projectstore-claude 0.30.1 → 0.30.2

package/node_modules/projectstore/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "projectstore",
       "displayName": "projectstore",
       "description": "📚 Your agent runs the project through a verified loop: task → artifact (ADR · spec · epic · story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in an Obsidian-friendly vault, every write approved by you — and any model can pick the project up tomorrow.",
-      "version": "0.30.1",
+      "version": "0.30.2",
       "author": {
         "name": "Evgenii Konev",
         "email": "ekonev@smartandpoint.com",

package/node_modules/projectstore/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "projectstore",
   "displayName": "projectstore",
-  "version": "0.30.1",
+  "version": "0.30.2",
   "description": "Your agent runs the project through a verified loop: task → artifact (ADR / spec / epic / story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in git — any model can pick the project up tomorrow.",
   "author": {
     "name": "Evgenii Konev @ SmartAndPoint",

package/node_modules/projectstore/README.md

@@ -208,14 +208,14 @@ Setup asks only what a first install needs. Everything after it is one command,
 npx projectstore configure
 ```
 
-At a terminal it shows every setting with its current value and where it lives:
+At a terminal it opens a settings menu that works like a monitor's: ↑ and ↓ move, → opens a group or a setting in a frame beside it, space chooses, ← goes back, and Enter shows the plan. A second Enter writes it. Under the frames, a few lines say what the row under the cursor means. The settings:
 
-- each agent's model, per harness;
+- each agent's model, per harness. Claude Code offers its aliases: `fable`, `opus`, `sonnet` and `haiku`. Codex offers its own list of models, with its descriptions. With `ANTHROPIC_API_KEY` set, each alias also names the newest model of its line. A list is kept for a day in projectstore's user cache, and "refresh the list" asks again;
 - the status line and the band above the prompt (Claude Code);
 - the vault's template language, the default author and tags;
 - the vault's spec policy and lifecycle gates.
 
-It asks which to change, then shows one plan and asks once. Without a terminal it prints the same view and writes nothing. To change a setting there, name it with `--set`; naming it is the confirmation:
+Without a terminal it prints every setting with its current value and where it lives, and writes nothing. To change a setting there, name it with `--set`; naming it is the confirmation:
 
 ```
 npx projectstore configure --set agents.critic=fable --set statusline=on

package/node_modules/projectstore/docs/getting-started.md

@@ -97,7 +97,7 @@ After setup, every setting is one command away, from a terminal in your project:
 npx projectstore configure
 ```
 
-It shows each agent's model, the status line and the band, the template language, and the vault's spec policy and lifecycle gates — with their values and the file each one lives in. Then it asks which to change, shows one plan and asks once. From a script or an agent, name the change; naming it is the confirmation:
+At a terminal it opens a settings menu: each agent's model, the status line and the band, the template language, and the vault's spec policy and lifecycle gates. ↑ and ↓ move, → opens, space chooses, ← goes back, and Enter shows one plan; a second Enter writes it. A model is chosen from its harness's list: Claude Code's aliases, or Codex's own models. Without a terminal it prints the settings with their values and the file each one lives in. From a script or an agent, name the change; naming it is the confirmation:
 
 ```
 npx projectstore configure --set language=de --set lifecycle_gates=on

package/node_modules/projectstore/harnesses/claude-code.json

@@ -533,6 +533,57 @@
     "carries_model": true,
     "cheap_model": "sonnet",
     "cheap_model_evidence": "measured",
-    "cheap_model_reason": "The model the clerk is pinned to when a strong default would otherwise lift it (ADR-008). A literal here, in the one file allowed to name a harness's vocabulary; it used to be a literal in scripts/cli.mjs, which made `agents configure --harness codex` write an Anthropic model name into a Codex overlay. MEASURED in the sense that matters: this is the model the clerk has been running on since ADR-008, in this repository, and tests/overlay.test.mjs asserts the pin end to end."
+    "cheap_model_reason": "The model the clerk is pinned to when a strong default would otherwise lift it (ADR-008). A literal here, in the one file allowed to name a harness's vocabulary; it used to be a literal in scripts/cli.mjs, which made `agents configure --harness codex` write an Anthropic model name into a Codex overlay. MEASURED in the sense that matters: this is the model the clerk has been running on since ADR-008, in this repository, and tests/overlay.test.mjs asserts the pin end to end.",
+    "models": {
+      "spawn_takes": "alias",
+      "spawn_takes_evidence": "measured",
+      "spawn_takes_reason": "The Agent tool's `model` parameter is an enum, [\"sonnet\", \"opus\", \"haiku\", \"fable\"], in the tool schema Claude Code 2.1.296 gave a session on 2026-10-13. The registration block tells the session to pass the overlay's model as that parameter, so an overlay value outside the enum fails at every spawn of that agent. Only an agent definition's frontmatter takes a full model name, and ADR-008 retired the copies that carried one. So the list offers the aliases, never an exact id (the ADR \"Agent model lists are read from each harness's own catalog, declared in its manifest and cached for a day\", decision 1).",
+      "static": [
+        {
+          "id": "fable",
+          "family": "fable",
+          "description": "Follows the newest Fable model: Claude Code resolves the alias when it starts the agent."
+        },
+        {
+          "id": "opus",
+          "family": "opus",
+          "description": "Follows the newest Opus model: Claude Code resolves the alias when it starts the agent."
+        },
+        {
+          "id": "sonnet",
+          "family": "sonnet",
+          "description": "Follows the newest Sonnet model: Claude Code resolves the alias when it starts the agent."
+        },
+        {
+          "id": "haiku",
+          "family": "haiku",
+          "description": "Follows the newest Haiku model: Claude Code resolves the alias when it starts the agent."
+        }
+      ],
+      "static_reason": "The enum above, in the order the menu lists it. A line the catalog below reports that this list lacks is never offered: a Claude Code release that adds an alias is named with `--set`, with the warning, until this list learns it.",
+      "catalogs": [
+        {
+          "kind": "http",
+          "source": "the Anthropic API",
+          "caption": "Anthropic API",
+          "url": "https://api.anthropic.com/v1/models?limit=1000",
+          "base_env": "ANTHROPIC_BASE_URL",
+          "path": "/v1/models?limit=1000",
+          "key_env": "ANTHROPIC_API_KEY",
+          "key_header": "x-api-key",
+          "headers": { "anthropic-version": "2023-06-01" },
+          "fields": {
+            "list": "data",
+            "id": "id",
+            "label": "display_name",
+            "family": "line",
+            "order": "created_at",
+            "order_desc": true,
+            "keep_when": { "lifecycle": "active" }
+          },
+          "reason": "Measured 2026-10-13: 14 models in 0.5–0.7 s, each with id, display_name, created_at, line (fable, opus, sonnet, haiku) and lifecycle. `line` is the family an alias follows, so the newest active entry of a line is the best local account of what that alias starts; Claude Code resolves the alias itself. Read only when a model list opens with a stale cache, or on refresh, and only with ANTHROPIC_API_KEY set; ANTHROPIC_BASE_URL, when set, is the base the key belongs to."
+        }
+      ]
+    }
   }
 }

package/node_modules/projectstore/harnesses/codex.json

@@ -357,6 +357,37 @@
     "effort_key": "model_reasoning_effort",
     "effort_evidence": "documented",
     "effort_precedence": "explicit spawn value, then the [agents] default from config, then the parent agent's value. A model chosen without an effort uses that model's default effort.",
-    "effort_reason": "Recorded, not yet consumed: the overlay's allowlist rejects an effort key and rewrites it out, deliberately, until the story Per-agent effort returns decides whether a role's effort travels in a rendered definition or at spawn. Documented 2026-09-08; the `ultra` level is Codex's and is not a level Claude Code accepts."
+    "effort_reason": "Recorded, not yet consumed: the overlay's allowlist rejects an effort key and rewrites it out, deliberately, until the story Per-agent effort returns decides whether a role's effort travels in a rendered definition or at spawn. Documented 2026-09-08; the `ultra` level is Codex's and is not a level Claude Code accepts.",
+    "models": {
+      "spawn_takes": "id",
+      "spawn_takes_evidence": "documented",
+      "spawn_takes_reason": "A Codex agent's model is passed at spawn by its slug: Codex's subagents documentation (learn.chatgpt.com/docs/agent-configuration/subagents, read 2026-10-13) says explicit spawn values override agents.default_subagent_model, and a wrong slug fails at spawn time, on the harness (cheap_model_reason above). So the list is Codex's own catalog, the slugs it shows in its picker.",
+      "static": [],
+      "fields": {
+        "list": "models",
+        "id": "slug",
+        "label": "display_name",
+        "description": "description",
+        "order": "priority",
+        "shown_when": { "visibility": "list" }
+      },
+      "catalogs": [
+        {
+          "kind": "file",
+          "source": "Codex",
+          "caption": "Codex",
+          "path": "models_cache.json",
+          "fields": { "at": "fetched_at" },
+          "reason": "Codex's own catalog under its home ($CODEX_HOME, else ~/.codex), which Codex refreshes itself. Measured 2026-10-13 on codex-cli 0.162.1: fetched_at, client_version and models[] with slug, display_name, description, visibility (list or hide), priority and upgrade."
+        },
+        {
+          "kind": "command",
+          "source": "Codex",
+          "caption": "Codex",
+          "argv": ["codex", "debug", "models"],
+          "reason": "Prints the same catalog as JSON after Codex refreshes it with its own login: 88–103 ms on codex-cli 0.162.1, measured 2026-10-13. A debug subcommand: if a release drops it, the file above keeps the list, and this argv is where it changes (app-server's model/list is the experimental alternative)."
+        }
+      ]
+    }
   }
 }

package/node_modules/projectstore/package.json

@@ -1,6 +1,6 @@
 {
   "name": "projectstore",
-  "version": "0.30.1",
+  "version": "0.30.2",
   "description": "Your agent runs the project through a verified loop: task → artifact (ADR / spec / epic / story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in git — any model can pick the project up tomorrow.",
   "keywords": [
     "project-management",