fix(advise): derive reflex patterns from proposal categories (ticket-106)

[tom-sapletta-com]

Problem

collect_reflex_patterns read analysis['patterns'], but reflex analyze returns proposals / events / statistics, with no patterns key. monag advise therefore always reported "0 wzorców reflex", and the priority readings ignored recurring failures. It also used min_repeat=1, so every one-off event became a proposal (595 on an 8-hour transcript corpus).

Change

• _patterns_from_proposals(): one pattern per proposal category, with summed frequency and group count, used by both the import and CLI runners.
• REFLEX_MIN_REPEAT = 2.

Evidence

On the 8 h tool-failure projection: 228 proposals → patterns operational-failure 3377/136, test-feedback 267/65, governance-friction 192/19, credential-readiness, provider-unavailability. Before the fix: patterns=[].
Full suite: 467 passed. Governance GOV-PASS. Ruff: no new findings in the touched files (one fewer).

Ticket: ticket-106

🤖 Generated with Claude Code

[ifuri-validator-agent]

Validator approval after policy checks for exact head 97ec37e4462ab3b0dde8e12a96cd4df4aab35b43.

Ticket: ticket-106
Correlation ID: local-semcod-monag-pr-129-ticket-106
Model: openai/cursor-auto
Reviewed diff chunks: 1
Advisory LLM verdict: APPROVE
Advisory summary: Reviewed all 1 diff chunk(s). The PR successfully addresses the issue where collect_reflex_patterns failed to find patterns from reflex analyze output. It properly groups proposals by category and computes frequencies and group counts using the new _patterns_from_proposals function. Additionally, REFLEX_MIN_REPEAT is correctly increased to 2 to prevent one-off failures from being reported as patterns. Tests and intent metadata correctly track the changes.
Advisory findings: none
The LLM output above is advisory and was not used as the approval trust root.
Semantic review prerequisite: not_required; policy 676cb4516bbfed2a000e40b9b1b6e4a430ecc761ec546aeb53d721a1905cfdd7.

Actual PR impact radar

Exact range: 452d655cdd4287c86a94a89c9b8816cf3d799b67...97ec37e4462ab3b0dde8e12a96cd4df4aab35b43
Change digest: b3c13a55e9508a52de28dcbb4e5513b3ee921f4d39a8a7f88e1e898c3e4df660
Score: 56/100 (L), estimated 72 min, split recommended: true
Affected services/components: repository-wide/unclassified

Machine-readable radar JSONL and SVG

{"actual_change":{"additions":99,"base_sha":"452d655cdd4287c86a94a89c9b8816cf3d799b67","binary_files":0,"categories":{"code":1,"configuration":1,"docs":1,"tests":1},"change_digest":"b3c13a55e9508a52de28dcbb4e5513b3ee921f4d39a8a7f88e1e898c3e4df660","comparison":"452d655cdd4287c86a94a89c9b8816cf3d799b67...97ec37e4462ab3b0dde8e12a96cd4df4aab35b43","deletions":4,"file_count":4,"files":["project/ticket-106/README.md","project/ticket-106/intent.json","src/monag/advise.py","tests/test_advise.py"],"head_sha":"97ec37e4462ab3b0dde8e12a96cd4df4aab35b43","service_count":0,"services":[]},"assessment_mode":"observed-pr","axes":{"coupling":5,"delivery":2,"scope":3,"uncertainty":3,"validation":1},"complexity":"L","confidence":0.9,"diagnostics":["RADAR-ACCEPTANCE-MISSING","RADAR-BUDGET-EXCEEDED"],"estimate":{"budget_minutes":30,"minutes":72,"within_budget":false},"impact":{"components":["192","267","3377","claude.com","project","src/monag","tests"],"files":["192/19","267/65","3377/136","claude.com/claude-code","project/ticket-106/README.md","project/ticket-106/intent.json","src/monag/advise.py","tests/test_advise.py"],"public_interfaces":[],"runtime_dependencies":0},"schema":"subactor.ticket-radar/v1","score":56,"split":{"parts":[{"estimated_minutes":10,"name":"Implement 192","scope":["192"]},{"estimated_minutes":10,"name":"Implement 267","scope":["267"]},{"estimated_minutes":10,"name":"Implement 3377","scope":["3377"]},{"estimated_minutes":10,"name":"Implement claude.com","scope":["claude.com"]},{"estimated_minutes":10,"name":"Implement project","scope":["project"]},{"estimated_minutes":15,"name":"Validate and project to trackers","scope":["tests","planfile","github/gitlab/jira projections"]}],"reason":"estimated_minutes_exceed_budget","recommended":true},"standards":[{"id":"wellmanifest/dsl","revision":"6c60fc4e0dd1f1bb74f46a7745e28019908d1203","version":"0.1.0-dev"},{"id":"wellmanifest/ticket-lifecycle","revision":"5bf581907a87b46a13a73e6c033d3abe4d9a306f","version":"0.1.0-dev"},{"id":"wellmanifest/git-lifecycle","revision":"7d77d4b7af57e69bc75c3a0290b3a4805c5c4438","version":"0.2.0-dev"},{"id":"wellmanifest/logs","revision":"48c284ef7a069055c0bcb6b900147ce5e65f8b43","version":"0.3.0"}],"ticket_ref":"ticket-106"}

<svg xmlns="http://www.w3.org/2000/svg" width="128" height="128" viewBox="0 0 128 128" role="img"><title>ticket-106: fix(advise): derive reflex patterns from proposal categories (ticket-106)</title><rect width="128" height="128" rx="12" fill="#f8fafc"/><g stroke-width="1"><polygon points="64,55 72,61 69,71 59,71 56,61" fill="none" stroke="#d7dde5"/><polygon points="64,47 80,59 74,78 54,78 48,59" fill="none" stroke="#d7dde5"/><polygon points="64,38 89,56 79,85 49,85 39,56" fill="none" stroke="#d7dde5"/><polygon points="64,30 97,53 84,92 44,92 31,53" fill="none" stroke="#d7dde5"/><polygon points="64,21 105,51 89,99 39,99 23,51" fill="none" stroke="#d7dde5"/><line x1="64" y1="64" x2="64" y2="21" stroke="#aab4c0"/><line x1="64" y1="64" x2="105" y2="51" stroke="#aab4c0"/><line x1="64" y1="64" x2="89" y2="99" stroke="#aab4c0"/><line x1="64" y1="64" x2="39" y2="99" stroke="#aab4c0"/><line x1="64" y1="64" x2="23" y2="51" stroke="#aab4c0"/></g><polygon points="64,38 105,51 79,85 59,71 48,59" fill="#fb923c" fill-opacity="0.45" stroke="#c2410c" stroke-width="2"/><circle cx="64" cy="64" r="3" fill="#c2410c"/><g font-family="sans-serif" font-size="7" fill="#334155"><text x="64" y="11" text-anchor="middle">SCO</text><text x="114" y="48" text-anchor="middle">COU</text><text x="95" y="107" text-anchor="middle">UNC</text><text x="33" y="107" text-anchor="middle">VAL</text><text x="14" y="48" text-anchor="middle">DEL</text></g><text x="64" y="124" text-anchor="middle" font-family="sans-serif" font-size="8" fill="#0f172a">L · 72m</text></svg>

Merge will be attempted after this approval when explicitly authorized. ## Decision record (recomputable)

DECISION D-106-3424
TICKET ticket-106
HEAD_SHA 97ec37e4462ab3b0dde8e12a96cd4df4aab35b43
CORRELATION_ID local-semcod-monag-pr-129-ticket-106
ACTOR agent:ifuri-validator-agent[bot]
APPLIED_RULE P-CORE-015
INPUT author_login = "tom-sapletta-com"
INPUT observed_checks = ["governance / remote lifecycle=PASS","governance / enforce=PASS","onedev/local-verify=PASS"]
INPUT required_checks = ["onedev/local-verify","governance / remote lifecycle","governance / enforce"]
INPUT required_checks_source = "protected registry (env/request)"
INPUT reviewer_login = "ifuri-validator-agent[bot]"
INPUT semantic_review_assessment = {"schema":"subactor.validator/semantic-review-assessment/v1","subject":{"repository":"semcod/monag","pull_request":129,"head_sha":"97ec37e4462ab3b0dde8e12a96cd4df4aab35b43","base_sha":"452d655cdd4287c86a94a89c9b8816cf3d799b67","diff_sha256":"ff94faaeea9e5e88917ef20697b3f61a8bf5919359a7aa0341f9a7e33acd5961"},"policy":{"policy_schema":"subactor.validator/semantic-review-policy/v1","policy_version":1,"policy_sha256":"676cb4516bbfed2a000e40b9b1b6e4a430ecc761ec546aeb53d721a1905cfdd7","required":false,"critical_paths":[],"observed_paths":["project/ticket-106/README.md","project/ticket-106/intent.json","src/monag/advise.py","tests/test_advise.py"]},"grounding":"full-diff-not-per-finding-proof","execution_authority":false,"status":"not_required","reason":null,"review_sha256":null,"unresolved":[]}
INPUT superseded_checks = []
INPUT ticket_radar_receipt = {"schema":"subactor.ticket-radar/v1","base_sha":"452d655cdd4287c86a94a89c9b8816cf3d799b67","head_sha":"97ec37e4462ab3b0dde8e12a96cd4df4aab35b43","change_digest":"b3c13a55e9508a52de28dcbb4e5513b3ee921f4d39a8a7f88e1e898c3e4df660","score":56,"complexity":"L","estimated_minutes":72,"split_recommended":true,"services":[],"authority":"ADVISORY","promotion":"FORBIDDEN"}
VERDICT APPROVE AUTHORITY DETERMINISTIC
REJECTED REQUEST_CHANGES BECAUSE NO_UNSAFE_CHANGE_REASON_FOUND
ADVISORY llm_verdict = "APPROVE" MODEL "openai/cursor-auto"
ASSERT VERDICT_AUTHORITY != "ADVISORY"