Oleks
88fc58b2fd
ci/woodpecker/push/test Pipeline was successful
The stability gate treated every evidence flip as symmetric, and that produced a false downgrade on the candidate it was written for (kotkan/claude-plugin-inference-arbitrage#15). Re-measuring anxious/agent-wip/release-policy-derivation over four real windows with the same script gave 0 -> 2 -> 12 -> 15 invocations at 7/14/27/60 days: monotonic accumulation of a step that runs about once every two days, not a label flipping about. The 7-day window had not caught an unstable candidate, it had failed to observe a real one. So a thin/unmeasured reading now only overturns a `measured` one when its window is at least 90% as wide (observed since->until span). Below that the comparison takes a third verdict, `insufficient-window`: not filed, not downgraded to a boundary question, no FR-6.5 self-report, and carried forward with the wider snapshot left as the standing comparison point. The parity is relative rather than an absolute day count because the adequate width is a property of the candidate's invocation rate, which the auditor does not know in advance. Unchanged, and tested: the reverse direction (thin prior -> measured now) still downgrades, a flip between comparably wide windows still downgrades, and a threshold crossing with `measured` on both sides is never excused by narrowness. An unreadable window is not an exemption either — the flip stands and window_parity records that the check could not run. - bin/stability-classify: window_days/window_parity/deferrable, the insufficient-window verdict, stability_deferrals, window_parity on findings too, insufficient_window + window_parity_ratio in the gate block - bin/audit-snapshot: record deferrals in the snapshot notes so the row is visible on the wiki page instead of silently dropped - design/spec.md: FR-4.5.1 as a testable requirement; S4 restated - design/rubric.md: the third boundary in §5b - skills/offload-audit/SKILL.md: do not file and do not self-report a deferral - tests: real 60-day anxious fixture; cases (f)/(f2) on real data, (j)-(n) synthetic — 7 test files pass Verified against the live store (~/.cache/inference-arbitrage/wiki): the real 7.0d-vs-26.49d comparison now reports insufficient-window with zero findings, while the real 33.4d-vs-26.49d one reports stable at 13.87% and files normally.
336 lines
9.6 KiB
JSON
336 lines
9.6 KiB
JSON
{
|
|
"window": {
|
|
"since": "2026-06-26T17:41:40.988000+00:00",
|
|
"until": "2026-07-30T02:30:59.111000+00:00",
|
|
"requested_since": "2026-05-31T02:30:03.118644+00:00",
|
|
"requested_until": null,
|
|
"sessions": 176
|
|
},
|
|
"plugin": "anxious",
|
|
"tool_versions": {
|
|
"cc_tokens_path": "/home/oleks/projects/claude-plugins/token-budget/bin/cc-tokens"
|
|
},
|
|
"coverage": {
|
|
"attributed_turns": 5197,
|
|
"candidate_turns": 249648,
|
|
"ratio": 0.021,
|
|
"caveat": "hook-driven and unattributed agent turns excluded"
|
|
},
|
|
"totals": {
|
|
"weighted_tokens": 35722973,
|
|
"cost_estimate_usd": 178.61,
|
|
"invocations": 700,
|
|
"mechanical_share": 0.106
|
|
},
|
|
"skills": [
|
|
{
|
|
"skill": "anxious:agent-wip",
|
|
"invocations": 15,
|
|
"turns": 375,
|
|
"sidechain_turns": 0,
|
|
"weighted_tokens": 14007053,
|
|
"cost_estimate_usd": 70.04,
|
|
"share_of_plugin": 0.392,
|
|
"mtr": 0.144,
|
|
"judgment_density": 0.027,
|
|
"retry_density": 0.069,
|
|
"offload_waste": 1532536,
|
|
"read_amplification": 383.83,
|
|
"fanout_multiplier": 1.0,
|
|
"repetition_factor": 3.322,
|
|
"ngrams": [
|
|
{
|
|
"sig": [
|
|
"label_write(color=<str>, method=<str>, name=<str>, owner=<str>, repo=<str>)",
|
|
"label_write(color=<str>, method=<str>, name=<str>, owner=<str>, repo=<str>)",
|
|
"issue_write(index=<n>, labels=<list>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 5,
|
|
"invocations": 4,
|
|
"waste": 345101
|
|
},
|
|
{
|
|
"sig": [
|
|
"Edit(file_path=<path>, new_string=<str>, old_string=<str>, replace_all=<bool>)",
|
|
"Read(file_path=<path>)",
|
|
"Edit(file_path=<path>, new_string=<str>, old_string=<str>, replace_all=<bool>)"
|
|
],
|
|
"recurrences": 3,
|
|
"invocations": 3,
|
|
"waste": 342125
|
|
},
|
|
{
|
|
"sig": [
|
|
"Read(file_path=<path>)",
|
|
"Read(file_path=<path>)",
|
|
"Bash(command=grep <str>, description=<str>)"
|
|
],
|
|
"recurrences": 3,
|
|
"invocations": 3,
|
|
"waste": 302043
|
|
},
|
|
{
|
|
"sig": [
|
|
"Bash(command=echo <str>, description=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 3,
|
|
"invocations": 3,
|
|
"waste": 299691
|
|
},
|
|
{
|
|
"sig": [
|
|
"ToolSearch(max_results=<n>, query=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)",
|
|
"issue_read(index=<n>, method=<str>, owner=<str>, repo=<str>)"
|
|
],
|
|
"recurrences": 4,
|
|
"invocations": 4,
|
|
"waste": 258683
|
|
}
|
|
],
|
|
"offload_value": 4953520
|
|
},
|
|
{
|
|
"skill": "anxious:delivery-flow",
|
|
"invocations": 1,
|
|
"turns": 1,
|
|
"sidechain_turns": 0,
|
|
"weighted_tokens": 48152,
|
|
"cost_estimate_usd": 0.24,
|
|
"share_of_plugin": 0.001,
|
|
"mtr": 0.0,
|
|
"judgment_density": 0.0,
|
|
"retry_density": 0.0,
|
|
"offload_waste": 0,
|
|
"read_amplification": 378.0,
|
|
"fanout_multiplier": 1.0,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 0
|
|
}
|
|
],
|
|
"agents": [
|
|
{
|
|
"agent": "anxious:issuer-agent",
|
|
"invocations": 608,
|
|
"turns": 4207,
|
|
"sidechain_turns": 4207,
|
|
"weighted_tokens": 13682748,
|
|
"cost_estimate_usd": 68.41,
|
|
"share_of_plugin": 0.383,
|
|
"mtr": 0.097,
|
|
"judgment_density": 0.051,
|
|
"retry_density": 0.082,
|
|
"offload_waste": 778919,
|
|
"read_amplification": 545.98,
|
|
"fanout_multiplier": 0.2,
|
|
"repetition_factor": 7.741,
|
|
"ngrams": [
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 107,
|
|
"invocations": 47,
|
|
"waste": 874165
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 56,
|
|
"invocations": 25,
|
|
"waste": 496902
|
|
},
|
|
{
|
|
"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": 28,
|
|
"invocations": 26,
|
|
"waste": 318874
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 31,
|
|
"invocations": 10,
|
|
"waste": 207299
|
|
},
|
|
{
|
|
"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": 13,
|
|
"invocations": 13,
|
|
"waste": 184334
|
|
}
|
|
],
|
|
"offload_value": 5722452
|
|
},
|
|
{
|
|
"agent": "repo-worker",
|
|
"invocations": 2,
|
|
"turns": 268,
|
|
"sidechain_turns": 268,
|
|
"weighted_tokens": 1816949,
|
|
"cost_estimate_usd": 9.08,
|
|
"share_of_plugin": 0.051,
|
|
"mtr": 0.19,
|
|
"judgment_density": 0.004,
|
|
"retry_density": 0.075,
|
|
"offload_waste": 303294,
|
|
"read_amplification": 650.6,
|
|
"fanout_multiplier": 0.66,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 302081
|
|
},
|
|
{
|
|
"agent": "anxious:steward-agent",
|
|
"invocations": 56,
|
|
"turns": 225,
|
|
"sidechain_turns": 225,
|
|
"weighted_tokens": 5597218,
|
|
"cost_estimate_usd": 27.99,
|
|
"share_of_plugin": 0.157,
|
|
"mtr": 0.009,
|
|
"judgment_density": 0.08,
|
|
"retry_density": 0.076,
|
|
"offload_waste": 17835,
|
|
"read_amplification": 677.33,
|
|
"fanout_multiplier": 0.34,
|
|
"repetition_factor": 7.728,
|
|
"ngrams": [
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 106,
|
|
"invocations": 29,
|
|
"waste": 2987563
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 77,
|
|
"invocations": 22,
|
|
"waste": 2434027
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 55,
|
|
"invocations": 15,
|
|
"waste": 1816278
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, run_in_background=<bool>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 40,
|
|
"invocations": 8,
|
|
"waste": 1196514
|
|
},
|
|
{
|
|
"sig": [
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)",
|
|
"Agent(description=<str>, prompt=<str>, subagent_type=<str>)"
|
|
],
|
|
"recurrences": 5,
|
|
"invocations": 3,
|
|
"waste": 205780
|
|
}
|
|
],
|
|
"offload_value": 126805
|
|
},
|
|
{
|
|
"agent": "anxious:docs-agent",
|
|
"invocations": 10,
|
|
"turns": 98,
|
|
"sidechain_turns": 98,
|
|
"weighted_tokens": 502645,
|
|
"cost_estimate_usd": 2.51,
|
|
"share_of_plugin": 0.014,
|
|
"mtr": 0.276,
|
|
"judgment_density": 0.061,
|
|
"retry_density": 0.051,
|
|
"offload_waste": 107413,
|
|
"read_amplification": 164.08,
|
|
"fanout_multiplier": 0.34,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 100861
|
|
},
|
|
{
|
|
"agent": "feature-dev:code-reviewer",
|
|
"invocations": 3,
|
|
"turns": 4,
|
|
"sidechain_turns": 4,
|
|
"weighted_tokens": 26969,
|
|
"cost_estimate_usd": 0.13,
|
|
"share_of_plugin": 0.001,
|
|
"mtr": 0.75,
|
|
"judgment_density": 0.25,
|
|
"retry_density": 0.0,
|
|
"offload_waste": 13850,
|
|
"read_amplification": 797.8,
|
|
"fanout_multiplier": 0.09,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 10388
|
|
},
|
|
{
|
|
"agent": "cluster:gitea-agent",
|
|
"invocations": 5,
|
|
"turns": 19,
|
|
"sidechain_turns": 19,
|
|
"weighted_tokens": 41235,
|
|
"cost_estimate_usd": 0.21,
|
|
"share_of_plugin": 0.001,
|
|
"mtr": 0.105,
|
|
"judgment_density": 0.158,
|
|
"retry_density": 0.0,
|
|
"offload_waste": 4163,
|
|
"read_amplification": 299.0,
|
|
"fanout_multiplier": 0.24,
|
|
"repetition_factor": 1.0,
|
|
"ngrams": [],
|
|
"offload_value": 3505
|
|
}
|
|
]
|
|
}
|