diff --git a/README.md b/README.md index ca0d937..84a873f 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ A bounded task runtime and evaluation harness for autonomous coding-agent experi - **Durable task lifecycle:** Reconstructs task state via an append-only event log with idempotent enqueue, retry bounds, cancellation, and restart recovery. - **Bounded subprocess execution:** Runs allowlisted programs in a canonical workspace directory with wall-clock timeouts, captured output byte caps, and Unix process-group termination. -- **Separated model authority:** Constrains model providers (such as AGY) to structured actions and streamed text events while enforcing tool execution through the runtime. +- **Separated model authority:** Constrains model providers (such as AGY, the Google Antigravity command-line client used here to call Gemini models) to structured actions and streamed text events while enforcing tool execution through the runtime. - **Verification debt:** Enforces that file edits require passing an operator-configured verification command before a task can complete. - **Independent acceptance evaluation:** Validates agent patches against external acceptance fixtures isolated from the agent's workspace. diff --git a/docs/commit-id-map.md b/docs/commit-id-map.md new file mode 100644 index 0000000..42bfa0e --- /dev/null +++ b/docs/commit-id-map.md @@ -0,0 +1,15 @@ +# Commit ID map + +On 2026-09-27 this repository's history was rewritten to normalise commit author identities and commit-message metadata. File contents at every commit and tag are otherwise unchanged; only commit IDs changed. +Files that recorded a commit ID on `main` (evaluation reports, run metadata, validation notes, changelog) were updated to the new IDs. This table maps each updated reference to its original ID, so older external references can still be resolved. +IDs that refer to commits on merged pull-request branches are left unchanged: GitHub keeps those commits with their pull request. + +| Original ID | New ID | +| :--- | :--- | +| `09a73f17107448d6d0f270d0bbddde6c9e442bba` | `6a7d3ee82fb0d967c64c491dc54fd4fa56a00f53` | +| `23925b1a234a8734d5f699ae480a36a0d0276b94` | `5006979b2e03eb88abbfcf383cecca410fe4bd70` | +| `6683999ac5d150591f726a9c68dfecfd1f8a12f1` | `7abbab0588d5c6046b83c9a8e0207c50af1ab251` | +| `8ddc7a3b55fbc62fccaf3118c3899cb4ec873496` | `11821afac9963949be5ed95f1569ab628f847ea7` | +| `a6cb005bdeffd555e1078d83f9078df543496b1a` | `697ef8473c0515e60ee46ced6145bcee4b95a825` | +| `cc8e890a9cfc3743a3d3bf79734971a81534fb6d` | `af0a796b7fb8b7cf05088844aca6bb6443860c49` | +| `d0068b9600d0caeb85b2dbcdd27c008d8791f0b0` | `943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7` | diff --git a/evaluation/agy-off-by-one.md b/evaluation/agy-off-by-one.md index 2b18bf1..1f0d817 100644 --- a/evaluation/agy-off-by-one.md +++ b/evaluation/agy-off-by-one.md @@ -2,7 +2,7 @@ Date: 2026-09-06 Model: `gemini-3.8-flash-low` -Runtime commit under test: `09a73f17107448d6d0f270d0bbddde6c9e442bba` +Runtime commit under test: `6a7d3ee82fb0d967c64c491dc54fd4fa56a00f53` Fixture: `fixtures/off_by_one` copied to a fresh temporary directory ## Task diff --git a/evaluation/fresh-evaluation-report.md b/evaluation/fresh-evaluation-report.md index 2a6d25f..5312a0f 100644 --- a/evaluation/fresh-evaluation-report.md +++ b/evaluation/fresh-evaluation-report.md @@ -5,7 +5,7 @@ Model: `gemini-3.8-flash-low` via the AGY structured-output provider Provider binary: `agy 1.2.0` Runtime: `rust-agent-runtime` (durable worker + bounded executor + macOS seatbelt) Host: macOS Apple Silicon, `rustc 1.94.1` -Code under test: commits `23925b1` (explicit verify action) and `6683999` (trustworthy harness + +Code under test: commits `5006979` (explicit verify action) and `7abbab0` (trustworthy harness + controls); real runs additionally record the harness and binary hashes below. Historical runs from before these commits are preserved under `evaluation/runs/`. @@ -89,7 +89,7 @@ Final control run `evaluation/runs/controls-20260911T203623Z-*` (36 checks, 0 fa ### Attempt-consistency regression (2026-09-11) -The base harness (commit `a6cb005`) latched `family_acceptance` and `family_clean` independently +The base harness (commit `697ef84`) latched `family_acceptance` and `family_clean` independently across attempts (`evaluation/run_fresh_evaluation.sh:340-345` and `:362` on that base). An attempt that passed acceptance but failed the worker, followed by an attempt that was worker-clean but failed acceptance, combined into `patch_acceptance_pass=true` + `worker_clean_success=true` and exit 0 even @@ -116,7 +116,7 @@ RUN_ID=20260910T215500Z-real AGY_BIN=agy AGY_MODEL=gemini-3.8-flash-low \ AGENT_MAX_STEPS=6 AGENT_TIMEOUT_SECS=120 bash evaluation/run_fresh_evaluation.sh ``` -Metadata: `source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1`, +Metadata: `source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251`, `harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed`, binary sha256 `974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683`, `source_dirty_count=2` (the preserved untracked `tests/fixtures/unwrap-panic/Cargo.lock` plus this @@ -136,7 +136,7 @@ runtime-run verification (`tool cargo argc=1`) with status 0. ## Real-model confirmation run `20260910T215600Z-real2` A second run confirmed the result after a metadata-only harness change (dirty count measured before -the run directory is created). Metadata: `source_sha=6683999...`, `harness_sha256=6033c654...`, +the run directory is created). Metadata: `source_sha=7abbab0...`, `harness_sha256=6033c654...`, `source_dirty_count=3` (untracked fixture lock, the uncommitted metadata fix, and the first run directory). diff --git a/evaluation/runs/20260910T215500Z-real/metadata.txt b/evaluation/runs/20260910T215500Z-real/metadata.txt index 00e5d8d..a85ae82 100644 --- a/evaluation/runs/20260910T215500Z-real/metadata.txt +++ b/evaluation/runs/20260910T215500Z-real/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=2 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/20260910T215600Z-real2/metadata.txt b/evaluation/runs/20260910T215600Z-real2/metadata.txt index b046b82..240b4fe 100644 --- a/evaluation/runs/20260910T215600Z-real2/metadata.txt +++ b/evaluation/runs/20260910T215600Z-real2/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=3 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-acceptance-failure/metadata.txt b/evaluation/runs/controls-20260910T214922Z-acceptance-failure/metadata.txt index 4b088e6..1b2e867 100644 --- a/evaluation/runs/controls-20260910T214922Z-acceptance-failure/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-acceptance-failure/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=22 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-invalid-baseline/metadata.txt b/evaluation/runs/controls-20260910T214922Z-invalid-baseline/metadata.txt index 8973319..c49bf7b 100644 --- a/evaluation/runs/controls-20260910T214922Z-invalid-baseline/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-invalid-baseline/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=21 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-rerun-1/metadata.txt b/evaluation/runs/controls-20260910T214922Z-rerun-1/metadata.txt index 7d2999d..ffb9fe6 100644 --- a/evaluation/runs/controls-20260910T214922Z-rerun-1/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-rerun-1/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=27 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-rerun/metadata.txt b/evaluation/runs/controls-20260910T214922Z-rerun/metadata.txt index 89fe519..c77fe3e 100644 --- a/evaluation/runs/controls-20260910T214922Z-rerun/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-rerun/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=26 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-step-limit/metadata.txt b/evaluation/runs/controls-20260910T214922Z-step-limit/metadata.txt index 947dd77..fbeaacf 100644 --- a/evaluation/runs/controls-20260910T214922Z-step-limit/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-step-limit/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=23 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-success/metadata.txt b/evaluation/runs/controls-20260910T214922Z-success/metadata.txt index 74dc2dd..8989d4b 100644 --- a/evaluation/runs/controls-20260910T214922Z-success/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-success/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=25 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T214922Z-wall-timeout/metadata.txt b/evaluation/runs/controls-20260910T214922Z-wall-timeout/metadata.txt index 04cdc72..0d257d7 100644 --- a/evaluation/runs/controls-20260910T214922Z-wall-timeout/metadata.txt +++ b/evaluation/runs/controls-20260910T214922Z-wall-timeout/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=6f791224d9a50e49f207f4ce94038e187c195532ff2700462a66bd2b11efddf2 -source_sha=d0068b9600d0caeb85b2dbcdd27c008d8791f0b0 +source_sha=943bee7bc5ab63fe8658bc7bbf4d11f4e67e22c7 source_dirty_count=24 harness_sha256=801cd3da31904f87bb0b03fa9324bab67902712c7016e925ff6c745c5a6513ed provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-acceptance-failure/metadata.txt b/evaluation/runs/controls-20260910T215842Z-acceptance-failure/metadata.txt index 5e58204..8887c60 100644 --- a/evaluation/runs/controls-20260910T215842Z-acceptance-failure/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-acceptance-failure/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=7 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-invalid-baseline/metadata.txt b/evaluation/runs/controls-20260910T215842Z-invalid-baseline/metadata.txt index 905f624..8279a71 100644 --- a/evaluation/runs/controls-20260910T215842Z-invalid-baseline/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-invalid-baseline/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=6 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-rerun-1/metadata.txt b/evaluation/runs/controls-20260910T215842Z-rerun-1/metadata.txt index b95769f..7b57a01 100644 --- a/evaluation/runs/controls-20260910T215842Z-rerun-1/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-rerun-1/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=12 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-rerun/metadata.txt b/evaluation/runs/controls-20260910T215842Z-rerun/metadata.txt index 14e505e..00740c2 100644 --- a/evaluation/runs/controls-20260910T215842Z-rerun/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-rerun/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=11 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-step-limit/metadata.txt b/evaluation/runs/controls-20260910T215842Z-step-limit/metadata.txt index 8711800..ee0ab45 100644 --- a/evaluation/runs/controls-20260910T215842Z-step-limit/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-step-limit/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=8 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-success/metadata.txt b/evaluation/runs/controls-20260910T215842Z-success/metadata.txt index e4b274a..d038396 100644 --- a/evaluation/runs/controls-20260910T215842Z-success/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-success/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=10 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T215842Z-wall-timeout/metadata.txt b/evaluation/runs/controls-20260910T215842Z-wall-timeout/metadata.txt index 124f492..18ede90 100644 --- a/evaluation/runs/controls-20260910T215842Z-wall-timeout/metadata.txt +++ b/evaluation/runs/controls-20260910T215842Z-wall-timeout/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=6683999ac5d150591f726a9c68dfecfd1f8a12f1 +source_sha=7abbab0588d5c6046b83c9a8e0207c50af1ab251 source_dirty_count=9 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-acceptance-failure/metadata.txt b/evaluation/runs/controls-20260910T220053Z-acceptance-failure/metadata.txt index 0cd7103..e9e65d1 100644 --- a/evaluation/runs/controls-20260910T220053Z-acceptance-failure/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-acceptance-failure/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=5 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-invalid-baseline/metadata.txt b/evaluation/runs/controls-20260910T220053Z-invalid-baseline/metadata.txt index 5ea7d26..d4bdd57 100644 --- a/evaluation/runs/controls-20260910T220053Z-invalid-baseline/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-invalid-baseline/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=4 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-mixed-families/metadata.txt b/evaluation/runs/controls-20260910T220053Z-mixed-families/metadata.txt index 73bf16f..19acd70 100644 --- a/evaluation/runs/controls-20260910T220053Z-mixed-families/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-mixed-families/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=9 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-rerun-1/metadata.txt b/evaluation/runs/controls-20260910T220053Z-rerun-1/metadata.txt index 703db5d..dcc91cf 100644 --- a/evaluation/runs/controls-20260910T220053Z-rerun-1/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-rerun-1/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=11 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-rerun/metadata.txt b/evaluation/runs/controls-20260910T220053Z-rerun/metadata.txt index dd8ced8..6fe8e6a 100644 --- a/evaluation/runs/controls-20260910T220053Z-rerun/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-rerun/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=10 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-step-limit/metadata.txt b/evaluation/runs/controls-20260910T220053Z-step-limit/metadata.txt index 9be33c3..3bc0854 100644 --- a/evaluation/runs/controls-20260910T220053Z-step-limit/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-step-limit/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=6 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-success/metadata.txt b/evaluation/runs/controls-20260910T220053Z-success/metadata.txt index 6494063..e3f9b9c 100644 --- a/evaluation/runs/controls-20260910T220053Z-success/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-success/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=8 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220053Z-wall-timeout/metadata.txt b/evaluation/runs/controls-20260910T220053Z-wall-timeout/metadata.txt index af1bed9..c10adae 100644 --- a/evaluation/runs/controls-20260910T220053Z-wall-timeout/metadata.txt +++ b/evaluation/runs/controls-20260910T220053Z-wall-timeout/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=cc8e890a9cfc3743a3d3bf79734971a81534fb6d +source_sha=af0a796b7fb8b7cf05088844aca6bb6443860c49 source_dirty_count=7 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-acceptance-failure/metadata.txt b/evaluation/runs/controls-20260910T220306Z-acceptance-failure/metadata.txt index 413faab..899a217 100644 --- a/evaluation/runs/controls-20260910T220306Z-acceptance-failure/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-acceptance-failure/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=4 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-invalid-baseline/metadata.txt b/evaluation/runs/controls-20260910T220306Z-invalid-baseline/metadata.txt index 5611955..731a8ed 100644 --- a/evaluation/runs/controls-20260910T220306Z-invalid-baseline/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-invalid-baseline/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=3 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-mixed-families/metadata.txt b/evaluation/runs/controls-20260910T220306Z-mixed-families/metadata.txt index 2e53744..a0d4fd3 100644 --- a/evaluation/runs/controls-20260910T220306Z-mixed-families/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-mixed-families/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=8 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-rerun-1/metadata.txt b/evaluation/runs/controls-20260910T220306Z-rerun-1/metadata.txt index 7d73f7b..48be5ae 100644 --- a/evaluation/runs/controls-20260910T220306Z-rerun-1/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-rerun-1/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=10 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-rerun/metadata.txt b/evaluation/runs/controls-20260910T220306Z-rerun/metadata.txt index 7af9ccb..355723c 100644 --- a/evaluation/runs/controls-20260910T220306Z-rerun/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-rerun/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=9 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-step-limit/metadata.txt b/evaluation/runs/controls-20260910T220306Z-step-limit/metadata.txt index c3914f6..9b1c151 100644 --- a/evaluation/runs/controls-20260910T220306Z-step-limit/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-step-limit/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=5 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-success/metadata.txt b/evaluation/runs/controls-20260910T220306Z-success/metadata.txt index f7febd3..28321a6 100644 --- a/evaluation/runs/controls-20260910T220306Z-success/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-success/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=7 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260910T220306Z-wall-timeout/metadata.txt b/evaluation/runs/controls-20260910T220306Z-wall-timeout/metadata.txt index da57cab..0d3e192 100644 --- a/evaluation/runs/controls-20260910T220306Z-wall-timeout/metadata.txt +++ b/evaluation/runs/controls-20260910T220306Z-wall-timeout/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=974966a8280f11a52a52074554526291fb4a2ddd03a62ac1c47af0b120942683 -source_sha=8ddc7a3b55fbc62fccaf3118c3899cb4ec873496 +source_sha=11821afac9963949be5ed95f1569ab628f847ea7 source_dirty_count=6 harness_sha256=6033c654ba994cafad0d5230251938b4b2a4ff1d2178f416785b9ff7fc2cfa64 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-acceptance-failure/metadata.txt b/evaluation/runs/controls-20260911T203623Z-acceptance-failure/metadata.txt index 865ca1e..4aadaf6 100644 --- a/evaluation/runs/controls-20260911T203623Z-acceptance-failure/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-acceptance-failure/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=6 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-invalid-baseline/metadata.txt b/evaluation/runs/controls-20260911T203623Z-invalid-baseline/metadata.txt index b974255..144cc25 100644 --- a/evaluation/runs/controls-20260911T203623Z-invalid-baseline/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-invalid-baseline/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=5 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-mixed-families/metadata.txt b/evaluation/runs/controls-20260911T203623Z-mixed-families/metadata.txt index 2f74c28..dadff09 100644 --- a/evaluation/runs/controls-20260911T203623Z-mixed-families/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-mixed-families/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=11 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-opposite-attempts/metadata.txt b/evaluation/runs/controls-20260911T203623Z-opposite-attempts/metadata.txt index 2cbbcbb..1462ae7 100644 --- a/evaluation/runs/controls-20260911T203623Z-opposite-attempts/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-opposite-attempts/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=9 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-rerun-1/metadata.txt b/evaluation/runs/controls-20260911T203623Z-rerun-1/metadata.txt index 89be06a..0ece54a 100644 --- a/evaluation/runs/controls-20260911T203623Z-rerun-1/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-rerun-1/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=13 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-rerun/metadata.txt b/evaluation/runs/controls-20260911T203623Z-rerun/metadata.txt index ba8d196..2027b0e 100644 --- a/evaluation/runs/controls-20260911T203623Z-rerun/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-rerun/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=12 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-step-limit/metadata.txt b/evaluation/runs/controls-20260911T203623Z-step-limit/metadata.txt index 6b2704d..e2ff7a1 100644 --- a/evaluation/runs/controls-20260911T203623Z-step-limit/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-step-limit/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=7 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-success/metadata.txt b/evaluation/runs/controls-20260911T203623Z-success/metadata.txt index db9569b..925b7e9 100644 --- a/evaluation/runs/controls-20260911T203623Z-success/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-success/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=10 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0 diff --git a/evaluation/runs/controls-20260911T203623Z-wall-timeout/metadata.txt b/evaluation/runs/controls-20260911T203623Z-wall-timeout/metadata.txt index dd7350e..c3c9feb 100644 --- a/evaluation/runs/controls-20260911T203623Z-wall-timeout/metadata.txt +++ b/evaluation/runs/controls-20260911T203623Z-wall-timeout/metadata.txt @@ -1,6 +1,6 @@ built_binary=/target/debug/rust-agent-runtime built_binary_sha256=5a0051fdb69b6165d0bfe619b742a3933520a62ab2d108d04edb67f512deae5e -source_sha=a6cb005bdeffd555e1078d83f9078df543496b1a +source_sha=697ef8473c0515e60ee46ced6145bcee4b95a825 source_dirty_count=8 harness_sha256=1edad579e0b183ddfdcd9b2142bac8b849be87549cc48c5ca9a8d1f8bdc9fc37 provider_version=1.2.0