oleks
dcec9cabfb
Phase 7 filed anxious/agent-wip/release-policy-derivation as `measured` at 11.94% of audited spend on a 30-day window. The same candidate over 7 days came back `thin` at 0.00%. Only the date range differed. A human reading either issue body alone cannot know the other exists, which is rubric.md §4a's failure mode reached through the plugin's own headline number. That was caught by a human running a second skeptical review — luck, not a control. It is now mechanical, in the same register as FR-4.2's overrule-case gate: - bin/stability-classify matches each `file` candidate against the most recent prior snapshot recording it (FR-5.2 identity) and downgrades it to a boundary question if `measurement_strength` changed or the share crossed the 2% filing threshold between windows. Movement within a label is a trend, not an instability; no prior window is `unchecked`, not unstable (FR-2.4). - The downgrade is a finding against THIS repo, not the target's — the target did not change, the auditor described it two ways. Carries an `ia-stability` marker so a re-run comments rather than duplicating. - bin/ia_store.py factors the store and identity resolution out of audit-snapshot so both scripts hash signatures identically. A divergence there would make the gate match nothing and fail open. Documented as spec FR-4.5 and rubric §5b (shipped verbatim in references/). Wired into skills/offload-audit as step 4b, before filing-plan; steps 5-6 now consume its output rather than classified.json. S4 is retired in its old form — a human triage catching a bad candidate is not a repeatable test — and re-passed as: the gate catches the real release-policy-derivation case with no human in the loop. Asserted in tests/stability.test.sh case (f) against the verbatim two-window Phase 7 output. Closes kotkan/claude-plugin-inference-arbitrage#11 Suite: 178 assertions, exit 0.
117 lines
3.0 KiB
JSON
117 lines
3.0 KiB
JSON
{
|
|
"window": {
|
|
"since": "2026-07-22T15:04:13.318000+00:00",
|
|
"until": "2026-07-29T15:04:20.306000+00:00",
|
|
"requested_since": "2026-07-22T15:04:13.270540+00:00",
|
|
"requested_until": null,
|
|
"sessions": 69
|
|
},
|
|
"plugin": "anxious",
|
|
"tool_versions": {
|
|
"cc_tokens_path": "/home/oleks/projects/claude-plugins/token-budget/bin/cc-tokens"
|
|
},
|
|
"coverage": {
|
|
"attributed_turns": 1493,
|
|
"candidate_turns": 45384,
|
|
"ratio": 0.033,
|
|
"caveat": "hook-driven and unattributed agent turns excluded"
|
|
},
|
|
"totals": {
|
|
"weighted_tokens": 4036235,
|
|
"cost_estimate_usd": 20.18,
|
|
"invocations": 146,
|
|
"mechanical_share": 0.179
|
|
},
|
|
"skills": [],
|
|
"agents": [
|
|
{
|
|
"agent": "anxious:issuer-agent",
|
|
"invocations": 144,
|
|
"turns": 1487,
|
|
"sidechain_turns": 1487,
|
|
"weighted_tokens": 3856203,
|
|
"cost_estimate_usd": 19.28,
|
|
"share_of_plugin": 0.955,
|
|
"mtr": 0.18,
|
|
"judgment_density": 0.019,
|
|
"retry_density": 0.132,
|
|
"offload_waste": 536202,
|
|
"read_amplification": 492.12,
|
|
"fanout_multiplier": 1.0,
|
|
"repetition_factor": 5.755,
|
|
"ngrams": [
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 23,
|
|
"invocations": 21,
|
|
"waste": 277765
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 10,
|
|
"invocations": 10,
|
|
"waste": 151483
|
|
},
|
|
{
|
|
"sig": [
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 11,
|
|
"invocations": 9,
|
|
"waste": 133610
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 7,
|
|
"invocations": 7,
|
|
"waste": 127433
|
|
},
|
|
{
|
|
"sig": [
|
|
"Bash(command=cat <str>)",
|
|
"Bash(command=cat <str>)",
|
|
"Bash(command=cat <str>)"
|
|
],
|
|
"recurrences": 27,
|
|
"invocations": 9,
|
|
"waste": 102394
|
|
}
|
|
],
|
|
"offload_value": 3027155
|
|
},
|
|
{
|
|
"agent": "anxious:steward-agent",
|
|
"invocations": 2,
|
|
"turns": 6,
|
|
"sidechain_turns": 6,
|
|
"weighted_tokens": 180032,
|
|
"cost_estimate_usd": 0.9,
|
|
"share_of_plugin": 0.045,
|
|
"mtr": 0.0,
|
|
"judgment_density": 0.167,
|
|
"retry_density": 0.333,
|
|
"offload_waste": 0,
|
|
"read_amplification": 0.0,
|
|
"fanout_multiplier": 1.0,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 0
|
|
}
|
|
]
|
|
}
|