fix: use Pi user auth and handle startup failures

2026-07-21 14:01:47 +02:00
parent 2ff63d371f
commit 801f847ec4
12 changed files with 311 additions and 6 deletions
@@ -12,6 +12,7 @@ MAX_PI_PROCESSES=4
 PI_PROVIDER=
 PI_MODEL=
 PI_THINKING=
+PI_AUTH_FILE=${HOME}/.pi/agent/auth.json

 # Set these for the selected DWH/vector/embedding adapters.
 THT_DB_NAME=
@@ -1,8 +1,30 @@
 # ThothII — Project State

-> Starting-point snapshot for new sessions. Last updated: 2026-07-15 (central live log and compact CTE density live).
+> Starting-point snapshot for new sessions. Last updated: 2026-07-21 (local Pi user-auth wiring and startup error handling live).
 > Point a fresh session here ("read PROJECT_STATE.md") before substantial work.

+## Local Pi user auth + startup failure handling — LIVE 2026-07-21
+
+- The PSD Docker profile now bind-mounts the configurable host `PI_AUTH_FILE` read-only at
+  `/home/thoth/.pi/agent/auth.json`; on this Mac it resolves to the real user profile
+  `/Users/mp/.pi/agent/auth.json`. The container keeps its correct Linux identity
+  `HOME=/home/thoth` while Pi sees the user's independent `deepseek` and `zai` credentials.
+- `deploy/pi/settings.json` is the non-secret model policy and exposes, in order,
+  `zai/glm-5.2`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-pro`, and
+  `aritmolab/qwen3.6-35b-a3b`. The core image is aligned to Pi 0.80.3.
+- New-session creation now validates the saved provider/model against Pi before persistence;
+  unavailable selections return sanitized `503 model_unavailable` without creating a manifest.
+  A synchronous runtime-construction failure after persistence marks that session `failed` and
+  returns the fixed startup-recovery message instead of leaving an ambiguous `open` session.
+- Verification: backend 235/235, TypeScript clean, dedicated Compose auth/model contract green
+  with a demonstrated RED→GREEN cycle. Rebuilt core image
+  `sha256:a8b4dd9f016c2335e4da897073bc6d5bdf1e8ce9b60dcfcca171b6677f563228`
+  is healthy; live `/models` returned all four models; a real `deepseek-v4-pro` smoke reached its
+  first reviewer gate, deleted only its own session, and restored the exact prior settings.
+- Deleted the three explicitly approved incomplete DeepSeek attempts:
+  `a390c8b8-0a91-4a37-967b-ce7ff9be9797`, `a2f974b2-4c48-4967-b4b6-afdbc2b2d541`, and
+  `f66e1959-3c71-4b10-8aa1-606992046b7e` (API delete 204, subsequent lookup 404 for each).
+
 ## User-owned sessions cutover — prepared, manual gate pending (2026-07-16)

 - **Target contract:** the public server runs `AUTH_MODE=upstream` with Task 4 portal identity
@@ -95,7 +95,8 @@ export function buildApp(config: AppConfig, deps?: BuildAppDeps): FastifyInstanc
  app.get("/health/dwh", async () => tht.dbPing());
  app.get("/me", async (req) => getPrincipal(req));
  sessionRoutes(app, {
-    mgr, tht: tht as ThtRunner, hub, getSettings, readiness, dwhPrecheck: config.dwhPrecheck,
+    mgr, tht: tht as ThtRunner, hub, getSettings, readiness, listModels,
+    dwhPrecheck: config.dwhPrecheck,
  });
  sqlRoutes(app, { tht: tht as ThtRunner, getSettings });
  metaRoutes(app, { harnessDir: config.harnessDir, listModels });
@@ -6,6 +6,7 @@ import type { Settings } from "../settings/settings-store.js";
 import { getPrincipal } from "../auth/auth.js";
 import type { PrincipalContext } from "../auth/principal.js";
 import type { ReadinessManager } from "../runtime/readiness-manager.js";
+import type { ListModelsFn } from "./meta.js";

 const BOOTSTRAP_FAILURE_MESSAGE =
  "Session startup failed. Check configuration and connectivity, then Resume the session.";
@@ -15,6 +16,8 @@ const RESUME_FAILURE_MESSAGE =
  "Session could not be resumed. Check configuration and connectivity, then try again.";
 const DWH_UNREACHABLE_MESSAGE =
  "Cannot start a session: the database is unreachable. Check the VPN connection and try again.";
+const MODEL_UNAVAILABLE_MESSAGE =
+  "Selected model is unavailable. Check Pi authentication and model settings, then try again.";

 export function sessionRoutes(
  app: FastifyInstance,
@@ -22,6 +25,7 @@ export function sessionRoutes(
    mgr: PiProcessManager; tht: ThtRunner; hub: SseHub;
    getSettings: (principal: PrincipalContext) => Promise<Settings>;
    readiness: ReadinessManager;
+    listModels: ListModelsFn;
    /** Local-only guard: probe DWH reachability before creating a session (run-stack.sh). */
    dwhPrecheck?: boolean;
  },
@@ -189,6 +193,26 @@ export function sessionRoutes(
        return reply.code(503).send({ error: DWH_UNREACHABLE_MESSAGE, code: "dwh_unreachable" });
      }
    }
+    if (s.provider && s.model) {
+      let available: Awaited<ReturnType<ListModelsFn>>;
+      try {
+        available = await d.listModels();
+      } catch {
+        return reply.code(503).send({
+          error: MODEL_UNAVAILABLE_MESSAGE,
+          code: "model_unavailable",
+        });
+      }
+      const selectedAvailable = available.some(
+        (candidate) => candidate.provider === s.provider && candidate.id === s.model,
+      );
+      if (!selectedAvailable) {
+        return reply.code(503).send({
+          error: MODEL_UNAVAILABLE_MESSAGE,
+          code: "model_unavailable",
+        });
+      }
+    }
    // Settings (global) supply workspace/provider/model/thinking. The new-question
    // form sends only the question text. `workspace` selects the tht `-c <config>`.
    let id: string;
@@ -206,8 +230,21 @@ export function sessionRoutes(
      principal,
      question: b.question,
    };
-    const rt = d.mgr.createFor(id, options);
-    bindRuntime(id, rt, runner, s.workspace);
+    let rt: ReturnType<PiProcessManager["createFor"]> | undefined;
+    try {
+      rt = d.mgr.createFor(id, options);
+      bindRuntime(id, rt, runner, s.workspace);
+    } catch (error) {
+      if (rt) d.mgr.teardownIfCurrent(id, rt);
+      console.error(
+        `[pi:${id}] runtime construction failed:`,
+        error instanceof Error ? error.message : "unknown error",
+      );
+      await runner.failSession(id, s.workspace).catch((persistenceError: unknown) => {
+        console.error(`[session:${id}] failSession persistence failed:`, persistenceError);
+      });
+      return reply.code(503).send({ error: BOOTSTRAP_FAILURE_MESSAGE });
+    }
    info(id, "Session created");
    bootstrap(
      id, rt, runner, s.workspace, d.mgr.configure(rt, options),
@@ -164,6 +164,9 @@ test("POST /sessions usa i settings (workspace/provider/model/thinking) e crea+a
      sessionList: async () => [{ id: "s1" }],
    } as any,
    getSettings: () => ({ workspace: "w", provider: "zai", model: "glm-5.2", thinking: "high" }),
+    listModels: async () => [
+      { provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
+    ],
    spawnFn: () => nodeSpawn("node", [FAKE, SCRIPT]) as any,
  });
  const created = await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
@@ -259,6 +262,9 @@ test("POST /sessions configura Pi con il thinking globale selezionato", async ()
      sessionNew: async () => ({ id: "s-thinking" }),
    } as any,
    getSettings: () => ({ workspace: "psd", provider: "zai", model: "glm-5.2", thinking: "high" }) as any,
+    listModels: async () => [
+      { provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
+    ],
  });

  await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
@@ -1539,6 +1545,69 @@ test("POST /sessions proceeds when ollamaEnsure succeeds", async () => {
  expect(ensureWs).toBe("psd");
 });

+test("POST /sessions rejects an unavailable saved model before persisting a session", async () => {
+  let created = 0;
+  const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
+    thtRunner: {
+      sessionNew: async () => { created += 1; return { id: "must-not-exist" }; },
+    } as any,
+    readiness: { ensure: async () => ({ ok: true }) } as any,
+    getSettings: () => ({
+      workspace: "psd",
+      provider: "deepseek",
+      model: "deepseek-v4-pro",
+      thinking: "medium",
+    }) as any,
+    listModels: async () => [
+      { provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
+    ],
+  });
+
+  const res = await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
+
+  expect(res.statusCode).toBe(503);
+  expect(res.json()).toEqual({
+    error: "Selected model is unavailable. Check Pi authentication and model settings, then try again.",
+    code: "model_unavailable",
+  });
+  expect(created).toBe(0);
+});
+
+test("POST /sessions marks a persisted session failed when runtime construction throws", async () => {
+  let failed = 0;
+  const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
+    mgr: {
+      createFor: () => { throw new Error("provider bootstrap unavailable"); },
+    } as any,
+    thtRunner: {
+      sessionNew: async () => ({ id: "s-runtime-failure" }),
+      failSession: async (id: string, workspace: string) => {
+        expect(id).toBe("s-runtime-failure");
+        expect(workspace).toBe("psd");
+        failed += 1;
+      },
+    } as any,
+    readiness: { ensure: async () => ({ ok: true }) } as any,
+    getSettings: () => ({
+      workspace: "psd",
+      provider: "deepseek",
+      model: "deepseek-v4-pro",
+      thinking: "medium",
+    }) as any,
+    listModels: async () => [
+      { provider: "deepseek", id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", reasoning: true },
+    ],
+  });
+
+  const res = await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
+
+  expect(res.statusCode).toBe(503);
+  expect(res.json()).toEqual({
+    error: "Session startup failed. Check configuration and connectivity, then Resume the session.",
+  });
+  expect(failed).toBe(1);
+});
+
 test("POST /sessions/:id/resume returns 409 for a read-only session without calling ollamaEnsure", async () => {
  let ensureCalled = false;
  const app = mutApp({
@@ -33,6 +33,7 @@ services:
    volumes:
      - /home/chirone/thothii-data:/data
      - /home/chirone/thothii-data/pi-config:/home/thoth/.pi
+      - ${PI_AUTH_FILE:?set PI_AUTH_FILE}:/home/thoth/.pi/agent/auth.json:ro
      - /home/chirone/chirone/etl/docs/evidence:/data/evidence:ro
    restart: unless-stopped
    networks:
@@ -1,3 +1,9 @@
 {
-  "defaultProjectTrust": "always"
+  "defaultProjectTrust": "always",
+  "enabledModels": [
+    "zai/glm-5.2",
+    "deepseek/deepseek-v4-flash",
+    "deepseek/deepseek-v4-pro",
+    "aritmolab/qwen3.6-35b-a3b"
+  ]
 }
@@ -1,7 +1,7 @@
 # syntax=docker/dockerfile:1.7
 # thothii-core: Fastify (Node 22) + harness Python 3.12 (tht CLI) + runtime Pi.
 # Singolo container, entrypoint logico "server" (default).
-ARG PI_VERSION=0.80.2
+ARG PI_VERSION=0.80.3

 # ---- Stage 1: backend TypeScript -> dist ----
 FROM node:22-bookworm AS backend-build
@@ -0,0 +1,87 @@
+# Pi User Authentication and Startup Error Handling Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Make Dockerized Pi consume the configured user auth store, expose four approved models, fail session startup cleanly, and remove three incomplete attempts.
+
+**Architecture:** Compose mounts only the host Pi `auth.json` into the container while repository-owned Pi settings define the model policy. The backend validates the persisted model before creating a session and converts post-persistence runtime-construction errors into a failed session plus a sanitized 503.
+
+**Tech Stack:** Docker Compose, Pi 0.80.3, Fastify/TypeScript, Vitest, shell deployment-contract tests.
+
+## Global Constraints
+
+- Never copy or log provider keys.
+- Mount the auth file read-only.
+- Enabled model order is ZAI, DeepSeek Flash, DeepSeek Pro, local Qwen.
+- UI error strings remain English.
+- Preserve the question in the frontend retry composer.
+- Delete only the three explicitly approved incomplete session IDs.
+
+---
+
+### Task 1: Container Pi auth and model policy
+
+**Files:**
+- Modify: `compose.yaml`
+- Modify: `.env.example`
+- Modify: `deploy/pi/settings.json`
+- Modify: `docker/core.Dockerfile`
+- Test: `scripts/test-default-compose.sh`
+- Test: `scripts/test-container-deployment.sh`
+
+**Interfaces:**
+- Consumes: `PI_AUTH_FILE`, an absolute readable host path.
+- Produces: `/home/thoth/.pi/agent/auth.json` read-only and a four-entry `enabledModels` policy.
+
+- [ ] Add failing deployment-contract assertions for the auth mount, four enabled models, and Pi 0.80.3.
+- [ ] Run the focused shell tests and confirm the expected failures.
+- [ ] Add the configurable auth mount, model policy, environment documentation, and Pi version alignment.
+- [ ] Re-run the focused shell tests and confirm they pass.
+
+### Task 2: Pre-persistence model availability guard
+
+**Files:**
+- Modify: `backend/src/app.ts`
+- Modify: `backend/src/routes/sessions.ts`
+- Test: `backend/test/routes-sessions.test.ts`
+
+**Interfaces:**
+- Consumes: the existing `ListModelsFn` used by model/settings routes.
+- Produces: a sanitized 503 before `sessionNew` when saved settings are unavailable.
+
+- [ ] Add a failing route test proving an unavailable model returns 503 and never calls `sessionNew`.
+- [ ] Run the single Vitest test and confirm the expected failure.
+- [ ] Inject the model-list dependency into session routes and implement the minimal guard.
+- [ ] Re-run the focused test and confirm it passes.
+
+### Task 3: Post-persistence runtime-construction failure
+
+**Files:**
+- Modify: `backend/src/routes/sessions.ts`
+- Test: `backend/test/routes-sessions.test.ts`
+
+**Interfaces:**
+- Consumes: `ThtRunner.failSession(id, workspace)` and `PiProcessManager.createFor`.
+- Produces: failed persisted state plus sanitized 503 when runtime construction throws.
+
+- [ ] Add a failing route test for a throwing `createFor` after `sessionNew`.
+- [ ] Run the single test and confirm it fails because the route currently returns 500 and leaves the session open.
+- [ ] Catch runtime construction/binding failures, persist `failed`, and return the startup error.
+- [ ] Re-run the focused test and confirm it passes.
+
+### Task 4: Cleanup and full verification
+
+**Files:**
+- Modify: external PSD session store only through `tht session delete`.
+
+**Interfaces:**
+- Consumes: the three approved session IDs.
+- Produces: no corresponding directories or API rows.
+
+- [ ] Run backend Vitest and TypeScript typecheck.
+- [ ] Run deployment-contract tests and render Compose with the real auth path.
+- [ ] Rebuild/recreate the core container and verify health.
+- [ ] Verify `/models` returns all four enabled models in order.
+- [ ] Start a uniquely named DeepSeek smoke and observe the first reviewer gate; clean up only the smoke.
+- [ ] Delete the three approved incomplete sessions and verify they are absent.
+- [ ] Run `git diff --check` and inspect the final diff for secret leakage.
@@ -0,0 +1,46 @@
+# Pi User Authentication and Startup Error Handling
+
+## Goal
+
+Make the Dockerized ThothII runtime use the same provider authentication that Pi stores for
+the host user, expose only the explicitly enabled model set (including DeepSeek V4 Pro), and
+avoid leaving apparently healthy `open` sessions when model startup cannot begin.
+
+## Runtime configuration
+
+- Keep the container user `thoth` and `HOME=/home/thoth`; those are valid container-local
+  identities and must not be changed to a macOS path.
+- Bind-mount a configurable host Pi auth file, `PI_AUTH_FILE`, to
+  `/home/thoth/.pi/agent/auth.json` read-only. The default local value is
+  `${HOME}/.pi/agent/auth.json`; deployments may override it with another absolute path.
+- Keep `deploy/pi/settings.json` as the non-secret runtime policy. It must enable, in order:
+  `zai/glm-5.2`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-pro`, and
+  `aritmolab/qwen3.6-35b-a3b`.
+- Keep `deploy/pi/models.json` for custom provider definitions only. Provider credentials stay
+  exclusively in Pi's user auth file and are never copied into the repository.
+- Run Pi 0.80.3 in the core image, matching the audited backend provider contract.
+
+## Session-start behavior
+
+The settings write endpoint remains the main model-validation boundary. Session creation adds a
+defense-in-depth availability check before persistence: if the saved provider/model is absent
+from Pi's current enabled and authenticated model list, return a sanitized 503 and do not call
+`tht session new`.
+
+If runtime construction fails after persistence despite that check (for example a race or local
+process limit), catch the error, mark the just-created session failed, and return the same
+sanitized startup error. Never expose provider credentials or raw Pi errors to the browser.
+Asynchronous bootstrap failures continue to emit `session_failed` and persist failed state.
+
+## Cleanup and verification
+
+Delete only these incomplete sessions:
+
+- `a390c8b8-0a91-4a37-967b-ce7ff9be9797`
+- `a2f974b2-4c48-4967-b4b6-afdbc2b2d541`
+- `f66e1959-3c71-4b10-8aa1-606992046b7e`
+
+Verify configuration contracts, backend tests and typecheck, rendered Compose mounts, `/models`
+containing all four configured models, and a live DeepSeek startup reaching its first reviewer
+gate. The auth file must remain read-only and no secret value may appear in rendered Compose,
+logs, tests, or source control.
@@ -39,6 +39,7 @@ MAX_PI_PROCESSES=4
 PI_PROVIDER=zai
 PI_MODEL=glm-5.2
 PI_THINKING=medium
+PI_AUTH_FILE=$auth_file
 THT_PROFILE=workstation
 THT_DB_NAME=$(required THT_DB_NAME)
 THT_DWH_REST_URL=$(required THT_DWH_REST_URL)
@@ -0,0 +1,34 @@
+#!/bin/sh
+set -eu
+
+cd "$(dirname "$0")/.."
+
+tmp=$(mktemp -d)
+trap 'rm -rf "$tmp"' EXIT HUP INT TERM
+auth_file="$tmp/auth.json"
+printf '%s\n' '{}' >"$auth_file"
+chmod 0600 "$auth_file"
+
+rendered=$(PI_AUTH_FILE="$auth_file" docker compose config)
+printf '%s\n' "$rendered" | grep -q "source: $auth_file"
+printf '%s\n' "$rendered" | grep -q 'target: /home/thoth/.pi/agent/auth.json'
+printf '%s\n' "$rendered" | grep -A4 'target: /home/thoth/.pi/agent/auth.json' \
+  | grep -q 'read_only: true'
+
+python3 - <<'PY'
+import json
+from pathlib import Path
+
+settings = json.loads(Path("deploy/pi/settings.json").read_text())
+assert settings["enabledModels"] == [
+    "zai/glm-5.2",
+    "deepseek/deepseek-v4-flash",
+    "deepseek/deepseek-v4-pro",
+    "aritmolab/qwen3.6-35b-a3b",
+]
+PY
+
+grep -q '^ARG PI_VERSION=0.80.3$' docker/core.Dockerfile
+grep -q '^PI_AUTH_FILE=$auth_file$' scripts/bootstrap-local-psd-docker-config.sh
+
+echo "Pi user-auth Compose contract passed."