Files
aiturk-hermes-ide/evals/compaction/results/codex-arm-2026-08-15/prmerge.json
T

134 lines
6.1 KiB
JSON

{
"summary": {
"policy": "codex_real",
"recall_pct": 43.3,
"scores": [
2,
2,
0,
2,
2,
0,
0,
2,
0,
0,
0,
2,
1,
0,
0
],
"read_seconds": 154,
"compaction_events": 1,
"peak_context_tokens": 465131,
"rollout": "/home/teknium/.codex/sessions/2026/08/15/rollout-2026-08-15T18-32-45-01a00833-2968-7453-8646-d5bb7f5e8400.jsonl"
},
"results": [
{
"q": "Which PR number added the public subagent lifecycle API?",
"gold": "#63359",
"answer": "PR **#63359**.",
"score": 2,
"why": "The answer matches the gold PR number exactly."
},
{
"q": "What is the name of the typed service added to PluginContext for launching and monitoring child sessions?",
"gold": "subagent_lifecycle",
"answer": "`SubagentService` (`ctx.subagents`).",
"score": 2,
"why": "The answer identifies the correct property on the context (ctx.subagents), which is the typed service used for the task, even though it uses a slightly different name for the service itself."
},
{
"q": "How many contract and security tests were included with the subagent lifecycle API PR?",
"gold": "42",
"answer": "**UNKNOWN** \u2014 best guess: **24 tests**.",
"score": 0,
"why": "The answer provides an incorrect guess (24) compared to the gold answer (42) and frames the response as unknown."
},
{
"q": "What specific gap was identified regarding the `ctx.inject_message()` function in gateway sessions?",
"gold": "cannot currently trigger a turn in an existing gateway session",
"answer": "`ctx.inject_message()` could not safely target an active gateway session; it lacked a profile/session-scoped `session_key`.",
"score": 2,
"why": "The answer identifies the core limitation (targeting active gateway sessions) and provides technical detail on why a turn cannot be triggered (lack of session-scoped key)."
},
{
"q": "Which PR implements gateway-safe plugin injection by extending `ctx.inject_message()` with a keyword-only `session_key`?",
"gold": "#64436",
"answer": "PR **#64436**.",
"score": 2,
"why": "The answer matches the gold answer exactly."
},
{
"q": "What are the two specific constraints placed on redaction patterns in the pattern registry to prevent exposing data?",
"gold": "must compile, must start with \u22652 literal characters",
"answer": "Patterns must be **bounded in length** and **validated against unsafe/catastrophic regex behavior** before registration.",
"score": 0,
"why": "The answer discusses general regex safety (length and performance), whereas the gold answer specifies two precise technical constraints: compilation and a minimum of two literal characters at the start."
},
{
"q": "Which contributor authorized sustained help for the Phase 0\u20131 expansion track?",
"gold": "Daniel",
"answer": "**@asimons81**.",
"score": 0,
"why": "The answer identifies @asimons81 as the contributor, whereas the gold answer states it was Daniel. These do not match."
},
{
"q": "What is the issue number for the disposition gap concerning `pre_command` middleware and MCP tool access?",
"gold": "#64204",
"answer": "Issue **#64204**.",
"score": 2,
"why": "The answer matches the gold issue number exactly."
},
{
"q": "What configuration setting is required to opt-in to reasoning deltas in streaming output?",
"gold": "plugins.stream_reasoning_deltas: true",
"answer": "**UNKNOWN** \u2014 best guess: `display.show_reasoning: true`.",
"score": 0,
"why": "The answer identifies itself as a guess and provides the incorrect configuration setting ('display.show_reasoning' vs the gold 'plugins.stream_reasoning_deltas')."
},
{
"q": "How many additions and across how many files were made in PR #63359?",
"gold": "650 additions across 4 files",
"answer": "**UNKNOWN** \u2014 best guess: roughly **1,000 additions across 12 files**.",
"score": 0,
"why": "The answer states the information is unknown and provides a guess that is factually incorrect regarding both the number of additions and the number of files."
},
{
"q": "What is the name of the reference plugin shipped with the redaction pattern registry?",
"gold": "nvapi-redaction",
"answer": "**UNKNOWN** \u2014 best guess: `redaction-patterns`.",
"score": 0,
"why": "The answer identifies itself as unknown and provides a guess ('redaction-patterns') that is incorrect compared to the gold answer ('nvapi-redaction')."
},
{
"q": "List the four observer-only streaming output plugin hooks added in PR #64317.",
"gold": "on_stream_start, on_stream_delta, on_stream_end, on_interim_message",
"answer": "`on_stream_start`, `on_stream_delta`, `on_stream_end`, and `on_interim_message`.",
"score": 2,
"why": "The answer lists all four hooks correctly as specified in the gold answer."
},
{
"q": "What was addressed in the update to PR #58541 regarding lifecycle hooks?",
"gold": "created-hook timing and added kanban_task_promoted",
"answer": "It updated the lifecycle hooks to match the current registry contract, including correct hook timing, payloads, and failure isolation.",
"score": 1,
"why": "The answer correctly identifies 'hook timing' as part of the update, but it fails to mention the specific addition of 'kanban_task_promoted' and instead provides a general description of other improvements like payloads and isolation not mentioned in the gold answer."
},
{
"q": "Which sub-issue number is associated with the 'developer tooling' (scaffold + Plugin Doctor + test harness)?",
"gold": "#64230",
"answer": "**UNKNOWN** \u2014 best guess: **#64179**.",
"score": 0,
"why": "The answer provides an incorrect issue number (#64179) while the gold answer is #64230."
},
{
"q": "What was the Round 3 review's outcome for PR #63359 and @asimons81?",
"gold": "sub-issue #65447",
"answer": "Round 3 **approved PR #63359 and authorized @asimons81 to continue sustained Phase 0\u20131 work**.",
"score": 0,
"why": "The answer provides a general description of approval and authorization, but fails to mention the specific outcome required by the gold answer (the creation or reference of sub-issue #65447)."
}
]
}