Commit Graph
5 Commits
Author SHA1 Message Date
pku-xht 15612c1998 review fix: trim duplicate closure evidence 2026-08-14 16:40:23 +08:00
pku-xht b4366e711d feat(subagent): make Claude Code provider directly installable 2026-08-14 16:05:48 +08:00
pku-xht d1629eed45 feat(subagent): make product providers directly installable 2026-08-12 19:28:31 +08:00
Huanqi Cao e56b1ccab2 refactor(loader): tighten the disabled gate and rehome the note
Address review: the gate module docstring now states the actual evaluation
contexts (config after injections against the plugin context, disabled at
every mount decision against the loader context); metadataExpressionErrors
rejects expressions nested below disabled and syntax-checks the disabled
expression itself so an unparseable gate fails at the gate instead of the
boot. The tutorial's !!js claims follow, and the loader note moves to
implemented/architecture with its inbound links retargeted.
2026-08-11 18:52:52 +08:00
Huanqi Cao 6fb226ea24 feat(loader): interpolate the entry disabled field
The Windows platform layer disables tool-bash and inserts the pwsh stack, but the shipped presets each mount a tool-bash row that re-enabled the tool on win32 — the session had both a PowerShell-backed bash tool and tool-pwsh, silently, because no spec pinned the composed preset layer.

The Loader now evaluates a disabled: !!js expression against the loader context at every mount decision; disabled is the only interpolated metadata field, and the raw node stays in the options so write-back keeps the !!js form. The standard/code/cordis presets gate tool-bash with process.platform === 'win32', verify-cordis-config allows expressions in disabled only, and the windows-shell spec pins the preset-level invariant.
2026-08-11 11:33:53 +08:00