voyage/hooks/scripts
Kjell Tore Guttormsen 6dafdf2a2a fix(research-loop-cap): resolve the data root in code so the loop can run
CLAUDE_PLUGIN_DATA is empty in the Bash tool's process env, and the Phase 5
bash snippet is the cap's only caller. resolveLedgerPath() returned null there
and allowTurn() failed closed, so the budget gate denied turn 1 of every real
run: the loop this delivery exists to bound could never spend a turn, and the
pre-registered measurement could not be run at all.

resolveDataRoot() is now the single root for everything the loop writes --
CLAUDE_PLUGIN_DATA when the harness sets it, ~/.claude/voyage when it does
not. Three consumers resolve through it, which is the point: the cap ledger,
the PreToolUse hook's scope-marker lookup, and the command's bash snippets.
A writer and a reader that resolved the root separately are what made the
enforcement hook allow unconditionally in every real run while CLAUDE.md and
docs/architecture.md called it enforcing.

Same root cause, same commit:
- Marker write and remove now share ONE absolute-path guard and one root; the
  write requires a non-empty CLAUDE_CODE_SESSION_ID before composing the path
  (unset, the marker was named `.json`, which no lookup matches and no TTL
  sweep cleans up).
- The per-turn gates resolve VOYAGE_ROOT with a plugin-cache fallback and
  reserve exit 2 for "gate could not run". Interpolating an empty
  ${CLAUDE_PLUGIN_ROOT} ran `node /lib/...` -> exit 1, which the contract read
  as "privacy gate says no" -- an unsatisfiable rewrite loop no query could
  clear.

Two now-unreachable deny branches are removed rather than left as dead safety
claims (allowTurn's no_plugin_data_dir; the hook's uncountable-ledger deny).
The fail-closed stance stays where it is still real: a ledger that cannot be
WRITTEN denies the turn.

Verified end-to-end through the real bash snippets and the real hook with both
variables stripped and HOME sandboxed: marker written under the fallback root,
8 turns spent, 9th denied, hook exits 2, and exits 0 again after removal.
Note: the fallback exit-2 branch fires against the installed v5.9.1 cache,
which predates lib/util/research-loop-cap.mjs -- correct behaviour, and it
clears when the plugin is reinstalled.

Review findings 2670c10a, fbd6d534, 93550dfb.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011vPSXe88qp5aqWUqbDNWoF
2026-08-12 22:26:46 +02:00
..
otel-export.mjs feat(observability): opt-in token capture in Stop hook (VOYAGE_TOKEN_METER) 2026-06-26 14:42:58 +02:00
post-bash-stats.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00
post-compact-flush.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00
pre-agent-cap.mjs fix(research-loop-cap): resolve the data root in code so the loop can run 2026-08-12 22:26:46 +02:00
pre-bash-executor.mjs fix(hooks): close the bypasses anchoring opened in the destructive-command rule 2026-08-12 22:03:22 +02:00
pre-compact-flush.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00
pre-write-executor.mjs chore(voyage): W3 hardening (S2) — exec-form hooks, enforced disallowed-tools, F2 decision 2026-06-18 12:03:11 +02:00
session-title.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00