gm-skill 2.0.2056 → 2.0.2058

package/AGENTS.md

@@ -71,7 +71,7 @@ Record only non-obvious multi-run-cost caveats; prune stale; never document the
 
 **No UTF-8 BOM in any tracked source file** -- always `-Encoding utf8` (no BOM) or the `Write` tool; PowerShell defaults betray this. Checked manually on sight; one sighting spawns the full-tree sweep. Cause + breakage mechanics in the recall store (`recall: BOM regression incident`).
 
-**No graphical symbols; convert to industry-standard text on sight.** Any non-ASCII decorative glyph (arrows, box/geometric glyphs, stars, dots, bullets, checks/crosses, emojis) is forbidden in all output and source -- convert it to its plain-ASCII equivalent the same turn (the word, `->`, `-`/`*`, `[x]`/`[ ]`, done/todo/pass/fail). Tell-tale-AI class: one sighting spawns the full-codebase sweep, never a one-off edit. Exempt: functional code operators (`=>`, `??`, `?.`, comparison/math), frozen changelog/git-log entries, binary stores, intentional icon-font/CSS-content product glyphs. `ccsniff --glyph-discipline` flags decorative glyphs post-hoc (run each audit, like `--git-discipline`/`--search-discipline`).
+**No graphical symbols; convert to industry-standard text on sight.** Any non-ASCII decorative glyph (arrows, box/geometric glyphs, stars, dots, bullets, checks/crosses, emojis) is forbidden in all output and source -- convert it to its plain-ASCII equivalent the same turn (the word, `->`, `-`/`*`, `[x]`/`[ ]`, done/todo/pass/fail). Tell-tale-AI class: one sighting spawns the full-codebase sweep, never a one-off edit. Exempt: functional code operators (`=>`, `??`, `?.`, comparison/math), frozen changelog/git-log entries, binary stores, intentional icon-font/CSS-content product glyphs. `ccsniff --glyph-discipline` flags decorative glyphs post-hoc (run each audit, like `--git-discipline`/`--search-discipline`/`--verb-bypass-discipline`/`--spool-discipline`).
 
 **Implicit, not explicit, in skill prose**: skill files elicit, never describe -- terse imperatives, no recipes/citations/manuals; boot-edge ABI (spool paths, JSON fields, verb names, deviation ids, gate names) stays explicit; SKILL.md keeps only invocation syntax, transition markers, gate conditions, constraints, exact-usage examples. Full criteria: the recall store (`recall: implicit-not-explicit skill prose criteria`).
 
@@ -105,7 +105,7 @@ A task that reduces to read/investigate/report, or a change confined to files th
 
 **Disciplines are isolated knowledge stores**, tracked, `@<name>` sigil-scoped, enabled list at `.gm/disciplines/enabled.txt` (one name per line; `discipline_note.rs::active_policies()` auto-surfaces each enabled discipline's `.gm/disciplines/<name>/policy.md` on every `instruction`). Detail: the recall store (`recall: gm disciplines mechanics`).
 
-**Every runtime config surface, indexed**: `.gm/instructions/<key>.md` + `.gm/instructions/source.json` (prose vendoring, see above); `.gm/instructions/fsm/graph.json` (phase-graph override, write path is the `fsm-vendor` verb, see SKILL.md); `.gm/browser-config.json` (`BrowserConfig::load`, per-project -- `cdp_poll_timeout_ms` default 1000, `cdp_poll_interval_ms` default 250, `chrome_ready_deadline_ms` default 30000, `eval_timeout_grace_ms` default 6000, `headless` default false, `session_idle_timeout_ms` default 1800000); `.gm/daemon-project-config.json` (`gm_concurrency_limit`, per-project fairness cap on the shared pool); `~/.agentplug/daemon-config.json` (`DaemonConfig::load`, machine-wide daemon lifecycle timing); `.gm/disciplines/enabled.txt` + `.gm/disciplines/<name>/policy.md` (above); `AGENTPLUG_NO_DAEMON`/`CLAUDE_PROJECT_DIR`/`GM_PLUGKIT_SKIP_SELF_STALE_CHECK` (env toggles, SKILL.md documents the third). Daemon-scoped fields (`daemon-project-config.json`, `~/.agentplug/daemon-config.json`) fully detailed in `.gm/daemon-config-reference.md`; this line is the top-level index into that doc and the others.
+**Every runtime config surface, indexed**: `.gm/instructions/<key>.md` + `.gm/instructions/source.json` (prose vendoring, see above); `.gm/instructions/fsm/graph.json` (phase-graph override, write path is the `fsm-vendor` verb, see SKILL.md); `.gm/browser-config.json` (`BrowserConfig::load`, per-project -- `cdp_poll_timeout_ms` default 1000, `cdp_poll_interval_ms` default 250, `chrome_ready_deadline_ms` default 30000, `eval_timeout_grace_ms` default 6000, `headless` default false, `session_idle_timeout_ms` default 1800000); `.gm/daemon-project-config.json` (`gm_concurrency_limit`, per-project fairness cap on the shared pool); `~/.agentplug/daemon-config.json` (`DaemonConfig::load`, machine-wide daemon lifecycle timing, including the `side_plugin_concurrency` pool-size knob for the shared bert/treesitter/libsql instances); `.gm/disciplines/enabled.txt` + `.gm/disciplines/<name>/policy.md` (above); `AGENTPLUG_NO_DAEMON`/`CLAUDE_PROJECT_DIR`/`GM_PLUGKIT_SKIP_SELF_STALE_CHECK` (env toggles, SKILL.md documents the third). Daemon-scoped fields (`daemon-project-config.json`, `~/.agentplug/daemon-config.json`) fully detailed in `.gm/daemon-config-reference.md`; this line is the top-level index into that doc and the others.
 
 **Nothing fake in source the user runs**: stub/mock/placeholder-return/fixture-only-path/demo-mode-short-circuit/"TODO: implement" forbidden in shipped code. Scaffolds/shims permitted only delegating to real behavior (upstream API, subprocess, disk); check for an existing library before adding a shim. Detection = behavioral: always-succeeds, input-invariant, or type-signature-satisfying short-circuit = stub. Acceptance = real input through real code into real output, witnessed. `Mock*`/`Fake*`/`Stub*` names checked at VERIFY explicitly, not left prose-only (`recall: nevil false-completion mock-network incident`). A row marked `completed` by documenting it (a README "Future Optimizations" section, a design note) instead of implementing it is the same violation -- `prd-resolve` structurally refuses two PRD rows sharing byte-identical `witness_evidence` text (`deviation.prd-resolve-duplicate-witness`), the copy-paste tell of rubber-stamped completion.
 

package/README.md

@@ -60,7 +60,7 @@ gm/
 |-- skills/gm/        <- the skill (SKILL.md), installed as /gm
 |-- bin/               <- bootstrap + installer + plugkit wasm pins (gmsniff / ccsniff are separate npm packages, `bun x gmsniff`, `bun x ccsniff`)
 |-- scripts/           <- publish-time helper scripts
-|-- gm-plugkit/        <- separate npm package: thin launcher + bootstrap that delegates to the native agentplug-runner, with the JS wasm-wrapper kept only as a fallback host
+|-- gm-plugkit/        <- separate npm package: thin launcher + bootstrap that downloads and delegates to the native agentplug-runner (sole loader, no JS-wrapper fallback)
 |-- gm.json            <- version + plugkit pin
 |-- package.json       <- npm publish manifest
 |-- AGENTS.md          <- architectural rules (present-tense, no history)
@@ -87,7 +87,7 @@ Every tool the agent uses is a dispatch verb. No direct shell, no direct file wr
 - **`recall`**: vector + KV recall against `rs-learn`, scored by cosine x recency, namespace-aware
 - **`codesearch`**: semantic vector search across the project
 - **`memorize`**: write to the recall index (with the BGE query/passage prefix asymmetry)
-- **`browser`**: managed Chrome session with project-scoped profile at `.gm/browser-profile/`
+- **`browser`**: headful-by-default Chrome session driven natively by `agentplug` (CDP direct, no JS wrapper) -- a process-wide session registry keeps the launched Chrome child + CDP port alive across dispatches instead of relaunching per-call, profile persisted at `.gm/browser-chrome-profile-<session_id>/`; `session new|list|close|reset <id>` manages sessions explicitly
 - **`git_status` / `branch_status` / `git_push`**: git verbs that gate on porcelain
 - **`filter`**: in-wasm stdout-compaction (grep/ls/tree/json/diff)
 
@@ -123,7 +123,14 @@ The plugkit wasm itself is built and released by [rs-plugkit](https://github.com
 
 ## developing gm itself
 
-`rs-plugkit/` is a git submodule (rs-plugkit's Rust source, not a compiled artifact). A plain `git clone` leaves it empty -- clone with submodules, or init it after the fact:
+Seven git submodules, source only, none compiled artifacts:
+
+- **`rs-plugkit/`** -- the wasm guest: orchestrator, gates, spool dispatch (the gm "brain")
+- **`agentplug/`** -- the native host that loads that wasm and drives `browser`/`task` natively via CDP, plus the shared-plugin loader
+- **`agentplug-bert`**, **`agentplug-libsql`**, **`agentplug-treesitter`** -- the shared native plugins agentplug loads alongside the gm wasm (embeddings, vector storage, syntax parsing)
+- **`rs-codeinsight`**, **`rs-search`** -- codebase-indexing and search backends the `codesearch` verb consumes
+
+A plain `git clone` leaves all seven empty -- clone with submodules, or init them after the fact:
 
 ```
 git clone --recurse-submodules https://github.com/AnEntrypoint/gm.git
@@ -131,7 +138,7 @@ git clone --recurse-submodules https://github.com/AnEntrypoint/gm.git
 git submodule update --init --recursive
 ```
 
-An empty `rs-plugkit/` directory after a normal `git clone` is expected, not a bug -- it only matters if you're changing rs-plugkit's own Rust source (orchestrator, gates, spool dispatch) rather than the skill/installer JS in this repo's own tree.
+Empty submodule directories after a normal `git clone` are expected, not a bug -- they only matter if you're changing one of these repos' own source rather than the skill/installer JS in this repo's own tree.
 
 ## license
 

package/bin/plugkit-slim.wasm.sha256

@@ -1 +1 @@
-1ce7dffacf51e249053b52078eda82c5078d6c7326f63cdb6eb7eccd8f3dfdff  plugkit-slim.wasm
+33cd0cbebece68b2ea2a471484fb8ed5f89563f2cdf5e3911431d77891de0872  plugkit-slim.wasm

package/bin/plugkit.version

@@ -1 +1 @@
-0.1.951
+0.1.952

package/bin/plugkit.wasm.sha256

@@ -1 +1 @@
-d1c18f62093d596a4026c11db5c9f2769b40a1658eff83c1ab796385c2995404  plugkit.wasm
+778ee71c1742320da0555a43013b9895599c1dd223ab20e2d69f932601619aec  plugkit.wasm

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.2056",
+  "version": "2.0.2058",
   "description": "Bootstrap and daemon-spawn tool for gm plugkit binary. Downloads the correct platform wasm, verifies SHA256, and launches agentplug-runner (the native wasm host) as the spool watcher daemon.",
   "main": "index.js",
   "bin": {

package/gm-plugkit/plugkit-slim.wasm.sha256

@@ -1 +1 @@
-1ce7dffacf51e249053b52078eda82c5078d6c7326f63cdb6eb7eccd8f3dfdff  plugkit-slim.wasm
+33cd0cbebece68b2ea2a471484fb8ed5f89563f2cdf5e3911431d77891de0872  plugkit-slim.wasm

package/gm-plugkit/plugkit.version

@@ -1 +1 @@
-0.1.951
+0.1.952

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.2056",
+  "version": "2.0.2058",
   "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",
@@ -17,5 +17,5 @@
   "publishConfig": {
     "access": "public"
   },
-  "plugkitVersion": "0.1.951"
+  "plugkitVersion": "0.1.952"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-skill",
-  "version": "2.0.2056",
+  "version": "2.0.2058",
   "description": "Canonical universal harness — AI-native software engineering via skill-driven orchestration; bootstraps plugkit for task execution and session isolation. Install in any AI coding agent host.",
   "author": "AnEntrypoint",
   "license": "MIT",