Comparisons / pz-59-agent-capture-baseline · 3214a1c5d383 → pz-61-agent-capture-row-changed · 33ba22f318c0 / Text diff

Text diff · agent_step

first difference: agent_step — output text changed; settings unchanged; inputs run:pz-60-agent-capture-baseline-subagent, run:pz-62-agent-capture-row-changed-subagent changed

Shown only for outputs whose bytes match their receipts in both runs. The diff never changes a verdict.

Changed, from the first difference on

Inputs that changed

input run:pz-60-agent-capture-baseline-subagent (operator-authored) removed: 66521c85c6b6; content not stored

input run:pz-62-agent-capture-row-changed-subagent (operator-authored) added: 72e26c8224b3; content not stored

agent_step

model_call.steps.json application/json Baseline: verified Candidate: verified

8 lines removed · 8 added

22    "digests": [
33      "01fc6be9a75534351c7eff4f69c4aea247e3956dd5e9fb410f500084480ad859",
44      "380b80e7fd15ba846177fbb22fd2a6885475ec48b78c5fd678ca0261a5612c97",
5-     "779b0cddb659ca3df3b55074d8a096271e0b06b9653609571420b578ff466101",
5+     "dbea6f8a0a9e202ceb23bbb0c05ec17cded2f84e7600d54875f420e6e311f29f",
6-     "33fbc77b8ea9b8701b30588741e9fef9cd7371be07e5c1d758f915d8e7264fe7",
6+     "eb21b01f9fce4a2bcf90d00e3cdeb1da53c2669e1623611e66c5fa3d02696b68",
7-     "9efff192fcd64e51ceec6289f57e4c9b657bb0c47cf458d2774efe824d64162e",
7+     "2ea4afc843783e05a2749741bc089b97bd9ac435dbc0fe330ebb230448cdaf59",
8-     "169cae47bad00a4cfe6ae86d6cd9ec23c16f27717c9feca5788859aec68f1380"
8+     "9dedf004b5b0f831c62321e380137732b3361080e0089ce9930930a3db19251e"
99    ],
1010    "level": "L3",
1111    "method": "sha256-tree-512/v0",
1414      "12",
1515      "13",
1616      "14",
17-     "15",
17+     "40",
18-     "16"
18+     "41"
1919    ],
2020    "top_k_ids": [
2121      [
4343        "9003"
4444      ],
4545      [
46-       "15",
46+       "40",
4747        "9001",
4848        "9002",
4949        "9003"
5050      ],
5151      [
52-       "16",
52+       "41",
5353        "9001",
5454        "9002",
5555        "9003"

By member, as JSON

Numbers are compared as written, so 1.0 and 1.00 differ.

0 added · 0 removed · 8 changed

  • /digests/2 changed: "779b0cddb659ca3df3b55074d8a096271e0b06b9653609571420b578ff466101" → "dbea6f8a0a9e202ceb23bbb0c05ec17cded2f84e7600d54875f420e6e311f29f"
  • /digests/3 changed: "33fbc77b8ea9b8701b30588741e9fef9cd7371be07e5c1d758f915d8e7264fe7" → "eb21b01f9fce4a2bcf90d00e3cdeb1da53c2669e1623611e66c5fa3d02696b68"
  • /digests/4 changed: "9efff192fcd64e51ceec6289f57e4c9b657bb0c47cf458d2774efe824d64162e" → "2ea4afc843783e05a2749741bc089b97bd9ac435dbc0fe330ebb230448cdaf59"
  • /digests/5 changed: "169cae47bad00a4cfe6ae86d6cd9ec23c16f27717c9feca5788859aec68f1380" → "9dedf004b5b0f831c62321e380137732b3361080e0089ce9930930a3db19251e"
  • /token_ids/4 changed: "15" → "40"
  • /token_ids/5 changed: "16" → "41"
  • /top_k_ids/4/0 changed: "15" → "40"
  • /top_k_ids/5/0 changed: "16" → "41"

agent_step

model_call.json application/json Baseline: verified Candidate: verified

1 line removed · 1 added

210210    "steps": {
211211      "source": "model_call.steps.json",
212212      "status": "observed",
213-     "value": "sha256:6b2e802ce2ef5f0c5bbe648eaf721379fed6b1da575407368d3af6c2a606952e"
213+     "value": "sha256:b891d1cf41d086267ab96ca798215aeb800c8785fe8a6b68872568d8a026c37a"
214214    },
215215    "steps.count": {
216216      "source": "example data, constructed for the demo; no model was called",

By member, as JSON

Numbers are compared as written, so 1.0 and 1.00 differ.

0 added · 0 removed · 1 changed

  • /steps/value changed: "sha256:6b2e802ce2ef5f0c5bbe648eaf721379fed6b1da575407368d3af6c2a606952e" → "sha256:b891d1cf41d086267ab96ca798215aeb800c8785fe8a6b68872568d8a026c37a"

Line numbers, positions and counts come from the SDK's text-diff document, unchanged.

A text diff shows what changed between two verified outputs. It doesn't say which answer is right.

This record shows what was verified and evaluated at the time — not what was ultimately true.