Run
run-20261102-135659-dfdbb7ee
verdict
not evaluated
score
not measured
time
15 m 5 s
input tokens
452,414
generated tokens
32,517
tokens
484,931
tool calls
19
status
timeout
Where this run belongs
| field | value |
|---|---|
| experiment | router-config-comparison@1.0.0 |
| task | cadence-catchup-001@1.0.0 |
| parameters | knowledge_enabled=False, model=qwen/Qwen3.8-Flash-Next |
| variant | v-e816befad22e |
| agent | codex@codex-cli 0.166.0 |
| runtime | llm-router |
| mode | router |
| repetition | 3 |
| session | 01a19c8d-116b-7710-ab1a-a0799b3bea1d |
| manifest digest | sha256:f7c4f022daa6d73af13534dd09ba8d4e527698b7a6c776305eabb7af78ed508b |
Evaluation
this run was never evaluated: it has no verdict and no score
What the agent reported
| field | value |
|---|---|
| started | 2026-11-02T13:56:59.006858 |
| finished | 2026-11-02T14:12:03.783278 |
| wall clock | 15 m 5 s |
| input tokens | 452,414 |
| total tokens | 484,931 |
| tool calls | 19 |
| exit code | 1 |
| failure class | agent |
| error | Several more of my expectations were wrong (an always-planned upstream settles its dependents, so real waits need staggered schedules). Rewriting with `(day, hour)` tuples and genuinely blocked upstreams. |
Model
| requested | observed | source | verification |
|---|---|---|---|
| qwen/Qwen3.8-Flash-Next | qwen/Qwen3.8-Flash-Next | agent_reported | unverified |
Plugins observed
| plugin | version | enabled | verification | note |
|---|---|---|---|---|
| agentic_knowledge | 1.0.0 | no | unsupported | LLM_ROUTER_KNOWLEDGE_AGENTIC_ENABLED is not set, so the plugin keeps its built-in default; verification methods effective_router_config, plugin_runtime_events, … |
| agentic_routing_codex | 1.0.0 | no | unsupported | descriptor declares no plugin-level toggle (benchmark.enabled_when), so activation is not observable and enabled is reported as false; verification methods resp … |
Artifacts
| kind | path | checksum |
|---|---|---|
| manifest | /mnt/data2/dev/develop/ak-bench-data/artifacts/runs/codex-20261102-135659-006548-ab002e/manifest.json | sha256:c636fa8c7840421bf7f6069a7fe99914b9ddb43fb2bcd4dc69e1d0a356e11a5f |
| run_record | /mnt/data2/dev/develop/ak-bench-data/artifacts/runs/codex-20261102-135659-006548-ab002e/run_record.json | sha256:aba04e27875693b1f20230d36e6f7f78c4ebc8ff47c8feba835920c027911126 |
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-20261102-135659-dfdbb7ee | 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-20261102-135659-dfdbb7ee | 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-Flash-Next | unverified | run-20261102-135659-dfdbb7ee |