open/voyage
1
0
Fork 0
Code Issues Releases 13 Activity
voyage/tests/fixtures/jsonl-schemas.md
Kjell Tore Guttormsen 1989656a9c
 feat(run): the run step names Claude Code's run; owner=run is a built-in owner (A2) 
The coupling to Claude Code's built-in run skill (wave 4, order A2,
decisions 54 and 64). The plan's "run the thing" step, the executor's
End to end part and the plan template each say in one sentence that the
app is seen and driven with run, and that the verdict is still the
End-to-end: command, because run gives no exit code. The template quotes
the name instead of backticking it: every backticked span on a template
step bullet is read as a runnable example.

R2: lib/skills/routing.mjs keeps a short fixed list of Claude Code's own
skills a quiet case may name as owner (BUILTIN_OWNERS, only run, seen in
2.1.303). For such an owner only "not taken" is checked, and the report
says so; ROUTING_NEGATIVE_WON stands, and an owner on no list is still
ROUTING_UNKNOWN_OWNER. skill-writing-criteria-quiet-2 gets owner=run.

The trekplan.md paragraph is reflowed to its old line count so the stats
line_ref there does not move (order B edits the same file); the
trekexecute Phase 9 line_ref fixture moves by two lines.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 18:26:10 +02:00

6.2 KiB
Raw Blame History

Voyage JSONL stats — schema audit (v4.1 input)

Purpose: Field-allowlist input for v4.1 OTel exporter (Step 11). Lists every field every voyage stats JSONL writer emits today, plus the additive fields v4.1 introduces. Load-bearing for Step 11 (field-allowlist) and Step 8 (stats plumbing).

PII-flag: command_excerpt from hooks/scripts/post-bash-stats.mjs slices the first 120 chars of an arbitrary Bash command — may contain operator paths, branch names, or fragments of secrets that survived the secrets-hook. CWE-212 (Improper Cross-boundary Removal of Sensitive Data). The OTel exporter MUST NOT export this field unless the operator explicitly opts in via VOYAGE_EXPORT_INCLUDE_COMMAND_EXCERPT=1 (deferred to v4.2 — v4.1 hard-excludes).

Additive v4.1 fields: profile, phase_models, parallel_agents, external_research_enabled, profile_source. All are forward-compat: existing v4.0 consumers ignore unknown keys, v4.1 consumers get richer signal.

Field table per JSONL writer

schema_id fields writer_path line_ref v4.1 additive PII
trekbrief-stats ts, task, slug, mode, interview_turns, review_iterations, brief_quality, research_topics, auto_research, auto_result, intent_approved, project_dir, order_id, order_claimed_at, order_reason commands/trekbrief.md (orchestrator-emit Phase 7; order_* added by lib/stats/stats-append.mjs) trekbrief.md:1128-1152 profile, phase_models, profile_source none
trekresearch-stats ts, question, mode, scope, engine, slug, project_dir, brief_path, dimensions, dimensions_baseline, dimensions_baseline_preserved, effort, conv_turns, empty_turns, unique_sources, agents_local, agents_external, gemini_used, confidence, contradictions, open_questions lib/stats/stats-append.mjs (trekresearch.md Stats tracking) trekresearch.md:782-808 profile, phase_models, parallel_agents, external_research_enabled, profile_source none
trekplan-stats ts, task, mode, slug, brief_path, project_dir, codebase_size, codebase_files, agents_deployed, deep_dives, research_briefs_used, research_scout_used, critic_verdict, guardian_verdict, outcome lib/stats/stats-append.mjs (trekplan.md Phase 12) trekplan.md:1277-1305 profile, phase_models, parallel_agents, profile_source none
trekexecute-stats (Phase 9 record) ts, plan, plan_type, mode, result, steps_total, steps_passed, steps_failed, steps_skipped, failed_at_step lib/stats/stats-append.mjs (trekexecute.md Phase 9) trekexecute.md:2909-2931 profile, phase_models, profile_source none
trekexecute-stats (autonomy events) ts, event, known_event, payload lib/stats/event-emit.mjs emit() event-emit.mjs:78-99 payload.profile, payload.phase_models, payload.profile_source none
trekexecute-stats (PostToolUse Bash) ts, session_id, command_excerpt, duration_ms, success hooks/scripts/post-bash-stats.mjs (Bash PostToolUse) post-bash-stats.mjs:42-54 none (hook is plugin-level, not profile-aware) command_excerpt (CWE-212)
trekreview-stats ts, slug, verdict, counts (BLOCKER/MAJOR/MINOR/SUGGESTION), reviewed_files_count, mode, duration_ms lib/stats/stats-append.mjs (trekreview.md Phase 8) trekreview.md:636-686 profile, phase_models, profile_source none
trekcontinue-stats ts, project, next_session_label, status lib/stats/stats-append.mjs (trekcontinue.md Phase 5) trekcontinue.md:293-297 profile, profile_source none
token-usage ts, session_id, scope, model, tokens_input, tokens_output, tokens_cache_creation, tokens_cache_read, cost_usd, is_estimate, price_table_version lib/stats/token-usage.mjs captureTokenUsage (via hooks/scripts/otel-export.mjs Stop hook, opt-in VOYAGE_TOKEN_METER) token-usage.mjs:buildRecord n/a (SKAL-2 schema) session_id (stripped at export)

Field-allowlist input for Step 11

The OTel exporter (Step 11 lib/exporters/field-allowlist.mjs) MUST inline the following static const arrays (NOT load from this file at runtime — Step 11 explicit constraint: INLINE static const, IKKE runtime fra tests/fixtures):

EXPORT_ALLOWLIST (numeric/bool/short-string fields safe for OTel metric labels):

ts, slug, mode, brief_quality, auto_research, auto_result,
codebase_size, codebase_files, agents_deployed, deep_dives,
agents_local, agents_external, gemini_used, dimensions, confidence,
contradictions, open_questions, interview_turns, review_iterations,
research_topics, research_briefs_used, research_scout_used,
critic_verdict, guardian_verdict, outcome, plan_type, result,
steps_total, steps_passed, steps_failed, steps_skipped, failed_at_step,
verdict, reviewed_files_count, duration_ms, status, next_session_label,
event, known_event, success, scope,
profile, profile_source, parallel_agents, external_research_enabled,
model, tokens_input, tokens_output, tokens_cache_creation, tokens_cache_read,
cost_usd, is_estimate, price_table_version

EXPORT_DENYLIST (PII or high-cardinality, never export):

task, question, project_dir, project, plan, brief_path, command_excerpt, payload, counts, phase_models, session_id,
order_id, order_claimed_at, order_reason

Notes:

  • task and question may contain user-content prose → high-cardinality + PII risk.
  • project_dir and paths leak filesystem layout.
  • command_excerpt per CWE-212 above.
  • phase_models is a structured object (6 keys) — too high-cardinality for label; profile name (profile) is the safe summary. v4.2 may revisit if operators ask.
  • counts (review BLOCKER/MAJOR/MINOR/SUGGESTION) is a nested object — Step 11 exporter flattens to voyage_review_counts_blocker/_major/_minor/_suggestion metrics rather than a label.
  • session_id is a UUID — high-cardinality, not useful as a label, log-only.

Cross-reference

  • Step 8 (stats plumbing) — adds profile + phase_models + profile_source to all 6 orchestrator-emit sites listed above.
  • Step 11 (field-allowlist) — codifies the EXPORT_ALLOWLIST/DENYLIST arrays above as inline static consts in lib/exporters/field-allowlist.mjs.
  • Step 9 (Prometheus textfile) — emits one metric line per allowlist-numeric field per JSONL writer; PII-flagged fields are dropped at format-layer, not export-layer.