-optimizer-subprocess-BmKtH3T6.js} +2 -2
  48. package/dist/{external-optimizer-subprocess-CkyUUV7h.js.map → external-optimizer-subprocess-BmKtH3T6.js.map} +1 -1
  49. package/dist/{extract-usage-DFATEuWW.js → extract-usage-BrnzRJ6H.js} +4 -3
  50. package/dist/extract-usage-BrnzRJ6H.js.map +1 -0
  51. package/dist/{feedback-trajectory-BXCGTRkz.d.ts → feedback-trajectory-C6NJxXEa.d.ts} +3 -3
  52. package/dist/{feedback-trajectory-BXCGTRkz.d.ts.map → feedback-trajectory-C6NJxXEa.d.ts.map} +1 -1
  53. package/dist/{index-Cuhxk05B.d.ts → index-CGAwP9l3.d.ts} +8 -8
  54. package/dist/{index-Cuhxk05B.d.ts.map → index-CGAwP9l3.d.ts.map} +1 -1
  55. package/dist/{index-DBk_4UPs.d.ts → index-CIkxRsLS.d.ts} +7 -7
  56. package/dist/{index-DBk_4UPs.d.ts.map → index-CIkxRsLS.d.ts.map} +1 -1
  57. package/dist/{index-CAtNOBQY.d.ts → index-Ce2HACcP.d.ts} +7 -7
  58. package/dist/{index-CAtNOBQY.d.ts.map → index-Ce2HACcP.d.ts.map} +1 -1
  59. package/dist/index.d.ts +19 -19
  60. package/dist/index.js +11 -11
  61. package/dist/{integrity-CaeNeusS.d.ts → integrity-BWO6RPxv.d.ts} +2 -2
  62. package/dist/{integrity-CaeNeusS.d.ts.map → integrity-BWO6RPxv.d.ts.map} +1 -1
  63. package/dist/{jev-review-DX6MI_jq.d.ts → jev-review-Cw06AKuF.d.ts} +2 -2
  64. package/dist/{jev-review-DX6MI_jq.d.ts.map → jev-review-Cw06AKuF.d.ts.map} +1 -1
  65. package/dist/jev.d.ts +3 -3
  66. package/dist/{llm-client-Bhqoglar.js → llm-client-DmCNzrc9.js} +77 -60
  67. package/dist/llm-client-DmCNzrc9.js.map +1 -0
  68. package/dist/{llm-judge-C-0P1WiT.js → llm-judge-EUMHOZOQ.js} +4 -4
  69. package/dist/{llm-judge-C-0P1WiT.js.map → llm-judge-EUMHOZOQ.js.map} +1 -1
  70. package/dist/{matrix-BucOjLF1.d.ts → matrix-BqHiMKIj.d.ts} +2 -2
  71. package/dist/{matrix-BucOjLF1.d.ts.map → matrix-BqHiMKIj.d.ts.map} +1 -1
  72. package/dist/meta-eval/index.d.ts +1 -1
  73. package/dist/multishot/golden/index.d.ts +1 -1
  74. package/dist/multishot/index.d.ts +2 -2
  75. package/dist/openapi.json +1 -1
  76. package/dist/{prime-protocol-T0i6xcAs.d.ts → prime-protocol-IoN4Qb6c.d.ts} +2 -2
  77. package/dist/{prime-protocol-T0i6xcAs.d.ts.map → prime-protocol-IoN4Qb6c.d.ts.map} +1 -1
  78. package/dist/{produced-state-CR2tAPLf.js → produced-state-g9BPgu4D.js} +3 -3
  79. package/dist/{produced-state-CR2tAPLf.js.map → produced-state-g9BPgu4D.js.map} +1 -1
  80. package/dist/{abort-signal-CtzAM_sJ.js → proposal-findings-CXblsskH.js} +2 -11
  81. package/dist/proposal-findings-CXblsskH.js.map +1 -0
  82. package/dist/{registry-Bu3lNole.d.ts → registry-CT-hMSkR.d.ts} +4 -4
  83. package/dist/{registry-Bu3lNole.d.ts.map → registry-CT-hMSkR.d.ts.map} +1 -1
  84. package/dist/{researcher-DojEMb7E.d.ts → researcher-zTpxNJBy.d.ts} +3 -3
  85. package/dist/{researcher-DojEMb7E.d.ts.map → researcher-zTpxNJBy.d.ts.map} +1 -1
  86. package/dist/rl.d.ts +4 -4
  87. package/dist/search/index.d.ts +2 -2
  88. package/dist/{search-kernel-B8RC6BlK.d.ts → search-kernel-C5jua_UB.d.ts} +2 -2
  89. package/dist/{search-kernel-B8RC6BlK.d.ts.map → search-kernel-C5jua_UB.d.ts.map} +1 -1
  90. package/dist/{semantic-concept-judge-BcjYg37z.js → semantic-concept-judge-BgWxa4L_.js} +4 -4
  91. package/dist/{semantic-concept-judge-BcjYg37z.js.map → semantic-concept-judge-BgWxa4L_.js.map} +1 -1
  92. package/dist/{series-convergence-DY7ha0kx.d.ts → series-convergence-DLy0bQMV.d.ts} +2 -2
  93. package/dist/{series-convergence-DY7ha0kx.d.ts.map → series-convergence-DLy0bQMV.d.ts.map} +1 -1
  94. package/dist/{server-B4jMhqQn.js → server-CoBZO1fj.js} +2 -2
  95. package/dist/{server-B4jMhqQn.js.map → server-CoBZO1fj.js.map} +1 -1
  96. package/dist/{skillopt-optimization-method-Bls9t-G_.js → skillopt-optimization-method-DZrdQGZl.js} +5 -5
  97. package/dist/{skillopt-optimization-method-Bls9t-G_.js.map → skillopt-optimization-method-DZrdQGZl.js.map} +1 -1
  98. package/dist/{statistical-heldout-DJtQAUZB.d.ts → statistical-heldout-CJYAO-4a.d.ts} +2 -2
  99. package/dist/{statistical-heldout-DJtQAUZB.d.ts.map → statistical-heldout-CJYAO-4a.d.ts.map} +1 -1
  100. package/dist/{store-tool-spans-Biio4_Nw.js → store-tool-spans-D5kOU0mr.js} +2 -2
  101. package/dist/{store-tool-spans-Biio4_Nw.js.map → store-tool-spans-D5kOU0mr.js.map} +1 -1
  102. package/dist/{store-tool-spans-fkNF7Q9Y.d.ts → store-tool-spans-fIE31bU8.d.ts} +5 -5
  103. package/dist/{store-tool-spans-fkNF7Q9Y.d.ts.map → store-tool-spans-fIE31bU8.d.ts.map} +1 -1
  104. package/dist/{tool-groups-Zm84Pqpk.d.ts → tool-groups-DP8b5kjF.d.ts} +3 -3
  105. package/dist/tool-groups-DP8b5kjF.d.ts.map +1 -0
  106. package/dist/{trace-questions--lnJTaou.d.ts → trace-questions-Cd0Fyhbv.d.ts} +3 -3
  107. package/dist/{trace-questions--lnJTaou.d.ts.map → trace-questions-Cd0Fyhbv.d.ts.map} +1 -1
  108. package/dist/trace-repair/index.d.ts +1 -1
  109. package/dist/traces.d.ts +5 -5
  110. package/dist/traces.js +2 -2
  111. package/dist/{types-CeDfCRXp.d.ts → types-6VEehmEg.d.ts} +2 -2
  112. package/dist/{types-CeDfCRXp.d.ts.map → types-6VEehmEg.d.ts.map} +1 -1
  113. package/dist/{types-C0bWoSKC.d.ts → types-DLxe96rp.d.ts} +2 -2
  114. package/dist/{types-C0bWoSKC.d.ts.map → types-DLxe96rp.d.ts.map} +1 -1
  115. package/dist/{types-khIUQ0O5.d.ts → types-Duc6xOoW.d.ts} +3 -3
  116. package/dist/{types-khIUQ0O5.d.ts.map → types-Duc6xOoW.d.ts.map} +1 -1
  117. package/dist/{types-B6JadxWL.d.ts → types-hH9APahd.d.ts} +2 -2
  118. package/dist/{types-B6JadxWL.d.ts.map → types-hH9APahd.d.ts.map} +1 -1
  119. package/dist/wire/index.d.ts +2 -2
  120. package/dist/wire/index.js +1 -1
  121. package/docs/changes/llm-physical-attempts.md +30 -0
  122. package/docs/changes/shared-model-request-lifetime.md +30 -0
  123. package/docs/concepts.md +8 -0
  124. package/docs/http-dispatch.md +33 -0
  125. package/docs/proofs/router-cache-usage-20261001/after.json +2058 -0
  126. package/docs/proofs/router-cache-usage-20261001/component-projections.json +584 -0
  127. package/docs/proofs/router-cache-usage-20261001/component-projections.nested-only.json +306 -0
  128. package/docs/proofs/router-cache-usage-20261001/manifest.json +32 -0
  129. package/docs/proofs/router-cache-usage-20261001/summary.json +49 -0
  130. package/docs/proofs/router-cache-usage-20261001/summary.nested-only.json +29 -0
  131. package/package.json +1 -1
  132. package/dist/abort-signal-CtzAM_sJ.js.map +0 -1
  133. package/dist/benchmark-command-DFs_i62N.js.map +0 -1
  134. package/dist/extract-usage-DFATEuWW.js.map +0 -1
  135. package/dist/llm-client-Bhqoglar.js.map +0 -1
  136. package/dist/tool-groups-Zm84Pqpk.d.ts.map +0 -1
@@ -0,0 +1,306 @@
1
+ [
2
+ {
3
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:0d0be573-dfa1-4e93-96e1-1875cd8790d2:turn:1",
4
+ "kind": "Only recorded component fields removed; no invented values.",
5
+ "promptCacheFallback": {
6
+ "input": 898,
7
+ "output": 13,
8
+ "reasoning": 0,
9
+ "cached": 0,
10
+ "cacheWrite": 0
11
+ },
12
+ "allCacheComponentsRemoved": {
13
+ "input": 898,
14
+ "output": 13,
15
+ "reasoning": 0
16
+ }
17
+ },
18
+ {
19
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:0d0be573-dfa1-4e93-96e1-1875cd8790d2:turn:2",
20
+ "kind": "Only recorded component fields removed; no invented values.",
21
+ "promptCacheFallback": {
22
+ "input": 80317,
23
+ "output": 34,
24
+ "reasoning": 0,
25
+ "cached": 0,
26
+ "cacheWrite": 80314
27
+ },
28
+ "allCacheComponentsRemoved": {
29
+ "input": 80317,
30
+ "output": 34,
31
+ "reasoning": 0
32
+ }
33
+ },
34
+ {
35
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:0d0be573-dfa1-4e93-96e1-1875cd8790d2:turn:3",
36
+ "kind": "Only recorded component fields removed; no invented values.",
37
+ "promptCacheFallback": {
38
+ "input": 81296,
39
+ "output": 211,
40
+ "reasoning": 0,
41
+ "cached": 80314,
42
+ "cacheWrite": 979
43
+ },
44
+ "allCacheComponentsRemoved": {
45
+ "input": 81296,
46
+ "output": 211,
47
+ "reasoning": 0
48
+ }
49
+ },
50
+ {
51
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:0d0be573-dfa1-4e93-96e1-1875cd8790d2:turn:4",
52
+ "kind": "Only recorded component fields removed; no invented values.",
53
+ "promptCacheFallback": {
54
+ "input": 81534,
55
+ "output": 79,
56
+ "reasoning": 0,
57
+ "cached": 81293,
58
+ "cacheWrite": 238
59
+ },
60
+ "allCacheComponentsRemoved": {
61
+ "input": 81534,
62
+ "output": 79,
63
+ "reasoning": 0
64
+ }
65
+ },
66
+ {
67
+ "callId": "sha256:946fdb890ecfc1a490f90e0a88812d088f955eef47f782ba12a7982fe77e692a:0:0d0be573-dfa1-4e93-96e1-1875cd8790d2:turn:3",
68
+ "kind": "Only recorded component fields removed; no invented values.",
69
+ "promptCacheFallback": {
70
+ "input": 2189,
71
+ "output": 64,
72
+ "reasoning": 0,
73
+ "cached": 1864,
74
+ "cacheWrite": 322
75
+ },
76
+ "allCacheComponentsRemoved": {
77
+ "input": 2189,
78
+ "output": 64,
79
+ "reasoning": 0
80
+ }
81
+ },
82
+ {
83
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:96d197d7-d362-4b4f-a78a-1c485d56d7c5:turn:1",
84
+ "kind": "Only recorded component fields removed; no invented values.",
85
+ "promptCacheFallback": {
86
+ "input": 898,
87
+ "output": 13,
88
+ "reasoning": 0,
89
+ "cached": 0,
90
+ "cacheWrite": 0
91
+ },
92
+ "allCacheComponentsRemoved": {
93
+ "input": 898,
94
+ "output": 13,
95
+ "reasoning": 0
96
+ }
97
+ },
98
+ {
99
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:96d197d7-d362-4b4f-a78a-1c485d56d7c5:turn:2",
100
+ "kind": "Only recorded component fields removed; no invented values.",
101
+ "promptCacheFallback": {
102
+ "input": 80317,
103
+ "output": 34,
104
+ "reasoning": 0,
105
+ "cached": 80314,
106
+ "cacheWrite": 0
107
+ },
108
+ "allCacheComponentsRemoved": {
109
+ "input": 80317,
110
+ "output": 34,
111
+ "reasoning": 0
112
+ }
113
+ },
114
+ {
115
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:96d197d7-d362-4b4f-a78a-1c485d56d7c5:turn:3",
116
+ "kind": "Only recorded component fields removed; no invented values.",
117
+ "promptCacheFallback": {
118
+ "input": 81296,
119
+ "output": 224,
120
+ "reasoning": 0,
121
+ "cached": 80314,
122
+ "cacheWrite": 979
123
+ },
124
+ "allCacheComponentsRemoved": {
125
+ "input": 81296,
126
+ "output": 224,
127
+ "reasoning": 0
128
+ }
129
+ },
130
+ {
131
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:96d197d7-d362-4b4f-a78a-1c485d56d7c5:turn:4",
132
+ "kind": "Only recorded component fields removed; no invented values.",
133
+ "promptCacheFallback": {
134
+ "input": 81547,
135
+ "output": 82,
136
+ "reasoning": 0,
137
+ "cached": 81293,
138
+ "cacheWrite": 251
139
+ },
140
+ "allCacheComponentsRemoved": {
141
+ "input": 81547,
142
+ "output": 82,
143
+ "reasoning": 0
144
+ }
145
+ },
146
+ {
147
+ "callId": "sha256:5dca9781fdfa199c2c2ee2ad1a9df1dbe18931967dffc60243b64cd1380c5f31:0:96d197d7-d362-4b4f-a78a-1c485d56d7c5:turn:1",
148
+ "kind": "Only recorded component fields removed; no invented values.",
149
+ "promptCacheFallback": {
150
+ "input": 898,
151
+ "output": 13,
152
+ "reasoning": 0,
153
+ "cached": 0,
154
+ "cacheWrite": 0
155
+ },
156
+ "allCacheComponentsRemoved": {
157
+ "input": 898,
158
+ "output": 13,
159
+ "reasoning": 0
160
+ }
161
+ },
162
+ {
163
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:1",
164
+ "kind": "Only recorded component fields removed; no invented values.",
165
+ "promptCacheFallback": {
166
+ "input": 952,
167
+ "output": 24,
168
+ "reasoning": 0,
169
+ "cached": 0,
170
+ "cacheWrite": 0
171
+ },
172
+ "allCacheComponentsRemoved": {
173
+ "input": 952,
174
+ "output": 24,
175
+ "reasoning": 0
176
+ }
177
+ },
178
+ {
179
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:2",
180
+ "kind": "Only recorded component fields removed; no invented values.",
181
+ "promptCacheFallback": {
182
+ "input": 1061,
183
+ "output": 34,
184
+ "reasoning": 0,
185
+ "cached": 0,
186
+ "cacheWrite": 1058
187
+ },
188
+ "allCacheComponentsRemoved": {
189
+ "input": 1061,
190
+ "output": 34,
191
+ "reasoning": 0
192
+ }
193
+ },
194
+ {
195
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:3",
196
+ "kind": "Only recorded component fields removed; no invented values.",
197
+ "promptCacheFallback": {
198
+ "input": 2040,
199
+ "output": 211,
200
+ "reasoning": 0,
201
+ "cached": 1058,
202
+ "cacheWrite": 979
203
+ },
204
+ "allCacheComponentsRemoved": {
205
+ "input": 2040,
206
+ "output": 211,
207
+ "reasoning": 0
208
+ }
209
+ },
210
+ {
211
+ "callId": "sha256:2f7f9ef5fe23b740b558604ca7b4d6af15452f1160575521a2e0d5f0b3fa12bf:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:4",
212
+ "kind": "Only recorded component fields removed; no invented values.",
213
+ "promptCacheFallback": {
214
+ "input": 2278,
215
+ "output": 106,
216
+ "reasoning": 0,
217
+ "cached": 2037,
218
+ "cacheWrite": 238
219
+ },
220
+ "allCacheComponentsRemoved": {
221
+ "input": 2278,
222
+ "output": 106,
223
+ "reasoning": 0
224
+ }
225
+ },
226
+ {
227
+ "callId": "sha256:946fdb890ecfc1a490f90e0a88812d088f955eef47f782ba12a7982fe77e692a:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:3",
228
+ "kind": "Only recorded component fields removed; no invented values.",
229
+ "promptCacheFallback": {
230
+ "input": 2243,
231
+ "output": 76,
232
+ "reasoning": 0,
233
+ "cached": 1918,
234
+ "cacheWrite": 322
235
+ },
236
+ "allCacheComponentsRemoved": {
237
+ "input": 2243,
238
+ "output": 76,
239
+ "reasoning": 0
240
+ }
241
+ },
242
+ {
243
+ "callId": "sha256:5dca9781fdfa199c2c2ee2ad1a9df1dbe18931967dffc60243b64cd1380c5f31:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:1",
244
+ "kind": "Only recorded component fields removed; no invented values.",
245
+ "promptCacheFallback": {
246
+ "input": 952,
247
+ "output": 24,
248
+ "reasoning": 0,
249
+ "cached": 0,
250
+ "cacheWrite": 0
251
+ },
252
+ "allCacheComponentsRemoved": {
253
+ "input": 952,
254
+ "output": 24,
255
+ "reasoning": 0
256
+ }
257
+ },
258
+ {
259
+ "callId": "sha256:5dca9781fdfa199c2c2ee2ad1a9df1dbe18931967dffc60243b64cd1380c5f31:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:2",
260
+ "kind": "Only recorded component fields removed; no invented values.",
261
+ "promptCacheFallback": {
262
+ "input": 1061,
263
+ "output": 34,
264
+ "reasoning": 0,
265
+ "cached": 1058,
266
+ "cacheWrite": 0
267
+ },
268
+ "allCacheComponentsRemoved": {
269
+ "input": 1061,
270
+ "output": 34,
271
+ "reasoning": 0
272
+ }
273
+ },
274
+ {
275
+ "callId": "sha256:5dca9781fdfa199c2c2ee2ad1a9df1dbe18931967dffc60243b64cd1380c5f31:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:3",
276
+ "kind": "Only recorded component fields removed; no invented values.",
277
+ "promptCacheFallback": {
278
+ "input": 2040,
279
+ "output": 226,
280
+ "reasoning": 0,
281
+ "cached": 2037,
282
+ "cacheWrite": 0
283
+ },
284
+ "allCacheComponentsRemoved": {
285
+ "input": 2040,
286
+ "output": 226,
287
+ "reasoning": 0
288
+ }
289
+ },
290
+ {
291
+ "callId": "sha256:5dca9781fdfa199c2c2ee2ad1a9df1dbe18931967dffc60243b64cd1380c5f31:0:287b8bf4-edb6-473c-a27c-6de40881d1c4:turn:4",
292
+ "kind": "Only recorded component fields removed; no invented values.",
293
+ "promptCacheFallback": {
294
+ "input": 2293,
295
+ "output": 88,
296
+ "reasoning": 0,
297
+ "cached": 2037,
298
+ "cacheWrite": 253
299
+ },
300
+ "allCacheComponentsRemoved": {
301
+ "input": 2293,
302
+ "output": 88,
303
+ "reasoning": 0
304
+ }
305
+ }
306
+ ]
@@ -0,0 +1,32 @@
1
+ {
2
+ "schema": "agent-eval.usage-proof.manifest.v1",
3
+ "files": [
4
+ {
5
+ "file": "after.json",
6
+ "bytes": 68696,
7
+ "sha256": "4015229a91eb49b89d8fb546372a0e0384dcffd4855a32162f59df2fc25e7246"
8
+ },
9
+ {
10
+ "file": "component-projections.json",
11
+ "bytes": 25504,
12
+ "sha256": "c8cdc6c5548b2f9cbc7e04eef1c76daaa0ea4bc900037196dc861123080d67b8"
13
+ },
14
+ {
15
+ "file": "component-projections.nested-only.json",
16
+ "bytes": 8859,
17
+ "sha256": "a062bd32bfd800559b3d4d19424369e35e3cbb8fcbfc49a0f3cc2a164c54132d"
18
+ },
19
+ {
20
+ "file": "summary.json",
21
+ "bytes": 2241,
22
+ "sha256": "ad85993e2470098d125bc36ca4fc433f5795bf3643fee3668ca4c767489f5d73"
23
+ },
24
+ {
25
+ "file": "summary.nested-only.json",
26
+ "bytes": 1359,
27
+ "sha256": "acd477c4b2c7968dad7cc6cb5dd4b05a493fbb4a2ed96cd6bda60a8d58981700"
28
+ }
29
+ ],
30
+ "privateOriginals": "/mnt/traces/eval-router-cache-usage-20261001",
31
+ "modelInference": false
32
+ }
@@ -0,0 +1,49 @@
1
+ {
2
+ "schema": "agent-eval.real-usage-replay.v1",
3
+ "sourceRevision": "443abdf0 plus minimal usage-reader change",
4
+ "before": {
5
+ "file": "/home/drew/webb/_wt/lab-evidence-unified/node_modules/.pnpm/@tangle-network+agent-eval@0.203.0/node_modules/@tangle-network/agent-eval/dist/index.js",
6
+ "sha256": "ca8daec8e5c02f31f98142210a8e00c6c48552ffd4e577538fd730a4edfd59a9"
7
+ },
8
+ "afterModule": {
9
+ "file": "/home/drew/code/_wt/eval-router-cache-usage-20261001/dist/index.js",
10
+ "sha256": "1dde3ce40faf7cff852a3b46eddb2a9f9a5bc4f48deea05ebc3dcb66bba41cb3"
11
+ },
12
+ "realResponses": 45,
13
+ "missingCacheWritesBefore": 34,
14
+ "missingCacheWritesAfter": 0,
15
+ "existingComponentsPreserved": true,
16
+ "componentProjectionControls": 34,
17
+ "modelInference": false,
18
+ "scientificUnits": 0,
19
+ "coverageLimit": "These45 actual responses exercise both newly supported shapes, including23 explicit zero and11 positive cache-write values. Missing cache components remain omitted. Replay cannot establish full physical-call coverage or billing.",
20
+ "realExplicitNestedCacheWrites": 19,
21
+ "newlyPreservedCacheWrites": 34,
22
+ "newlyPreservedZeroCacheWrites": 23,
23
+ "newlyPreservedPositiveCacheWrites": 11,
24
+ "promptCacheOnlyNewComponents": 15,
25
+ "amendment": {
26
+ "originalSummarySha256": "e055d668b819c577978c1cecdb8d8836adc34cc7776a10a5a59be27d12024ed8",
27
+ "cause": "Original summary selected nested details only. Its19 count excluded15 prompt_cache-only responses; its positive-unobserved statement did not describe the full population. Raw inputs and before/after projections remain unchanged.",
28
+ "nestedDetails": {
29
+ "newComponents": 19,
30
+ "zero": 19,
31
+ "positive": 0
32
+ },
33
+ "promptCacheOnly": {
34
+ "newComponents": 15,
35
+ "zero": 4,
36
+ "positive": 11
37
+ },
38
+ "reviewInstrument": "/mnt/traces/discovery-issue-review-20261001/eval906-independent-replay.mjs",
39
+ "reviewProof": "/mnt/traces/discovery-issue-review-20261001/eval906-frozen-proof"
40
+ },
41
+ "sourceSha256": "a3a8b6ed7a0fb815dc73a03f59b662a8a3fd4ecc0e45caea819e808b080c38f4",
42
+ "sourceBaseRevision": "443abdf0",
43
+ "checks": {
44
+ "build": "passed",
45
+ "typecheck": "passed",
46
+ "verifyPackage": "passed",
47
+ "unitTests": "not run per task instruction"
48
+ }
49
+ }
@@ -0,0 +1,29 @@
1
+ {
2
+ "schema": "agent-eval.real-usage-replay.v1",
3
+ "sourceRevision": "443abdf0 plus minimal usage-reader change",
4
+ "before": {
5
+ "file": "/home/drew/webb/_wt/lab-evidence-unified/node_modules/.pnpm/@tangle-network+agent-eval@0.203.0/node_modules/@tangle-network/agent-eval/dist/index.js",
6
+ "sha256": "ca8daec8e5c02f31f98142210a8e00c6c48552ffd4e577538fd730a4edfd59a9"
7
+ },
8
+ "afterModule": {
9
+ "file": "/home/drew/code/_wt/eval-router-cache-usage-20261001/dist/index.js",
10
+ "sha256": "1dde3ce40faf7cff852a3b46eddb2a9f9a5bc4f48deea05ebc3dcb66bba41cb3"
11
+ },
12
+ "realResponses": 45,
13
+ "realExplicitCacheWrites": 19,
14
+ "missingCacheWritesBefore": 19,
15
+ "missingCacheWritesAfter": 0,
16
+ "existingComponentsPreserved": true,
17
+ "componentProjectionControls": 19,
18
+ "modelInference": false,
19
+ "scientificUnits": 0,
20
+ "coverageLimit": "All newly handled cache-write values in these retained Router responses are explicit zero. Positive counts from these aliases remain unobserved; existing Anthropic counters are unchanged. Replay cannot establish full physical-call coverage or billing.",
21
+ "sourceSha256": "a3a8b6ed7a0fb815dc73a03f59b662a8a3fd4ecc0e45caea819e808b080c38f4",
22
+ "sourceBaseRevision": "443abdf0",
23
+ "checks": {
24
+ "build": "passed",
25
+ "typecheck": "passed",
26
+ "verifyPackage": "passed",
27
+ "unitTests": "not run per task instruction"
28
+ }
29
+ }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-eval",
3
- "version": "0.203.0",
3
+ "version": "0.203.1",
4
4
  "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
5
5
  "homepage": "https://github.com/tangle-network/agent-eval#readme",
6
6
  "repository": {
@@ -1 +0,0 @@
1
- {"version":3,"file":"abort-signal-CtzAM_sJ.js","names":[],"sources":["../src/analyst/proposal-findings.ts","../src/abort-signal.ts"],"sourcesContent":["import { z } from 'zod'\nimport type { ProposalFinding } from './types'\n\nconst ProposalFindingSchema = z\n .object({\n schema_version: z.literal('1.0.0'),\n finding_id: z.string().min(1),\n analyst_id: z.string().min(1),\n produced_at: z.string().min(1),\n severity: z.enum(['critical', 'high', 'medium', 'low', 'info']),\n area: z.string().min(1),\n claim: z.string().min(1),\n rationale: z.string().optional(),\n evidence_refs: z.array(\n z\n .object({\n kind: z.enum(['span', 'event', 'artifact', 'finding', 'metric']),\n uri: z.string().min(1),\n excerpt: z.string().optional(),\n })\n .strict(),\n ),\n recommended_action: z.string().optional(),\n validation_plan: z.string().optional(),\n confidence: z.number().min(0).max(1),\n subject: z.string().optional(),\n derived_from_judge: z.boolean().optional(),\n metadata: z.record(z.string(), z.unknown()).optional(),\n proposal_origin: z.enum(['search', 'production']),\n })\n .strict() satisfies z.ZodType<ProposalFinding>\n\n/** True when a finding names a source candidate generation may learn from. */\nexport function isProposalFinding(finding: unknown): finding is ProposalFinding {\n return ProposalFindingSchema.safeParse(finding).success\n}\n\n/**\n * Reject findings whose source has not been explicitly admitted for candidate\n * generation. Search feedback and observed production behavior are allowed;\n * final evaluation data has no allowed origin.\n */\nexport function assertProposalFindings(\n findings: unknown,\n context = 'proposal findings',\n): ReadonlyArray<ProposalFinding> {\n if (!Array.isArray(findings)) {\n throw new TypeError(`${context}: expected an array`)\n }\n const rejected = findings.flatMap((finding, index) =>\n isProposalFinding(finding) ? [] : [findingLabel(finding, index)],\n )\n if (rejected.length > 0) {\n throw new Error(\n `${context}: every finding must match AnalystFinding and declare ` +\n `proposal_origin as search or production. ` +\n `Rejected findings: [${rejected.join(', ')}].`,\n )\n }\n return findings as ReadonlyArray<ProposalFinding>\n}\n\nfunction findingLabel(finding: unknown, index: number): string {\n if (typeof finding !== 'object' || finding === null) return `index ${index}`\n const id = (finding as { finding_id?: unknown }).finding_id\n return typeof id === 'string' && id.length > 0 ? id : `index ${index}`\n}\n","/** Combine active cancellation sources without wrapping a single source. */\nexport function combineAbortSignals(\n ...signals: Array<AbortSignal | undefined>\n): AbortSignal | undefined {\n const active = [\n ...new Set(signals.filter((signal): signal is AbortSignal => signal !== undefined)),\n ]\n if (active.length === 0) return undefined\n if (active.length === 1) return active[0]\n return AbortSignal.any(active)\n}\n"],"mappings":";;AAGA,MAAM,wBAAwB,EAC3B,OAAO;CACN,gBAAgB,EAAE,QAAQ,OAAO;CACjC,YAAY,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;CAC5B,YAAY,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;CAC5B,aAAa,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;CAC7B,UAAU,EAAE,KAAK;EAAC;EAAY;EAAQ;EAAU;EAAO;CAAM,CAAC;CAC9D,MAAM,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;CACtB,OAAO,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;CACvB,WAAW,EAAE,OAAO,CAAC,CAAC,SAAS;CAC/B,eAAe,EAAE,MACf,EACG,OAAO;EACN,MAAM,EAAE,KAAK;GAAC;GAAQ;GAAS;GAAY;GAAW;EAAQ,CAAC;EAC/D,KAAK,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC;EACrB,SAAS,EAAE,OAAO,CAAC,CAAC,SAAS;CAC/B,CAAC,CAAC,CACD,OAAO,CACZ;CACA,oBAAoB,EAAE,OAAO,CAAC,CAAC,SAAS;CACxC,iBAAiB,EAAE,OAAO,CAAC,CAAC,SAAS;CACrC,YAAY,EAAE,OAAO,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC;CACnC,SAAS,EAAE,OAAO,CAAC,CAAC,SAAS;CAC7B,oBAAoB,EAAE,QAAQ,CAAC,CAAC,SAAS;CACzC,UAAU,EAAE,OAAO,EAAE,OAAO,GAAG,EAAE,QAAQ,CAAC,CAAC,CAAC,SAAS;CACrD,iBAAiB,EAAE,KAAK,CAAC,UAAU,YAAY,CAAC;AAClD,CAAC,CAAC,CACD,OAAO;;AAGV,SAAgB,kBAAkB,SAA8C;CAC9E,OAAO,sBAAsB,UAAU,OAAO,CAAC,CAAC;AAClD;;;;;;AAOA,SAAgB,uBACd,UACA,UAAU,qBACsB;CAChC,IAAI,CAAC,MAAM,QAAQ,QAAQ,GACzB,MAAM,IAAI,UAAU,GAAG,QAAQ,oBAAoB;CAErD,MAAM,WAAW,SAAS,SAAS,SAAS,UAC1C,kBAAkB,OAAO,IAAI,CAAC,IAAI,CAAC,aAAa,SAAS,KAAK,CAAC,CACjE;CACA,IAAI,SAAS,SAAS,GACpB,MAAM,IAAI,MACR,GAAG,QAAQ,qHAEc,SAAS,KAAK,IAAI,EAAE,GAC/C;CAEF,OAAO;AACT;AAEA,SAAS,aAAa,SAAkB,OAAuB;CAC7D,IAAI,OAAO,YAAY,YAAY,YAAY,MAAM,OAAO,SAAS;CACrE,MAAM,KAAM,QAAqC;CACjD,OAAO,OAAO,OAAO,YAAY,GAAG,SAAS,IAAI,KAAK,SAAS;AACjE;;;;ACjEA,SAAgB,oBACd,GAAG,SACsB;CACzB,MAAM,SAAS,CACb,GAAG,IAAI,IAAI,QAAQ,QAAQ,WAAkC,WAAW,KAAA,CAAS,CAAC,CACpF;CACA,IAAI,OAAO,WAAW,GAAG,OAAO,KAAA;CAChC,IAAI,OAAO,WAAW,GAAG,OAAO,OAAO;CACvC,OAAO,YAAY,IAAI,MAAM;AAC/B"}