Steven Chong 679757f3df fix(measurement): pair orphan tool_use blocks in cacheable-prefix probe ...

count_tokens validates structural pairing and rejects truncated prefix
bodies that contain tool_use blocks whose tool_result was in the
dropped tail, with: 'messages.<N>: tool_use ids were found without
tool_result blocks'. That's been firing on ~15% of Opus 4.7 rows
(75/503 last 7d) and excluding them from baseline_probe_status='ok'.

Append a synthetic user message with minimal tool_result blocks for
any orphan ids. Adds ~5-10 tokens per orphan (within ~1% of truth)
and converts those rows from 'partial' to 'ok' so they contribute
to honest savings rollups.

Source: ocproxy daemon.log under OCPROXY_PIXELPIPE_DEBUG=1.

2026-05-21 15:13:23 -04:00

..

fixtures

test: real-shape regression fixtures from production events.jsonl

2026-05-20 10:50:16 -04:00

dashboard-api.test.ts

dashboard: sessions UI + stats panel + smooth updates + cleanup

2026-05-18 22:14:00 -04:00

history.test.ts

feat(transform): horizon-aware history-collapse break-even gate

2026-05-21 10:33:07 -04:00

paging.test.ts

fix(gate): scale per-image token cost by numCols (close multi-col loss-risk)

2026-05-19 23:33:22 -04:00

proxy-usage.test.ts

feat(proxy): SSE+JSON output measurement scanner

2026-05-20 15:53:58 -04:00

public-api.test.ts

fix(measurement): pair orphan tool_use blocks in cacheable-prefix probe

2026-05-21 15:13:23 -04:00

render.test.ts

feat(transform): lower SLAB/HISTORY_CHARS_PER_TOKEN 2.5 → 2.0 for Opus 4.7 tokenizer

2026-05-21 14:34:06 -04:00

restart.test.sh

refactor: remove all CLI flags and behavior env vars — single codepath

2026-05-19 17:01:05 -04:00

sessions.test.ts

feat(dashboard): real saved% from count_tokens, rip α-regression dead code

2026-05-19 22:00:14 -04:00

stats.test.ts

cli: add 'pixelpipe stats' subcommand for offline log analysis

2026-05-18 16:13:04 -04:00

tracker.test.ts

feat(transform): per-bucket char attribution telemetry (Task #18 Phase 1)

2026-05-20 21:21:34 -04:00