Both runs' records agree. Every check behind this is on Proof

Diff

A is the baseline pz-59-agent-capture-baseline · 3214a1c5d383; B is the candidate pz-61-agent-capture-row-changed · 33ba22f318c0.

What changed? chose this comparison: compared with pz-59-agent-capture-baseline, the most recent earlier run whose final output differs.

The short answer

The runs first differ at agent_step, where 2 inputs changed.

Same: 0 · differ: 1.

  1. agent_stepFirst difference

Checked from the records. The same answer every time.

Model-call records, compared by onetrace

Each step where both runs hold a model-call record of the same name, in the words of the installed onetrace's comparator: its result, the mode it applied, what it rested on, and the rest of its report. It reads the two records; it runs no model.

Compared with the comparator's defaults: mode 1, fingerprint form tolerant.

agent_step · model_call.json (baseline, candidate)

  • result: could not compare: input not comparable (input.token_ids_digest: not observed)
  • mode 1
  • rests on: nothing beyond the preconditions
  • fingerprint: not compared (input not comparable (input.token_ids_digest: not observed))
  • output: not compared (input not comparable (input.token_ids_digest: not observed))
  • not compared; conditions not met: input not comparable (input.token_ids_digest: not observed); fingerprint 'tolerant' not recorded on A and B
  • records: A sha256:f0a2a8a78b96…, B sha256:9a3712103a2b…
    Each fingerprint in fullsha256:f0a2a8a78b9604ed99e1136147feb07c5f092bf0ca49d3909e0d27f138309d8bsha256:9a3712103a2bffde2d3438f3a69f1cee3d85d33720f131f3c30c5e8e5d2760fc
  • receipts: A verified, B verified
  • not claimed: hidden reasoning; semantic correctness; causality from a differing value alone; reproducibility across GPUs, versions or engines; hosted models' internals; anything not observed. Record equivalence is not correctness.

agent_step · model_call.2.json (baseline, candidate)

  • result: could not compare: batch context not observed: batch.size, batch.padded_width, batch.position, batch.members, batch.fillers, batch.batch_invariant
  • mode 1
  • rests on: nothing beyond the preconditions
  • fingerprint: not compared (batch context not observed: batch.size, batch.padded_width, batch.position, batch.members, batch.fillers, batch.batch_invariant)
  • output: not compared (batch context not observed: batch.size, batch.padded_width, batch.position, batch.members, batch.fillers, batch.batch_invariant)
  • not compared; conditions not met: batch context not observed: batch.size, batch.padded_width, batch.position, batch.members, batch.fillers, batch.batch_invariant; input not comparable (input.request_digest: not observed); fingerprint 'tolerant' not observed
  • records: A sha256:97c5212188b9…, B sha256:97c5212188b9…
    Each fingerprint in fullsha256:97c5212188b9b0ae0cc275225cef3f3ce635cc9f892006471c049454fb6c79fa
  • receipts: A verified, B verified
  • not claimed: hidden reasoning; semantic correctness; causality from a differing value alone; reproducibility across GPUs, versions or engines; hosted models' internals; anything not observed. Record equivalence is not correctness.

What changed between the two runs

The two runs differ.

agent_step · First differenceagent_stepFirst differenceinput run:pz-60-agent…input run:pz-60-agent-capture-baseline-subagent differsinput run:pz-62-agent…input run:pz-62-agent-capture-row-changed-subagent differs
  1. agent_stepFirst differenceinput run:pz-60-agent-capture-baseline-subagent differsinput run:pz-62-agent-capture-row-changed-subagent differsoutput model_call.steps.json differsoutput model_call.json differs

A link shows which recorded output a stage read. It does not by itself prove that one stage caused the next.

#nodebaselinecandidateannotationsresult
1agent_step11input run:pz-60-agent-capture-baseline-subagent differs; input run:pz-62-agent-capture-row-changed-subagent differs; output model_call.steps.json differs; output model_call.json differsFirst difference
baseline: nested run pz-60-agent-capture-baseline-subagent, its head recorded as
sha256:66521c85c6b6…sha256:66521c85c6b63ac150f8879decccf464d910046ecfd912e684fdfd5b66664dd3
· open its page
candidate: nested run pz-62-agent-capture-row-changed-subagent, its head recorded as
sha256:72e26c8224b3…sha256:72e26c8224b3594d45af79eba68673abcef4583702017eb2dba4522cdb106345
· open its page

agent_step: input run:pz-60-agent-capture-baseline-subagent changed: 66521c85c6b6 -> none

agent_step: input run:pz-62-agent-capture-row-changed-subagent changed: none -> 72e26c8224b3

At step agent_step: spans from your app's traces (the files under traces/)

From the app's own traces, as reported. Not checked by onetrace.

onetrace.stage agent_step

attributebaselinecandidate
duration28.0 ms17.0 msdiffers
onetrace.app.span_id5d3d846c2804fb5020fd583e7d0ffc03differs
onetrace.app.trace_ida3219e9d5de594d74ee68b731d07b464b728f85bab6e787aaa4373f6e15231c9differs
onetrace.inputs.digests["sha256:d77ccb69e3f9…", "sha256:66521c85c6b6…"]
Each fingerprint in fullsha256:d77ccb69e3f915ed75b4a2db3ff5893fdd0f433e02fdff100441fb843aae585bsha256:66521c85c6b63ac150f8879decccf464d910046ecfd912e684fdfd5b66664dd3
["sha256:d77ccb69e3f9…", "sha256:72e26c8224b3…"]
Each fingerprint in fullsha256:d77ccb69e3f915ed75b4a2db3ff5893fdd0f433e02fdff100441fb843aae585bsha256:72e26c8224b3594d45af79eba68673abcef4583702017eb2dba4522cdb106345
differs
onetrace.outputs.digests["sha256:6b2e802ce2ef…", "sha256:f0a2a8a78b96…", "sha256:97c5212188b9…", "sha256:3036e8bf5149…"]
Each fingerprint in fullsha256:6b2e802ce2ef5f0c5bbe648eaf721379fed6b1da575407368d3af6c2a606952esha256:f0a2a8a78b9604ed99e1136147feb07c5f092bf0ca49d3909e0d27f138309d8bsha256:97c5212188b9b0ae0cc275225cef3f3ce635cc9f892006471c049454fb6c79fasha256:3036e8bf514997c0c20570671c14c5d05fe6a431e1e1ad9b2d931a62df71aabc
["sha256:b891d1cf41d0…", "sha256:9a3712103a2b…", "sha256:97c5212188b9…", "sha256:3036e8bf5149…"]
Each fingerprint in fullsha256:b891d1cf41d086267ab96ca798215aeb800c8785fe8a6b68872568d8a026c37asha256:9a3712103a2bffde2d3438f3a69f1cee3d85d33720f131f3c30c5e8e5d2760fcsha256:97c5212188b9b0ae0cc275225cef3f3ce635cc9f892006471c049454fb6c79fasha256:3036e8bf514997c0c20570671c14c5d05fe6a431e1e1ad9b2d931a62df71aabc
differs
onetrace.receipt.digest
sha256:a537ab766176…sha256:a537ab7661763e94b38f1f553a7090a08edd646ec3b4f76f1c6ca325986c9e38
sha256:36e48c2b5c8f…sha256:36e48c2b5c8ff9cf791b59e87cb2af53b80257f95888c4f633d2c2246dfcc2fe
differs
13 attributes the same
attributebaselinecandidate
start, from the run's first span0.0 ms0.0 ms
onetrace.inputs.count22
onetrace.instrument.digest
sha256:0e5774cac5af…sha256:0e5774cac5af774b0eafa55f39a9997651cd54780b1b8c8d85172eda67d60fac
sha256:0e5774cac5af…sha256:0e5774cac5af774b0eafa55f39a9997651cd54780b1b8c8d85172eda67d60fac
onetrace.instrument.nameagent-planneragent-planner
onetrace.instrument.version1.0.01.0.0
onetrace.nodeagent_stepagent_step
onetrace.outcomeokok
onetrace.outputs.bytes1241212412
onetrace.outputs.count44
onetrace.stageagent_stepagent_step
onetrace.trust.externally-sourced.count22
onetrace.trust.model-generated.count11
onetrace.trust.operator-authored.count33

baseline: matches the receipt

candidate: matches the receipt

The app's spans at the first difference, side by side

Facts from the app's traces, not checked by onetrace, ranked: a status error first, then retries, a model, a span on one side only, tokens, then time.

No span view for the candidate run here: its trace file holds no span of the trace this step recorded.

What these spans do not say

  • The spans are the app's own report of what it did.
  • onetrace checks the join, the trace context it recorded for this step, not what the spans say.
  • A span difference is not a verdict and changes no verdict.

At the first difference: the model's rows and choices

Where both runs' model calls at the first differing step kept a per-step capture, what the two captures say there, from the steps files as the records name them. It reads the files; it runs no model.

model_call.json

Logits rows (L3)

The logits row changed at token 2; the chosen token first changed at token 4.

2 positions before token 4 had a changed logits row and the same chosen token.

the capture, as recordedbaselinecandidate
capture levelcapture level L3capture level L3
digest methoddigest method sha256-tree-512/v0digest method sha256-tree-512/v0
model runnermodel runner V1model runner V1
batch-invariant modebatch-invariant mode onbatch-invariant mode on

digests computed beyond the delivered tokens, counted and never compared: baseline 0, candidate 0

  • L3 shows whether the row the sampler chose from was the same bytes, not why it changed.
  • The cost and repeat figures in onetrace's docs are from one GPU, two models and greedy decoding.
  • A digest difference is not a verdict and changes no verdict.

Candidates (L2)

At token 4, the first token whose choice differs:

the candidate's token 40 is not among the baseline's top 4

the baseline's token 15 is not among the candidate's top 4

example data, constructed: the demo's own, not a real run's

k as recorded: 4 and 4

the capture, as recordedbaselinecandidate
capture levelcapture level L3capture level L3
k requestedk requested 4k requested 4
k returned, fewestk returned, fewest 4k returned, fewest 4
k returned, mostk returned, most 4k returned, most 4
sampling: allowed_token_idssampling: allowed_token_ids nonesampling: allowed_token_ids none
sampling: bad_wordssampling: bad_words nonesampling: bad_words none
sampling: frequency_penaltysampling: frequency_penalty 0.0sampling: frequency_penalty 0.0
sampling: logit_biassampling: logit_bias nonesampling: logit_bias none
sampling: logprobssampling: logprobs 4sampling: logprobs 4
sampling: min_tokenssampling: min_tokens 0sampling: min_tokens 0
sampling: presence_penaltysampling: presence_penalty 0.0sampling: presence_penalty 0.0
sampling: repetition_penaltysampling: repetition_penalty 1.0sampling: repetition_penalty 1.0
sampling: structured_outputssampling: structured_outputs nonesampling: structured_outputs none
sampling: temperaturesampling: temperature 0.0sampling: temperature 0.0
sampling: thinking_token_budgetsampling: thinking_token_budget nonesampling: thinking_token_budget none
  • A rank shows how the candidates were ordered, not why a different one was chosen.
  • L2 shows no probabilities unless the record holds them.
  • A candidate difference is not a verdict and changes no verdict.

Settings that changed

No recorded setting differs between the two runs.

The text diff

Shown with at most 200 lines per output (the SDK's default).

Open the text diff on its own page

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

agent_step · First difference

settings: none 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

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"

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"

Command: onetrace diff runs/pz-59-agent-capture-baseline runs/pz-61-agent-capture-row-changed --text

Repeat this yourself:

onetrace diff runs/pz-59-agent-capture-baseline runs/pz-61-agent-capture-row-changed
Not shown for graph-shaped runs: where the change started, and other runs that recorded the same value.

This console draws where the change started only for two linear runs; the SDK's localize report for this pair is below, as it wrote it.

The localize report as the SDK wrote it, with names from the records escaped
baseline   a  pz-59-agent-capture-baseline  (run)
candidate  b  pz-61-agent-capture-row-changed  (run)

localize: diverged

node            A     B     verdict
--------------------------------------------------------------------
agent_step      1     1     FIRST DIFFERENCE
                            input run:pz-60-agent-capture-baseline-subagent differs
                            input run:pz-62-agent-capture-row-changed-subagent differs
                            output model_call.steps.json differs
                            output model_call.json differs

first difference  agent_step
comparisons performed 1 of 1 nodes; same 0, FIRST DIFFERENCE 1, downstream 0, reconverged 0, COULD NOT CHECK 0

FIRST DIFFERENCE at node 'agent_step'
  instrument   agent-planner  1.0.0 -> 1.0.0
  config       0e5774cac5af -> 0e5774cac5af
    input run:pz-60-agent-capture-baseline-subagent differs
    input run:pz-62-agent-capture-row-changed-subagent differs
  blast radius not applicable — run-scoped

carried:
  [baseline] [NOT-RUN] originality on 2 receipts -- record is declared unanchored; this verifier can establish consistency, not originality
  [candidate] [NOT-RUN] originality on 2 receipts -- record is declared unanchored; this verifier can establish consistency, not originality
signing [baseline]: [SIGNED-UNTRUSTED] signatures/1.json: signature -- signed by an untrusted key sha256:6e20550ae0dc6b4471d54336d09d74d14f3f623b735045eddd053c444ec3b14c -- signer not on the reader's trust list
signing [candidate]: [SIGNED-UNTRUSTED] signatures/1.json: signature -- signed by an untrusted key sha256:6e20550ae0dc6b4471d54336d09d74d14f3f623b735045eddd053c444ec3b14c -- signer not on the reader's trust list

Repeat this yourself:

onetrace localize runs/pz-59-agent-capture-baseline runs/pz-61-agent-capture-row-changed

Other runs that recorded the same value are not looked for: this console doesn't match a graph comparison's first differences against other runs.

What may have happened

Explanations are not set up on this demo.

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