feat(evals): seedSkills opt-in for PTY slash-command tests + tripwire

Wire ClaudePtyOptions.seedSkills through launchClaudePty: when set (and
hermetic, and no per-test CLAUDE_CONFIG_DIR override), the child gets
hermeticSkillsConfigDir() so typed /skill slash commands resolve instead
of dying as Unknown command before any model turn. Opted in at the three
runPlanSkill* helpers and the four direct-launch slash-command tests
(plan-design-with-ui, plan-ceo-mode-routing, autoplan-chain,
ship-idempotency).

New static tripwire (test/pty-skill-seeding-wiring.test.ts): any test
file that sends a slash command over the PTY must route through a
runPlanSkill* helper or pass seedSkills: true — an unseeded slash-command
test spends money and measures nothing. hermetic-wiring.test.ts now
blesses the repo-tree seeding path explicitly (config dir under runRoot,
symlinks into the repo checkout, never operator ~/.claude).

The CI "Register gstack skills for PTY smoke" step keeps a keep-me note:
container cross-mount symlinks defeat the TUI scanner and HOME is not
hermeticized, so the real-file copies there must survive this change.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
(cherry picked from commit 63c52269daaffb833b3105ea9b4b99be6df8fec7)
This commit is contained in:
Garry Tan
2026-08-12 15:31:47 -07:00
parent 5819203905
commit 281227262d
8 changed files with 122 additions and 1 deletions
+8
View File
@@ -183,6 +183,14 @@ jobs:
# bin/ + sections/ are committed). $HOME is /github/home here; the spawned
# claude inherits it (this runner adds no HOME/CLAUDE_CONFIG_DIR override,
# no hermetic mode) and the Seed step already proved claude reads $HOME.
#
# KEEP THIS STEP even though seedSkills/hermeticSkillsConfigDir() now
# registers skills for hermetic PTY children: that registry is SYMLINKS
# into the repo checkout, and this container's cross-mount symlinks
# defeat the TUI skill scanner (see the note inside the step below) —
# the real-file copies here are what the TUI actually reads. HOME is
# also not hermeticized, so the absolute ~/.claude/skills/gstack/...
# preamble paths resolve through the gstack root symlink this step makes.
- name: Register gstack skills for PTY smoke
if: matrix.suite.name == 'e2e-pty-plan-smoke'
run: |