> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [rounds/long-tasks-reset-fix-1-after/README.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/long-tasks-reset-fix-1-after/README.md)
- [results/run-records/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/index.json)
- [rounds/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/index.json)
- [results/source-crosswalk/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/source-crosswalk/index.json)
- [rounds/STATUS.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/STATUS.md)
- [reproduce/round-inventory.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/reproduce/round-inventory.json)

# Long tasks on Kogen, after the reset fix

**Round ID:** long-tasks-reset-fix-1-after  
**Status:** DESCRIPTIVE

> Reviewed status from rounds/STATUS.md: DESCRIPTIVE.

> Round README and results text are source material. Numeric values not tied to a claim ledger record remain source-reported.

A before-and-after check of a Kogen fix for context resets on four long development tasks. This page holds the fixed version's first 8 cells and the comparison with the older version ([before page](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/long-tasks-reset-fix-1-before/README.md)). Two more repetitions of one task on the fixed version are on the [second-machine page](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/long-tasks-reset-fix-1-after-studio/README.md). The comparison tables on this page count all 10 fixed-version cells. The records, bundles and the counts in the last sections cover only the 8 cells run on the Linux server.

Observation only. Each task has 2 repetitions (4 for one task on the fixed version), one model (Sol, `gpt-6.1-sol`), Kogen's default settings, and two different machines across the comparison. No decision rule applies.

## Lanes

| Lane | Base Kogen | Patch | Models | Artifact sha256 |
| --- | --- | --- | --- | --- |
| fixed | [`56eecd57`](https://github.com/KogenAI/kogen/commit/56eecd572a6e07184863939254a90d9a2dc44e96) | [measurement.diff](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/long-tasks-reset-fix-1-after/patches/fixed/measurement.diff) `f4664506a979901c1508d3878631fec6472d6c905cb9a061832ed94a87799844` +26/-0 | defaults | `b5978ba30d0df8cb24102c59dacd5e591fed0a0cf4ba0517721bbb83bd4741ac` |


## What changed in Kogen

The older version is Kogen [`3f032206`](https://github.com/KogenAI/kogen/commit/3f0322062e4568ba1e7649054287508f866a0416). The fixed version is [`56eecd57`](https://github.com/KogenAI/kogen/commit/56eecd572a6e07184863939254a90d9a2dc44e96). Three commits separate them. The one that matters here makes a review reset tell the reviewer which source parts and images it has already received, so it does not have to re-read everything. The other two change how a stopped build resumes after a Git index refresh and how one other provider's tool turns are accepted. Neither should matter to these runs, but the two versions differ by all three. Both lanes carry the same 26-line measurement patch.

## Results

**Efficiency (observation).** After the fix, repeated reads after a reset fell from 265 in 8 cells to 9 in 10 cells. The largest repeat share of a resetting conversation's input fell from 45.7% to 4.6%. Tasks with a share above 10% went from 2 to 0. Resets still happen (17 in 8 cells before, 14 in 10 after); the change is that they no longer lead to wholesale re-reading. The repeated reads that remain are few: 1 to 5 reads in 4 cells.

**Correctness (open result, not a win).** 0 of 8 cells (older version) and 0 of 10 cells (fixed version) passed all hidden tests. Kogen does not yet complete these long tasks. 6 of 8 and 8 of 10 cells landed, and every landed cell failed some hidden tests. The other cells timed out at 3,600 s on one task, and those were graded on the unchanged starting tree. The fix was aimed at wasted reading, and it did not make these tasks pass.

**Correction (27 October 2026): some hidden tests were unfair.** A later audit of these four tasks found hidden tests that call internal function names, return shapes or error strings that the task request never states, so a correct implementation could fail them. documentation-lookup-evidence has 1 such test of 17, and that test was the only failure in every one of its cells. shaping-technical-discovery has 11 of 32, and 5 of its 6 cells failed only those. opencode-go-subscription has 6 of 66, and every cell also failed 1 to 3 fair tests. prompt-cache-reuse-and-usage also has such tests and a flaky baseline check; every cell timed out, so it stays unresolved. Counting only the fair hidden tests, **4 of 8 cells (older version) and 5 of 10 cells (fixed version) passed every fair test.** The statement that Kogen does not yet complete these long tasks is withdrawn as written: the published tasks undercount correctness, and they will be fixed and re-qualified before further use. The efficiency result (repeated reads after a reset) is not affected. The original figures are kept above for the record.

Before (older version, 8 cells):

| Task | Cells | Cells with a reset | Context resets | Repeated reads after a reset | Largest repeat share of a resetting conversation's input |
| --- | ---: | ---: | ---: | ---: | ---: |
| documentation-lookup-evidence | 2 | 0 | 0 | 0 | 0.0% |
| opencode-go-subscription | 2 | 2 | 6 | 69 | 29.4% |
| prompt-cache-reuse-and-usage | 2 | 2 | 8 | 194 | 45.7% |
| shaping-technical-discovery | 2 | 2 | 3 | 2 | 3.6% |

After (fixed version, 10 cells):

| Task | Cells | Cells with a reset | Context resets | Repeated reads after a reset | Largest repeat share of a resetting conversation's input |
| --- | ---: | ---: | ---: | ---: | ---: |
| documentation-lookup-evidence | 2 | 0 | 0 | 0 | 0.0% |
| opencode-go-subscription | 2 | 2 | 7 | 5 | 4.6% |
| prompt-cache-reuse-and-usage | 2 | 2 | 2 | 2 | 0.0% |
| shaping-technical-discovery | 4 | 4 | 5 | 2 | 2.2% |

Per cell, fixed version (round for the first 8 cells plus the extra 2 from the second-machine page):

| Task | Repetition | Kogen finished | Hidden tests failed | Context resets | Repeated reads after a reset | Venue |
| --- | ---: | --- | ---: | ---: | ---: | --- |
| documentation-lookup-evidence | 1 | landed | 1 of 17 | 0 | 0 | Linux server |
| documentation-lookup-evidence | 2 | landed | 1 of 17 | 0 | 0 | Linux server |
| opencode-go-subscription | 1 | landed | 8 of 66 | 3 | 0 | Linux server |
| opencode-go-subscription | 2 | landed | 6 of 66 | 4 | 5 | Linux server |
| prompt-cache-reuse-and-usage | 1 | timed out at 3,600 s | 26 of 97 | 1 | 1 | Linux server |
| prompt-cache-reuse-and-usage | 2 | timed out at 3,600 s | 26 of 97 | 1 | 1 | Linux server |
| shaping-technical-discovery | 1 | landed | 11 of 33 | 1 | 0 | Linux server |
| shaping-technical-discovery | 2 | landed | 12 of 33 | 1 | 0 | Linux server |
| shaping-technical-discovery | 1 | landed | 11 of 33 | 2 | 2 | Mac Studio |
| shaping-technical-discovery | 2 | landed | 11 of 33 | 1 | 0 | Mac Studio |

Use per task. Cost is an API-equivalent list-price estimate, not an invoice. Wall times come from different machines (older version on the Mac Studio; fixed version mostly on the Linux server) and should not be compared; for the one task that timed out, wall time is the 3,600 s cap in every cell.

Before:

| Task | Cells | Mean requests | Mean input tokens (incl. cached) | Mean cost | Mean wall time |
| --- | ---: | ---: | ---: | ---: | ---: |
| documentation-lookup-evidence | 2 | 14.0 | 777,646 | $0.36 | 508 s |
| opencode-go-subscription | 2 | 92.5 | 7,208,873 | $1.90 | 2583 s |
| prompt-cache-reuse-and-usage | 2 | 86.0 | 6,121,221 | $1.96 | 3601 s |
| shaping-technical-discovery | 2 | 62.0 | 4,494,789 | $1.24 | 2342 s |

After:

| Task | Cells | Mean requests | Mean input tokens (incl. cached) | Mean cost | Mean wall time |
| --- | ---: | ---: | ---: | ---: | ---: |
| documentation-lookup-evidence | 2 | 14.5 | 758,852 | $0.37 | 911 s |
| opencode-go-subscription | 2 | 85.5 | 6,267,858 | $1.82 | 2394 s |
| prompt-cache-reuse-and-usage | 2 | 71.0 | 4,223,847 | $0.99 | 3601 s |
| shaping-technical-discovery | 4 | 49.8 | 3,223,559 | $1.00 | 2132 s |

On the two timed-out cells' cost: the timeout caps wall time, not work, so cost and requests there only describe how the hour was spent. The fixed version used fewer requests and less cost in that task, but neither version finished it.

### Hidden-test result by lane (generated, first 8 cells of the fixed version)

| Lane | Cells | All hidden tests passed |
| --- | ---: | ---: |
| fixed | 8 | 0 |

Decision rule `descriptive` is recorded in `PLAN.json`, which the run wrote before any cell started.


## How resets and repeated reads were measured

Kogen keeps one conversation with the model for building and another for reviewing. When a conversation outgrows a fixed size limit, Kogen shrinks it and carries a summary forward. This page calls that a context reset.

A repeated read is a file read after a reset that returns exactly the same bytes (the same SHA-256) as a read made before it, in the same conversation. Its cost is estimated as bytes divided by 3 for tokens, times the number of later requests in that conversation until its next reset. The share is that estimate divided by the conversation's total input tokens. This is an estimate, not a token count from the provider.

Counts come from Kogen's request logs, which stay private. `measures/measures.json` has the per-cell counts and `measures/readobs.py` is the script. The tool that exports the standard records does not carry these fields, so they are not in `records.jsonl`.

## Fixed rule

Descriptive. Our written rule for this check, set before the fixed-version runs and recorded in private planning notes (not verifiable from this repository), was to count tasks where repeated reads exceed 10% of a resetting conversation's input. The older version had 2 such tasks and the fixed version has 0. Under that rule, a further remedy (a list of already-read files carried across resets) is held back. That is our decision about what to work on next, not a claim that Kogen is fixed.

## Limits

- This is observation-level evidence: 2 repetitions per task (4 for one task), one model, and not randomised.
- The two versions ran on different machines (older version on the Mac Studio; fixed version on the Linux server for 8 cells and the Mac Studio for 2). Machine, time of day, and the two extra commits are not separated from the reset fix.
- Reset and repeated-read counts are estimates from private logs (see above). The standard records carry outcome, tokens, cost and time but not these counts.
- Both versions failed every hidden-test run, so the check cannot say whether the fix changes correctness. It can only say it did not make these tasks pass.
- The fifth task of the original set was planned for the older version and never made a model request (its pre-build check failed on the machines tried). It is not part of either arm.
- The task folder hash and settings-file hash of each task differ between the older and the fixed runs because a per-task approval time limit was added to the settings file in between, according to our run notes. The old settings file is not published. Hidden-test, request, Intent and starting-tree hashes are the same.
- Cell counts: 8 older-version cells and 10 fixed-version cells. Further runs of the same fixed lane exist on other machines and are not part of this round.

## Task publication

These tasks are still used by an experiment that has not finished. This page therefore publishes only each task's id and content hashes (listed below and in `PLAN.json`). It publishes no task text, request, hidden tests, Intents, reference code or trees, and the published results hold no test names (each cell's test list is anonymised and holds only passed or failed per test). The tasks will be published when the experiment using them finishes. Until then the hashes commit to the inputs, but a reader cannot re-run or re-grade these cells.

A task is described here only by language and size. Hashes are SHA-256.

- `documentation-lookup-evidence`: Elixir, about 60 thousand source lines, a feature change.
  - folder `a809c26a22f4993fd47d6c43c4e5f79bfefc29e9cf1267d5a24c6ed751f4d1c1`
  - settings file `be1a2ac5c176a4722f10eada309e5662b4761821b91b05ed9b9a9698782f2b57`
  - hidden tests `f6721c6e2703494e89e1480b68361cef3172592fd590476d08583416de1e983c`
  - request `0552705147341f209b30267872fa40ed1d76d5db4575fd6c9cd166ebc90ec21d`
  - starting tree `f5148e416da44f66dcd631578a8ac2ef313b328899757701ff7bdb52e0aef0d0`
  - frozen Intent (Gherkin form) `bd670c7af941741a2cbe9e66a62e723c96335b1959889e2547f39cd1195f38e4`
- `opencode-go-subscription`: Elixir, about 61 thousand source lines, a feature change.
  - folder `dc1b06870f8fd25605a22d385d5cbfb46dcf237b783eaeae83f4dcaa4981e1ab`
  - settings file `0441923ca379633fda6ae12dfc3476e5285e9117e4467796397caf8108946ba3`
  - hidden tests `a9a86f74e19c55d7a0721156e36e62a72f116312f6324a5aa54519bdac8550fc`
  - request `8bfa6f4fc0819db6b4cdc0c6fed6a472f1295ec7b7397df65cb29629cb12b197`
  - starting tree `a45ef30a10c52eeeccb03aa5724040bb4657d89de3168db9bda1c2da3b7eb22f`
  - frozen Intent (Gherkin form) `1d4d8c0392d5a232b7cddb07fb022afe83f119baf7babdc644b1c06ef8f7eb72`
- `prompt-cache-reuse-and-usage`: Elixir, about 47 thousand source lines, a feature change.
  - folder `b888f1e23f89a6a5e1735945ce72fe74b27558172199289b8d22a510273fe488`
  - settings file `6e50bb98eae27a3b2949acfc8fcc556b4cd3cc7031cbc1f96fb77a6254d9ce73`
  - hidden tests `27a5ca014c512c1989e0d1bccf206a83ea9e8efcc3c46a2f634af1d3b5612eef`
  - request `2be5d52a0db6d6ab6d6279d7dd73b336415bb13fc6c2f21747d7def86f2a36dd`
  - starting tree `6e0e4b07a0b32d36f195e76406c846cfc82666d254e78ed9e0eea9b164a9e035`
  - frozen Intent (Gherkin form) `d4264954e7910196d410d6350830fd0808e44af9c21a633239d50e793288603a`
- `shaping-technical-discovery`: Elixir, about 58 thousand source lines, a feature change.
  - folder `30ce18cc31d87bc092413f446e02cad2dc639d514c2afdd0128a3fb00abe6fc6`
  - settings file `c4886e02b9345773e26d23a244675952aa50bc6e89e6d90d4cbbd1f8f920c83b`
  - hidden tests `e943e5d7e14239f1052e5833789f741282f2788989159bbd3d9a12339c1d41e0`
  - request `6701f786ce07ef90144386440a0d7c79e39eb8d4aff51392c9594b77e05a0c1f`
  - starting tree `5b83138b5e55d00dab469208ed2b1caee83c52889bae1f2660b8baa0fc6bcf77`
  - frozen Intent (Gherkin form) `307a0ccb009ed306aa978fd38821e55eb7c56a4a1f4a8f6f72b8eaf1b4f49cb8`

## How to reproduce

Today a reader can check what is published: the records, the bundles with each cell's stages, tokens and cost, the patch applied to Kogen, and the input hashes in `PLAN.json`. The Kogen source and the patch are public, so the lane can be rebuilt. The tasks, hidden tests and trees are not published yet, so the cells cannot be re-run or re-graded from this repository. When the tasks are published, they will be added under `reproduce/` and this page will say so; the command will then be:

```sh
lanes/reproduce.sh rounds/long-tasks-reset-fix-1-after
```

The reset and repeated-read counts come from Kogen's private run logs, which are not published. The script that computed them is in `measures/readobs.py`, and its output per cell is in `measures/measures.json`, so the counts can be read but not recomputed from public files.

## Counts

| Measure | Count |
| --- | ---: |
| Planned cells | 8 |
| Started cells | 8 |
| Finished cells | 8 |
| Graded cells | 8 |
| ITT count | 8 |

## Metadata

Round date: 2026-10-26
Label: DESCRIPTIVE
Publication badge: DESCRIPTIVE; KEPT FOR AUDIT
Recomputation status: OBSERVED SOURCE ONLY
Why not VALID: DESCRIPTIVE_ONLY, PROTOCOL_DEVIATION, INCOMPLETE_CAPTURE — lane harness run, no official grades, and missing Standard capture fields declared below.
STATUS: **DESCRIPTIVE**

## Execution record

Harness commit: 487a2b0e4356f36d2e3ccf13a4504beb8df02c3e
Model and effort: the Kogen defaults
Task IDs: documentation-lookup-evidence, opencode-go-subscription, prompt-cache-reuse-and-usage, shaping-technical-discovery
Command: lanes-run, lanes-grade and lanes-export on experiment `long-tasks-reset-fix-1-after`.
Kogen commits: 56eecd572a6e07184863939254a90d9a2dc44e96
Raw records: records.jsonl and the bundle in bundles/long-tasks-reset-fix-1-after preserve every cell's outcome and stages; a record's `ledger_sha256` hashes that cell's published attempt.json and evaluation.json.
Inputs: PLAN.json holds the hashes of the tasks, hidden tests, Intents, patches and settings. The task files are not published yet (see Task publication).

## What's missing and why
- `circumstances.cap_end` (8 missing): The Kogen build and the lane harness do not log this field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (`m08`).
- `circumstances.cap_start` (8 missing): The Kogen build and the lane harness do not log this field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (`m08`).
- `circumstances.concurrent_cells_end` (8 missing): The Kogen build and the lane harness do not log this field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.concurrent_cells_start` (8 missing): The Kogen build and the lane harness do not log this field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.dispatcher_id` (8 missing): The Kogen build and the lane harness do not log this field. Exact dispatcher revision is not present in the public receipt extract. Reason: Exact dispatcher revision is not present in the public receipt extract (`m63`).
- `circumstances.incidents` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell incident receipt was not captured. Reason: Per-cell incident receipt was not captured (`m78`).
- `circumstances.load1_end` (8 missing): The Kogen build and the lane harness do not log this field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (`m65`).
- `circumstances.load1_start` (8 missing): The Kogen build and the lane harness do not log this field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (`m65`).
- `circumstances.load_samples` (8 missing): The Kogen build and the lane harness do not log this field. Timestamped host-wide load samples were not captured. Reason: Timestamped host-wide load samples were not captured (`m93`).
- `circumstances.queue` (8 missing): The Kogen build and the lane harness do not log this field. Queue receipt was not captured. Reason: Queue receipt was not captured (`m91`).
- `cost.long_context_reconciled` (8 missing): The Kogen build and the lane harness do not log this field. Boolean receipt not recorded. Reason: Boolean receipt not recorded (`m07`).
- `effort.effective` (6 missing): The Kogen build and the lane harness do not log this field. Per-cell effective-effort receipt not published. Reason: Per-cell effective-effort receipt not published (`m73`).
- `effort.requested` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `effort.runner_requested` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `environment.account_class` (8 missing): The Kogen build and the lane harness do not log this field. No owner-approved class-only account receipt is available for the cell. Reason: No owner-approved class-only account receipt is available for the cell (`m100`).
- `environment.network.allowlist_hosts` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell network allowlist not present in the public round data. Reason: Per-cell network allowlist not present in the public round data (`m79`).
- `environment.network.profile` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell network profile not present in the public round data. Reason: Per-cell network profile not present in the public round data (`m80`).
- `environment.toolchains.elixir` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.erlang` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.node` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.other_inventory` (8 missing): The Kogen build and the lane harness do not log this field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `environment.toolchains.python` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.ruby` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.rust` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `grade.grader` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (`m77`).
- `grade.timestamp` (8 missing): The Kogen build and the lane harness do not log this field. No official grade in the public snapshot. Reason: No official grade in the public snapshot (`m32`).
- `host.id` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `model.requested` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `sandbox.egress_allow` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell egress allowlist is not present in the public round data. Reason: Per-cell egress allowlist is not present in the public round data (`m75`).
- `sandbox.egress_profile` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell egress profile is not present in the public round data. Reason: Per-cell egress profile is not present in the public round data (`m76`).
- `sandbox.profile` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell sandbox profile is not present in the public round data. Reason: Per-cell sandbox profile is not present in the public round data (`m87`).
- `sandbox.profile_sha256` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell sandbox profile fingerprint is not present in the public round data. Reason: Per-cell sandbox profile fingerprint is not present in the public round data (`m86`).
- `setup.adapter_harness_sha` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `setup.deps_source` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell dependency source is not recorded. Reason: Per-cell dependency source is not recorded (`m71`).
- `setup.sandbox_mode` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell sandbox mode is not present in the public round data. Reason: Per-cell sandbox mode is not present in the public round data (`m85`).
- `setup.sandbox_profile_sha256` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell sandbox fingerprint is not present in the public round data. Reason: Per-cell sandbox fingerprint is not present in the public round data (`m84`).
- `setup.task_base.hash` (8 missing): The Kogen build and the lane harness do not log this field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (`m42`).
- `setup.task_base.kind` (8 missing): The Kogen build and the lane harness do not log this field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (`m43`).
- `task.base_repo` (8 missing): The Kogen build and the lane harness do not log this field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `task.base_revision.hash` (8 missing): The Kogen build and the lane harness do not log this field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (`m42`).
- `task.base_revision.kind` (8 missing): The Kogen build and the lane harness do not log this field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (`m43`).
- `timestamps.phases.develop.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.develop.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.gate.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.gate.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.grade.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.grade.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.plan.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.plan.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.review.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.review.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.setup.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.setup.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.shape.end_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.shape.start_utc` (8 missing): The Kogen build and the lane harness do not log this field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timing.phases_s.grade` (8 missing): The Kogen build and the lane harness do not log this field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (`m45`).
- `timing.phases_s.setup` (8 missing): The Kogen build and the lane harness do not log this field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (`m45`).
- `tools.grader` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (`m77`).
- `tools.runner` (8 missing): The Kogen build and the lane harness do not log this field. Per-cell runner version not recorded in the public round data. Reason: Per-cell runner version not recorded in the public round data (`m83`).
- `tools.toolchains.elixir` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.erlang` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.node` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.other_inventory` (8 missing): The Kogen build and the lane harness do not log this field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `tools.toolchains.python` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.ruby` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.rust` (8 missing): The Kogen build and the lane harness do not log this field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).


## Captured run records

No records for this round are listed in the [run-record index](/downloads/results/run-records/index.json).


## Reproduction inventory

- **Type:** analysis-only
- **Script:** none published
- **Inputs:** `rounds/long-tasks-reset-fix-1-after/MEASURED.md`, `rounds/long-tasks-reset-fix-1-after/MISSING-DECLARED.json`, `rounds/long-tasks-reset-fix-1-after/MISSING.md`, `rounds/long-tasks-reset-fix-1-after/PLAN.json`, `rounds/long-tasks-reset-fix-1-after/README.md`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/EXCLUDED.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/documentation-lookup-evidence/r1/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/documentation-lookup-evidence/r1/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/documentation-lookup-evidence/r2/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/documentation-lookup-evidence/r2/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/opencode-go-subscription/r1/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/opencode-go-subscription/r1/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/opencode-go-subscription/r2/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/opencode-go-subscription/r2/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/prompt-cache-reuse-and-usage/r1/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/prompt-cache-reuse-and-usage/r1/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/prompt-cache-reuse-and-usage/r2/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/prompt-cache-reuse-and-usage/r2/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/shaping-technical-discovery/r1/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/shaping-technical-discovery/r1/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/shaping-technical-discovery/r2/fixed/a1/attempt.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/attempts/shaping-technical-discovery/r2/fixed/a1/evaluation.json`, `rounds/long-tasks-reset-fix-1-after/bundles/long-tasks-reset-fix-1-after/manifest.json`, `rounds/long-tasks-reset-fix-1-after/measures/measures.json`, `rounds/long-tasks-reset-fix-1-after/measures/readobs.py`, `rounds/long-tasks-reset-fix-1-after/patches/fixed/measurement.diff`, `rounds/long-tasks-reset-fix-1-after/records.jsonl`
- **Full execution replay:** unavailable
- **Scope:** Records and bundles preserve the graded outcomes; model execution is rerun with the reader's own login (lanes/reproduce.sh --rerun).

See the [complete per-round reproduction inventory](/reproduce/) and the [repository reproduction guide](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/reproduce/README.md).

## Related records

### Related experiments

- [long-tasks-reset-fix-1-after](/rounds/long-tasks-reset-fix-1-after/)
