Task
cadence-takeover-001@1.0.0
runs
12
success rate
100.0%
mean time
3 m 60 s
input tokens
2,182,492
generated tokens
53,408
tokens
2,235,900
tool calls
169
What the task asks
A worker with a stale epoch can take a live lease back
LeaseBook.takeover accepts a request whose epoch no longer matches the resource's current lease, so a worker that was cut off and comes back can steal the resource from the worker that holds it now. Restore the documented rule that only the holder of the current epoch may take a resource back.
full description (markdown source)
# A worker with a stale epoch can take a live lease back `LeaseBook.takeover` in `src/cadence/lease.py` is supposed to answer one question: does the caller still hold the epoch this resource was granted with? A worker that was cut off and comes back still believes it holds the resource, and asks for it back by the epoch it was given. The rule, as documented in the module: - the epoch is the whole question — a request for an epoch the book no longer carries is **stale**, because somebody else was granted the resource while the caller was silent; - granting a stale request would put two workers on the same work, so a stale epoch is refused with `LeaseHeld`, and the current holder keeps its lease and its validity; - a refused takeover must change nothing: not the holder, not the epoch, not the deadline. The repository's own suite is green on the pinned commit, because it only ever asks a holder back by the epoch it still carries. The defect only shows up when a request arrives for an epoch the book no longer holds — which is exactly the request that a worker that lost the lease makes.
Constraints
- do not change the public API of the cadence package
- do not modify the repository test suite under tests/
- do not change the lease epoch numbering or the acquisition rules
- do not add third-party dependencies
Recorded identity
| field | value |
|---|---|
| uid | cadence-takeover-001@1.0.0 |
| category | bug_fix |
| difficulty | expert |
| evaluator | pytest_evaluator |
| base commit | HEAD |
| repository | repo-457ed29341306d49 |
| snapshot digest | sha256:20071a11d3adde959c832627ec86d344b2e7697d7bca56d700aca9ddabd1e24a |
| source | datasets/_sources/cadence |
| ref | HEAD |
| mutation | none |
| timeout | 900 s |
| hidden tests | hidden_tests |
| public tests | public_tests |
| definition digest | sha256:20071a11d3adde959c832627ec86d344b2e7697d7bca56d700aca9ddabd1e24a |
| definition path | /mnt/data2/dev/develop/ak-bench/datasets/bug_fix/cadence-takeover-001 |
Runs of this task
in the order they started; the parameters column is the configuration each run was executed under
| run | parameters | started | agent | repetition | status | verdict | score | time | input tokens | generated tokens | total tokens | tool calls | failure class | error |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| run-20261102-102224-77a554a3 | knowledge_enabled=False, model=qwen/Qwen3.8-27B | 2026-11-02 10:22:24 | codex@codex-cli 0.166.0 | 1 | completed | passed | 1.000 | 2 m 25 s | 87,441 | 2,062 | 89,503 | 9 | ||
| run-20261102-102450-4c4dafd8 | knowledge_enabled=False, model=qwen/Qwen3.8-27B | 2026-11-02 10:24:50 | codex@codex-cli 0.166.0 | 2 | completed | passed | 1.000 | 3 m 56 s | 184,037 | 3,928 | 187,965 | 13 | ||
| run-20261102-102846-f9da52d1 | knowledge_enabled=False, model=qwen/Qwen3.8-27B | 2026-11-02 10:28:46 | codex@codex-cli 0.166.0 | 3 | completed | passed | 1.000 | 2 m 53 s | 166,105 | 2,393 | 168,498 | 14 | ||
| run-20261102-103139-c174189b | knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next | 2026-11-02 10:31:39 | codex@codex-cli 0.166.0 | 1 | completed | passed | 1.000 | 3 m 20 s | 142,081 | 4,157 | 146,238 | 13 | ||
| run-20261102-103500-42595b9b | knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next | 2026-11-02 10:35:00 | codex@codex-cli 0.166.0 | 2 | completed | passed | 1.000 | 3 m 6 s | 136,190 | 4,248 | 140,438 | 12 | ||
| run-20261102-103806-ca54befb | knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next | 2026-11-02 10:38:06 | codex@codex-cli 0.166.0 | 3 | completed | passed | 1.000 | 3 m 43 s | 176,874 | 4,786 | 181,660 | 14 | ||
| run-20261102-104150-ee470964 | knowledge_enabled=False, model=auto_codex | 2026-11-02 10:41:50 | codex@codex-cli 0.166.0 | 1 | completed | passed | 1.000 | 3 m 36 s | 184,263 | 2,829 | 187,092 | 15 | ||
| run-20261102-104527-df556abc | knowledge_enabled=False, model=auto_codex | 2026-11-02 10:45:27 | codex@codex-cli 0.166.0 | 2 | completed | passed | 1.000 | 5 m 33 s | 231,250 | 6,615 | 237,865 | 16 | ||
| run-20261102-105101-7f0ea089 | knowledge_enabled=False, model=auto_codex | 2026-11-02 10:51:01 | codex@codex-cli 0.166.0 | 3 | completed | passed | 1.000 | 2 m 31 s | 81,756 | 1,513 | 83,269 | 9 | ||
| run-20261102-105332-509d420c | knowledge_enabled=True, model=auto_codex | 2026-11-02 10:53:32 | codex@codex-cli 0.166.0 | 1 | completed | passed | 1.000 | 5 m 51 s | 181,892 | 10,799 | 192,691 | 15 | ||
| run-20261102-105924-5844ec5c | knowledge_enabled=True, model=auto_codex | 2026-11-02 10:59:24 | codex@codex-cli 0.166.0 | 2 | completed | passed | 1.000 | 7 m 45 s | 486,023 | 7,446 | 493,469 | 26 | ||
| run-20261102-110711-12e9e01e | knowledge_enabled=True, model=auto_codex | 2026-11-02 11:07:11 | codex@codex-cli 0.166.0 | 3 | completed | passed | 1.000 | 3 m 18 s | 124,580 | 2,632 | 127,212 | 13 |
Not verified
Configurations that are not verified. They stay in the report, because a result produced under them is only as trustworthy as they are.
| kind | subject | status | run | note |
|---|---|---|---|---|
| plugin | agentic_knowledge | unsupported | run-20261102-102224-77a554a3 | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-102224-77a554a3 | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-102450-4c4dafd8 | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-102450-4c4dafd8 | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-102846-f9da52d1 | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-102846-f9da52d1 | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-103139-c174189b | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-103139-c174189b | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-103500-42595b9b | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-103500-42595b9b | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-103806-ca54befb | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-103806-ca54befb | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-104150-ee470964 | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-104150-ee470964 | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-104527-df556abc | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-104527-df556abc | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-105101-7f0ea089 | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-105101-7f0ea089 | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-105332-509d420c | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-105332-509d420c | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-105924-5844ec5c | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-105924-5844ec5c | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| plugin | agentic_knowledge | unsupported | run-20261102-110711-12e9e01e | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| plugin | agentic_routing_codex | unsupported | run-20261102-110711-12e9e01e | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
| model | qwen/Qwen3.8-27B | unverified | run-20261102-102224-77a554a3 | |
| model | qwen/Qwen3.8-27B | unverified | run-20261102-102450-4c4dafd8 | |
| model | qwen/Qwen3.8-27B | unverified | run-20261102-102846-f9da52d1 | |
| model | qwen/Qwen3.8-Flash-Next | unverified | run-20261102-103139-c174189b | |
| model | qwen/Qwen3.8-Flash-Next | unverified | run-20261102-103500-42595b9b | |
| model | qwen/Qwen3.8-Flash-Next | unverified | run-20261102-103806-ca54befb | |
| model | auto_codex | unverified | run-20261102-104150-ee470964 | |
| model | auto_codex | unverified | run-20261102-104527-df556abc | |
| model | auto_codex | unverified | run-20261102-105101-7f0ea089 | |
| model | auto_codex | unverified | run-20261102-105332-509d420c | |
| model | auto_codex | unverified | run-20261102-105924-5844ec5c | |
| model | auto_codex | unverified | run-20261102-110711-12e9e01e |