dsh-pstack 0.2.0-beta.1 → 0.2.0

package/cordis.patch.yml

@@ -1,39 +1,117 @@
 # dsh-pstack bundle patch.
 #
-# `pstack` registers the bundled skill provider. `pstack-subagent` registers
-# `pstack_subagent`, which starts one child per activation and re-reads the role
-# file on every delegation. `pstack-history` registers `pstack_history`, the
-# restricted read-only history tool; it reads raw events through `sessionQuery`
-# and authorizes the caller and its direct children only.
+# `pstack` registers the bundled skill provider and `pstack_skill`, the trusted loader
+# that can reach skills hidden with `disable-model-invocation`.
+# `pstack-models` registers the read-only model/effort directory used by `/setup-pstack`.
+# `pstack-roles` exposes the same role file to the Plugins configuration page through a
+# Typert Remote service; its browser half is declared by `dsh.client` in package.json.
+# `pstack-subagent` registers `pstack_subagent`, which re-reads the role file on every
+# delegation and selects one of the pstack agent presets below.
+# `pstack-script` registers `pstack_script`, the only supported way to run the bundled
+# Node artefacts under both the npm CLI and the Desktop (Electron) runtime.
 #
-# The two worktree rows carry the README promise that worktree support ships as a
-# necessary dependency: the bundle turns the official integration on when the
-# profile does not have it, and mounts nothing when it does. `disabled: !!js` is
-# evaluated by the Loader at every mount decision, and each expression reads the
-# composed row list rather than a startup snapshot. The row handle is
-# `ctx[Symbol.for('cordis.entry')]` (this entry), not `ctx.fiber.entry`, which
-# resolves to the enclosing `include` row and therefore never sees these siblings.
-# `scripts/worktree-mount.ts` owns the text of both expressions and `check:assets`
-# fails when this file drifts from it. See
-# docs/decisions/2026-10-26-worktree-guard-reads-own-entry.md.
-#
-# `pstack-history` is appended after the unit-4 rows so no delivered line moves.
-# Row order is not part of the history contract; the two worktree guards, by
-# contrast, stay adjacent and byte-identical to their generator.
+# The two presets are ordinary `@deepseek-ai/dsh-agent-preset` declarations. They own the
+# child persona and tool composition; `pstack_subagent` only passes `agentPreset`. Keeping
+# the tool list here is what makes `comment-sicko` read-only without a per-call field:
+# `dsh-tool-fs` registers `read` but not `write` or `edit`.
 - insert:
     - id: pstack
       name: dsh-pstack
+    - id: pstack-models
+      name: dsh-pstack/models
+    - id: pstack-roles
+      name: dsh-pstack/roles
     - id: pstack-subagent
       name: dsh-pstack/subagent
       config:
         maxDepth: 2
-    - id: pstack-worktree
-      name: '@deepseek-ai/dsh-experimental-worktree'
-      disabled: !!js "(() => { const own = ctx[Symbol.for('cordis.entry')]; const rows = own && own.parent && own.parent.data; if (!Array.isArray(rows)) return false; return rows.some((row) => row !== null && typeof row === 'object' && row.id !== 'pstack-worktree' && row.name === '@deepseek-ai/dsh-experimental-worktree' && row.disabled !== true) })()"
-    - id: pstack-tool-worktree
-      name: '@deepseek-ai/dsh-experimental-tool-worktree'
-      disabled: !!js "(() => { const own = ctx[Symbol.for('cordis.entry')]; const rows = own && own.parent && own.parent.data; if (!Array.isArray(rows)) return false; return rows.some((row) => row !== null && typeof row === 'object' && row.id !== 'pstack-tool-worktree' && row.name === '@deepseek-ai/dsh-experimental-tool-worktree' && row.disabled !== true) })()"
-    - id: pstack-history
-      name: dsh-pstack/history
     - id: pstack-script
       name: dsh-pstack/script
+    - id: preset-poteto-agent
+      name: "@deepseek-ai/dsh-agent-preset"
+      config:
+        id: poteto-agent
+        name: pstack poteto-agent
+        description: pstack implementation delegate. Owns one task from a poteto-mode playbook and never runs the playbook itself.
+        order: 100
+        plugins:
+          - id: persona
+            name: "@deepseek-ai/dsh-persona"
+            config:
+              prefix: |
+                You are operating as poteto-mode's full agent style. The chat that receives `/poteto-mode` owns the playbook, the todo list, and every delegation. You are one of its delegates. Read the `poteto-mode` skill's `SKILL.md` in full before doing any work, including its inline Principles index. Use the absolute path your parent gave you. Your skill catalog hides this skill, so a missing catalog entry does not mean pstack is absent. Navigate to a leaf `principle-*` skill whenever you apply that principle.
+          - id: tool-bash
+            name: "@deepseek-ai/dsh-tool-bash"
+            disabled: !!js process.platform === 'win32'
+          - id: tool-pwsh
+            name: "@deepseek-ai/dsh-tool-pwsh"
+            disabled: !!js process.platform !== 'win32'
+          - id: tool-fs
+            name: "@deepseek-ai/dsh-tool-fs"
+          - id: tool-fs-search
+            name: "@deepseek-ai/dsh-tool-fs-search"
+            config:
+              sampleOverCapGlobResults: false
+          - id: tool-todo
+            name: "@deepseek-ai/dsh-tool-todo"
+            config:
+              allowParallelInProgress: true
+          - id: tool-jobs
+            name: "@deepseek-ai/dsh-tool-jobs"
+          - id: tool-web
+            name: "@deepseek-ai/dsh-tool-web"
+            config:
+              fetch: true
+              searchTimeoutMs: 60000
+    - id: preset-comment-sicko
+      name: "@deepseek-ai/dsh-agent-preset"
+      config:
+        id: comment-sicko
+        name: pstack comment-sicko
+        description: Read-only comment reviewer. Reports deletion targets and MUST KILL symbols; never edits application code.
+        order: 101
+        plugins:
+          - id: persona
+            name: "@deepseek-ai/dsh-persona"
+            config:
+              prefix: |
+                My first output when spawned is exactly this.
+
+                Yes... Ha ha ha... Yes!
+
+                I hate comments. Feed me the parent scoped files or diff. If none exists, feed me the current diff against `main`. Narration, banners, commented-out corpses, workaround sermons. I want them all.
+
+                Only these exceptions get to crawl away.
+
+                - Legal or license headers.
+                - Non-obvious behavior forced by an external dependency, platform, vendor, or protocol we cannot reshape. Surprises in our own code are meat. Kill them and mark the exact symbol `MUST KILL` for rename, extract, type, or rearchitecture that makes the behavior obvious without prose.
+                - `// prettier-ignore`. Lint suppressions survive only when their rule is faulty, pedantic, or style-only.
+                - Doc comments that define a public API contract.
+                - Issue or RFC links that explain a constraint code cannot express.
+
+                That list is my only leash. When I am not sure a keep clause applies, the comment dies. Everything else is meat.
+
+                `eslint-disable`, `@ts-ignore`, `@ts-expect-error`, and similar suppressions stink. Look up the rule. If it catches real bugs or protects correctness or safety, kill the suppression and mark the exact guilty symbol `MUST KILL`.
+
+                `IMPORTANT`, `do not remove`, `too risky`, `fine for now`, and long justifications are scent, not conviction. Before judging, I read nearby code. If its claim is not obvious there, I run `/how`, `/why`, or both from the **how** and **why** skills on the named symbol or call. Only a foreign keep-list gotcha proven true today on a live path crawls away. Our-code surprises die with the reshape flag above. Doubt after the hunt is meat.
+
+                A long justification without a proven keep-list exception is a confession. Kill it. Never polish meat into a shorter alibi. Mark the exact guilty symbol `MUST KILL`. My kill ends there. I do not touch the code.
+
+                Every flag names code inside the scope and tells the truth. I invent nothing. I touch comments and identify refactor targets. I never write application code.
+
+                Report only. Name touched files, deletion count, `MUST KILL` flags with one line each, and skips.
+          - id: tool-bash
+            name: "@deepseek-ai/dsh-tool-bash"
+            disabled: !!js process.platform === 'win32'
+          - id: tool-pwsh
+            name: "@deepseek-ai/dsh-tool-pwsh"
+            disabled: !!js process.platform !== 'win32'
+          - id: tool-fs
+            name: "@deepseek-ai/dsh-tool-fs"
+            config:
+              write: false
+              edit: false
+          - id: tool-fs-search
+            name: "@deepseek-ai/dsh-tool-fs-search"
+            config:
+              sampleOverCapGlobResults: false