paqad-ai 1.35.0 → 1.37.0

package/CHANGELOG.md

@@ -1,5 +1,49 @@
 # paqad-ai
 
+## 1.37.0
+
+### Minor Changes
+
+- 0d8b0db: Extend the enforcement record tier from Claude-only to Codex and Gemini, and document the honest cross-provider tier ladder (issue #265).
+
+  The stage writer and pre-edit block are Claude-only by physics (only Claude Code exposes a pre-mutation hook). But the _ledger_ half of the fix is portable to any host with a completion hook, so it now binds on Codex and Gemini too:
+
+  - **Codex / Gemini record their `paqad:stage` markers at turn end.** The record-only completion hook (`verification-record.mjs`, wired on Codex `Stop` and Gemini `AfterAgent`) now parses the agent's stage markers from the turn transcript and writes them to the same stage-evidence ledger the completion verify folds. Each row is attributed to the host that ran (`codex-cli` / `gemini-cli`), passed to the hook as an argv — never mislabelled `claude-code`. Codex reads its `transcript_path`; Gemini falls back to the inline `prompt_response` because its `transcript_path` is currently stubbed empty upstream ([google-gemini/gemini-cli#14715](https://github.com/google-gemini/gemini-cli/issues/14715)). The parser degrades gracefully to a raw-text scan when a transcript format is not the Claude JSONL shape.
+  - **Record-only, by design.** These hooks still always exit 0 and stay silent — there is **no in-chat verdict** on Codex/Gemini, because Codex rejects plain text on `Stop` and Gemini forces a retry on `decision: deny`, so the only non-disruptive channel is the ledger. The verdict is visible via the dashboard / SIEM export, never shoved into the chat.
+  - **No pre-edit block, stated plainly.** Codex/Gemini have no pre-mutation seam, so the hard block stays Claude-only. `docs/verification-enforcement.md` now carries a cross-provider guarantee table (hard block + verdict = Claude; record + ledger = Codex/Gemini; advisory = the 8 remaining hosts) and tracks the non-Claude hard block as a known, physics-bounded, upstream-blocked limitation.
+  - **The mandate holds:** enforcement is never added through an entry-file, prompt, or template edit. A parity test asserts the stage-writer and pre-mutation deny hooks are present for `claude-code` and absent for `codex-cli` / `gemini-cli` and every advisory host.
+
+## 1.36.0
+
+### Minor Changes
+
+- 69ab154: Add a native `aiassistant` adapter for JetBrains AI Assistant (#219).
+
+  - Onboarding and `paqad-ai refresh --providers` now generate and keep in sync `.aiassistant/rules/guidelines.md`, the lean bootstrap-pointer entry file AI Assistant auto-applies from `.aiassistant/rules/`.
+  - Soft, rules-only adapter (advisory hook coverage), like `junie`: AI Assistant exposes no hook/lifecycle system, so the sentinel gate cannot bind. MCP is intentionally omitted — AI Assistant configures MCP servers in the IDE, not a project file, so no dead artifact is written.
+  - The adapter is selectable everywhere the other ten are (onboarding prompt, `--providers`, factory), carries its Decision Pause Contract UI note, and is covered by tests parallel to `junie`.
+  - Also synced the `onboarding-manifest` schema `adapter` enum to the full adapter list (it had silently drifted to five, so a `cursor`/`aider`-onboarded manifest failed health-check validation).
+
+- 69ab154: Make the feature-development stage workflow **compel, not plead** (enforcement RCA, part 1 of the fix).
+
+  The stage-evidence recorder finally has a production caller, and a code edit is now blocked until the prior stages are recorded — closing the physics gaps that let every prior fix (#117–#261) regress.
+
+  - **Deterministic per-stage writer.** A new Claude PreToolUse hook (`stage-writer.mjs` → `src/stage-evidence/live-writer.ts`) script-mints a `live-mark` stage row on every Edit/Write/NotebookEdit, with real start/end times classified from the mutated file — no model involvement. The completion finalizer closes any stage left open at the turn boundary.
+  - **Block-forward deny.** A `stages` capability folded into the kernel evaluates at the pre-mutation seam and refuses an edit (exit 2, reason on stderr) until `planning` and `specification` each carry a recorded start+end pair. It reads the ledger, not a git delta, so a committed clean tree cannot bypass it. `se-mark` (a Bash script, ungated) is the escape hatch that clears the block.
+  - **Visible, non-vacuous verdict.** The Stop backstop now writes a failing verdict to **stderr** (the host surfaces only stderr to the model on exit 2), and the stage gate no longer skips on a zero-file working-tree diff — a committed-but-incomplete change still fails instead of passing silently.
+
+  Claude-only for the hard block (the only host with a pre-mutation seam); Codex/Gemini keep completion-time recording; other adapters are unchanged. Default `stages_mode` is strict.
+
+- 69ab154: Wire the last three enforcement consumers so the framework is felt, not just recorded (enforcement RCA, part 2 of the fix).
+
+  Building on the stage writer and block-forward deny, three contracts that shipped with a policy but no live consumer now bind through the kernel:
+
+  - **Delivery policy is enforced.** A `delivery` capability at the completion (Stop) seam reads HEAD branch/commit and — when `gh` can answer — the PR/CI state, then **warns** on a convention deviation (on the base branch, an off-convention branch name, red CI under `wait_for_green`) and appends a `delivery-evidence` row. Warn-floor by design: delivery is `mandatory:false`, so it surfaces a bad push one turn late but never blocks. Degrades cleanly when `gh` is absent.
+  - **The stage is printed on entry.** The stage-writer PreToolUse hook now prints a plain-English `▸ paqad · <stage>` line (via Claude's user-visible `systemMessage` channel) the first time a change enters each stage, so the developer sees the workflow running even when the model forgets to say it. Claude-only (the sole pre-mutation host); idempotent per change.
+  - **The Decision Pause Contract self-arms.** An opt-in pre-mutation capability reads the recent prompt from the turn transcript and, on a high-confidence create-vs-reuse fork with no decision pending or already made, mints ONE pending decision packet so the existing decision-pause gate blocks the _next_ edit — closing the "nothing mints the packet" gap. **Off by default** (enable with `PAQAD_DECISION_SELFARM` or a local `.config` `decision_selfarm` line); it only mints, never blocks, so the current edit is never interrupted.
+
+  The kernel gate now threads an optional tool/turn payload (edit target, transcript path, session id) to each capability; every existing capability ignores it. Coverage stays at the 95% branch gate.
+
 ## 1.35.0
 
 ### Minor Changes

package/README.md

@@ -20,7 +20,7 @@
 [![Node](https://img.shields.io/node/v/paqad-ai.svg?style=flat-square)](https://nodejs.org)
 [![website](https://img.shields.io/badge/website-paqad.ai-0A7A5C?style=flat-square)](https://paqad.ai)
 
-Works with Claude Code, Cursor, GitHub Copilot, Gemini, Codex, Windsurf, Junie, Continue, Antigravity, and Aider.
+Works with Claude Code, Cursor, GitHub Copilot, Gemini, Codex, Windsurf, Junie, Continue, Antigravity, Aider, and JetBrains AI Assistant.
 
 </div>
 
@@ -140,18 +140,19 @@ Three steps turn AI coding from a prompt you hope works into a pipeline you can
 
 Run `paqad-ai onboard` one time. It writes a thin, native config file for each tool you use, and they all point at the same shared instruction bundle. Change a rule in one place, and every agent sees it. Switch tools next month without losing anything.
 
-| Tool                   | What it creates                                          |
-| ---------------------- | -------------------------------------------------------- |
-| **Claude Code**        | `CLAUDE.md` and MCP config                               |
-| **Codex CLI**          | `AGENTS.md` and MCP config                               |
-| **Google Antigravity** | `ANTIGRAVITY.md` and MCP config                          |
-| **Gemini CLI**         | `GEMINI.md` and MCP config                               |
-| **Junie**              | `.junie/AGENTS.md` and `.junie/mcp/mcp.json`             |
-| **Cursor**             | `.cursor/rules/paqad.mdc` plus MCP, skills, agents       |
-| **GitHub Copilot**     | `.github/copilot-instructions.md` and `.vscode/mcp.json` |
-| **Windsurf**           | `.windsurfrules` plus MCP, skills, agents                |
-| **Continue**           | `.continue/rules/paqad.md` plus MCP, prompts             |
-| **Aider**              | `CONVENTIONS.md`                                         |
+| Tool                       | What it creates                                          |
+| -------------------------- | -------------------------------------------------------- |
+| **Claude Code**            | `CLAUDE.md` and MCP config                               |
+| **Codex CLI**              | `AGENTS.md` and MCP config                               |
+| **Google Antigravity**     | `ANTIGRAVITY.md` and MCP config                          |
+| **Gemini CLI**             | `GEMINI.md` and MCP config                               |
+| **Junie**                  | `.junie/AGENTS.md` and `.junie/mcp/mcp.json`             |
+| **Cursor**                 | `.cursor/rules/paqad.mdc` plus MCP, skills, agents       |
+| **GitHub Copilot**         | `.github/copilot-instructions.md` and `.vscode/mcp.json` |
+| **Windsurf**               | `.windsurfrules` plus MCP, skills, agents                |
+| **Continue**               | `.continue/rules/paqad.md` plus MCP, prompts             |
+| **Aider**                  | `CONVENTIONS.md`                                         |
+| **JetBrains AI Assistant** | `.aiassistant/rules/guidelines.md`                       |
 
 Pick one or pick all. Onboarding is multi-select.
 

package/dist/cli/index.js

@@ -2992,7 +2992,19 @@ var init_onboarding_manifest_schema = __esm({
         framework_version: { type: "string" },
         adapter: {
           type: "string",
-          enum: ["claude-code", "codex-cli", "antigravity", "gemini-cli", "junie"]
+          enum: [
+            "claude-code",
+            "codex-cli",
+            "antigravity",
+            "gemini-cli",
+            "junie",
+            "cursor",
+            "github-copilot",
+            "windsurf",
+            "continue",
+            "aider",
+            "aiassistant"
+          ]
         },
         project_root: { type: "string" },
         profile: { $ref: "project-profile" },
@@ -9742,10 +9754,21 @@ function hookCommand(hookFile, env = process.env) {
 function capabilityGateCommand(seam, env = process.env) {
   return `${hookCommand("capability-gate.mjs", env)} ${seam}`;
 }
-function completionRecordCommand(env = process.env) {
-  return hookCommand("verification-record.mjs", env);
+function completionRecordCommand(adapterType, env = process.env) {
+  const base = hookCommand("verification-record.mjs", env);
+  return adapterType ? `${base} ${adapterType}` : base;
 }
 var PAQAD_LIVE_HOOKS = [
+  {
+    id: "stage-writer",
+    event: "pre-tool-mutation",
+    hookFile: "stage-writer.mjs",
+    mutatingToolMatcher: PAQAD_MUTATING_TOOL_MATCHER,
+    // A non-blocking WRITER, not a gate. Ordered first so a live-mark stage row
+    // exists on disk before the decision-pause / capability gates read the change
+    // (RCA fix A — gives the stage-evidence recorder its production caller).
+    description: "Script-mint per-stage live-mark rows on every mutating edit (RCA fix A)."
+  },
   {
     id: "decision-pause-gate",
     event: "pre-tool-mutation",
@@ -9753,6 +9776,15 @@ var PAQAD_LIVE_HOOKS = [
     mutatingToolMatcher: PAQAD_MUTATING_TOOL_MATCHER,
     description: "Block mutating tools while a decision packet is unresolved (#117 C-3)."
   },
+  {
+    id: "stage-marker-parse",
+    event: "completion",
+    hookFile: "stage-marker-parse.mjs",
+    // Ordered before verification-completion so the non-mutation stage markers
+    // (planning/specification/review) are in the ledger when the completion
+    // backstop folds the change (RCA fix, Step 3). Non-blocking, best-effort.
+    description: "Record the agent\u2019s paqad:stage markers from the transcript on completion."
+  },
   {
     id: "verification-completion",
     event: "completion",
@@ -9761,7 +9793,7 @@ var PAQAD_LIVE_HOOKS = [
   }
 ];
 
-// src/adapters/aider/aider-adapter.ts
+// src/adapters/aiassistant/aiassistant-adapter.ts
 init_esm_shims();
 
 // src/adapters/shared/base-adapter.ts
@@ -10288,7 +10320,9 @@ var ADAPTER_OUTPUT_PATHS = {
   "github-copilot": ".vscode/mcp.json",
   windsurf: ".windsurf/mcp.json",
   continue: ".continue/mcp.json",
-  aider: "aider.mcp.json"
+  aider: "aider.mcp.json",
+  // unreachable; capabilities.mcp = false
+  aiassistant: ".aiassistant/mcp.json"
   // unreachable; capabilities.mcp = false
 };
 var McpConfigManager = class {
@@ -10543,7 +10577,45 @@ function getSkillBundleRelativePath(skill) {
   return segments.slice(skillsIndex + 1).join("/");
 }
 
+// src/adapters/aiassistant/aiassistant-adapter.ts
+var AiAssistantAdapter = class extends BaseAdapter {
+  type = "aiassistant";
+  capabilities = {
+    skills: false,
+    agents: false,
+    hooks: false,
+    mcp: false,
+    caching: false,
+    memory: false
+  };
+  configTemplateName() {
+    return "aiassistant.md.hbs";
+  }
+  configOutputPath() {
+    return ".aiassistant/rules/guidelines.md";
+  }
+  skillsRoot() {
+    return ".aiassistant/skills";
+  }
+  agentsRoot() {
+    return ".aiassistant/agents";
+  }
+  hooksOutputPath() {
+    return ".aiassistant/hooks.json";
+  }
+  mcpOutputPath() {
+    return ".aiassistant/mcp.json";
+  }
+  cacheOutputPath() {
+    return ".aiassistant/cache.json";
+  }
+  memoryOutputPath() {
+    return ".aiassistant/memory.json";
+  }
+};
+
 // src/adapters/aider/aider-adapter.ts
+init_esm_shims();
 var AiderAdapter = class extends BaseAdapter {
   type = "aider";
   capabilities = {
@@ -10769,22 +10841,20 @@ init_esm_shims();
 init_esm_shims();
 import { readFileSync as readFileSync6 } from "fs";
 import { join as join10 } from "pathe";
-var LEGACY_COMPLETION_COMMANDS = /* @__PURE__ */ new Set([
-  `${PAQAD_RUNTIME_PREFIX}/hooks/verification-record.mjs`
-]);
+var RECORD_HOOK_BASENAME = "verification-record.mjs";
+function isRecordHookCommand(command) {
+  return command.includes(RECORD_HOOK_BASENAME);
+}
 function buildNativeCompletionHookFile(options) {
-  const { projectRoot, settingsPath, completionEvent } = options;
-  const command = completionRecordCommand();
+  const { projectRoot, settingsPath, completionEvent, adapterType } = options;
+  const command = completionRecordCommand(adapterType);
   const existing = readJsonObject(join10(projectRoot, settingsPath));
   const hooks = existing.hooks && typeof existing.hooks === "object" && !Array.isArray(existing.hooks) ? existing.hooks : {};
   const eventGroups = (Array.isArray(hooks[completionEvent]) ? hooks[completionEvent] : []).map((group) => ({
     ...group,
-    hooks: (group?.hooks ?? []).filter((hook) => !LEGACY_COMPLETION_COMMANDS.has(hook.command))
+    hooks: (group?.hooks ?? []).filter((hook) => !isRecordHookCommand(hook.command))
   })).filter((group) => group.hooks.length > 0);
-  const alreadyPresent = eventGroups.some(
-    (group) => group?.hooks?.some((hook) => hook.command === command)
-  );
-  const nextGroups = alreadyPresent ? eventGroups : [...eventGroups, { hooks: [{ type: "command", command }] }];
+  const nextGroups = [...eventGroups, { hooks: [{ type: "command", command }] }];
   const next = {
     ...existing,
     hooks: { ...hooks, [completionEvent]: nextGroups }
@@ -10858,7 +10928,8 @@ var CodexCliAdapter = class extends BaseAdapter {
       buildNativeCompletionHookFile({
         projectRoot: context.projectRoot,
         settingsPath: CODEX_HOOKS_FILE,
-        completionEvent: CODEX_COMPLETION_EVENT
+        completionEvent: CODEX_COMPLETION_EVENT,
+        adapterType: this.type
       })
     ];
   }
@@ -10989,7 +11060,8 @@ var GeminiCliAdapter = class extends BaseAdapter {
       buildNativeCompletionHookFile({
         projectRoot: context.projectRoot,
         settingsPath: GEMINI_SETTINGS_FILE,
-        completionEvent: GEMINI_COMPLETION_EVENT
+        completionEvent: GEMINI_COMPLETION_EVENT,
+        adapterType: this.type
       })
     ];
   }
@@ -11136,6 +11208,8 @@ var AdapterFactory = class {
         return new ContinueAdapter();
       case "aider":
         return new AiderAdapter();
+      case "aiassistant":
+        return new AiAssistantAdapter();
       default:
         return assertUnreachableAdapter(type);
     }
@@ -13560,7 +13634,8 @@ var ADAPTER_TYPES = [
   "github-copilot",
   "windsurf",
   "continue",
-  "aider"
+  "aider",
+  "aiassistant"
 ];
 
 // src/core/types/agent.ts
@@ -22514,6 +22589,11 @@ async function promptProviders(defaultProviders) {
         name: "Aider (paul-gauthier)",
         value: "aider",
         checked: defaultProviders?.includes("aider") ?? false
+      },
+      {
+        name: "AI Assistant (JetBrains)",
+        value: "aiassistant",
+        checked: defaultProviders?.includes("aiassistant") ?? false
       }
     ],
     validate(choices) {
@@ -25561,7 +25641,7 @@ init_cancelled_error();
 init_events();
 
 // src/index.ts
-var VERSION = "1.35.0";
+var VERSION = "1.37.0";
 
 // src/cli/commands/audit.ts
 init_esm_shims();
@@ -33187,7 +33267,7 @@ function printNextSteps() {
 function createOnboardCommand() {
   return new Command15("onboard").description("Full project onboarding").option("--project-root <path>", "Project root", process.cwd()).option("--stack <stack>", "Force the target stack").option("--capability <capability...>", "Add one or more capabilities").option(
     "--providers <provider...>",
-    "Select one or more providers (codex-cli, antigravity, claude-code, gemini-cli, junie, cursor, github-copilot, windsurf, continue, aider)"
+    "Select one or more providers (codex-cli, antigravity, claude-code, gemini-cli, junie, cursor, github-copilot, windsurf, continue, aider, aiassistant)"
   ).action(
     async (options) => {
       printBanner();