v1.1.0:2 — model-agnostic AI program generation (5 providers)

Five providers behind one streaming abstraction:
  - claude              (Anthropic)
  - openai              (api.openai.com)
  - openai-compatible   (any base URL — OpenRouter / LiteLLM /
                         vLLM / Together / your own gateway)
  - gemini              (Google)
  - ollama              (self-hosted; no key; LAN URL like
                         http://ollama.embassy:11434)

The "self-hosted Ollama on Start9" angle is the killer use case —
configure Settings → AI integration with the LAN URL of your Ollama
service and no API keys ever leave your network.

Architecture
  - lib/ai/types.ts              LLMProvider streaming interface
  - lib/ai/sse.ts                shared SSE + NDJSON line iterators
  - lib/ai/providers/*.ts        5 implementations + factory
  - lib/ai/programSchema.ts      Zod schema + JSON-schema-for-prompt +
                                  parseAIProgram with markdown-fence
                                  stripping and balanced-brace JSON
                                  extraction
  - lib/ai/apply.ts              materializes parsed AIProgram into
                                  Program tree (validates exerciseIds,
                                  rejects unresolved nulls, atomic
                                  transaction, sets aiGenerated=true)

Schema
  - UserPreferences gets aiProvider/aiModel/aiBaseUrl/aiApiKey
    (plaintext — same threat model as the rest of /data). Dead
    enableClaudeAI/claudeApiKey columns from v1.0.0:1-7 stay as
    no-op fields.
  - AIPromptTemplate (userId nullable; userId=NULL = built-in)
  - AIGeneration (raw response + parsed program + status +
    appliedProgramId + token counts)
  - All compat-ALTER'd in docker_entrypoint.sh on first boot.

API
  - POST   /api/ai/generate              SSE streaming: emits
                                           generation/text/usage/complete
                                           events; persists AIGeneration
                                           row up front so failures show
                                           in history too
  - POST   /api/ai/apply                 takes user-edited AIProgram,
                                           creates Program, marks
                                           generation as applied
  - GET    /api/ai/templates             built-ins + this user's own
  - POST   /api/ai/templates             create user-owned template
  - PATCH  /api/ai/templates/[id]        edit; built-ins admin-only
  - DELETE /api/ai/templates/[id]        delete; built-ins admin-only
  - GET    /api/ai/generations           list (paginated)
  - GET    /api/ai/generations/[id]      full row
  - DELETE /api/ai/generations/[id]      delete one (Program survives)
  - GET    /api/ai/config                returns aiKeyConfigured flag,
                                           never plaintext key
  - POST   /api/ai/config                update provider config
  - DELETE /api/admin/ai/generations     admin-only "clear all" with
                                           optional userId / olderThanDays

UI
  - Settings → AI integration            provider/model/URL/key form;
                                           plaintext key warning visible
  - /main/ai                             hub page with cards
  - /main/ai/generate                    template picker + textarea +
                                           live SSE stream + cancel +
                                           ProgramPreview with inline
                                           unknown-exercise resolver +
                                           apply button + redirect to
                                           the new Program
  - /main/ai/templates                   list + create + edit + delete;
                                           per-row "show prompt" expand;
                                           built-in delete warns about
                                           reconcile re-creation
  - /main/ai/history                     list + delete; status badges;
                                           link to applied Program
  - Nav: "AI" entry between Programs and Exercises (Sparkles icon)

Built-in templates
  - prisma/aiTemplates.seed.json: 5 starter templates (hypertrophy /
    strength / endurance / recovery / custom)
  - prisma/ensurePromptTemplates.cjs: per-boot reconcile,
    INSERT-or-UPDATE keyed on (userId IS NULL AND name=...);
    user-created templates never touched

Tests
  - tests/ai-programSchema.test.ts: extractJson + parseAIProgram
    edge cases (markdown fences, balanced braces, malformed JSON,
    Zod shape rejection, unresolved-exerciseId tolerance)
  - tests/ai-apply.test.ts: materializes valid AIProgram, rejects
    cross-user exerciseIds, rejects unresolved exercises, honors
    isActive flag
  - tests/routes-ai-templates.test.ts: built-in vs user permissions,
    cross-user template isolation, /api/ai/config plaintext-key safety,
    provider enum validation
  - 123 tests across 14 files, all passing.

No data migration. Existing /data is augmented with the new columns
+ tables only.

start9/0.4/docker_entrypoint.sh

@@ -105,6 +105,73 @@ if command -v sqlite3 >/dev/null 2>&1 && [ -f "$DB_PATH" ]; then
     sqlite3 "$DB_PATH" "CREATE INDEX IF NOT EXISTS Workout_programDayId_idx ON Workout(programDayId);"
   fi
 
+  # v1.1.0:2 added the model-agnostic AI configuration fields to
+  # UserPreferences. Replaces the dead enableClaudeAI / claudeApiKey
+  # single-provider scheme (those columns stay as no-op fields for
+  # back-compat).
+  if ! sqlite3 "$DB_PATH" "PRAGMA table_info('UserPreferences');" 2>/dev/null | grep -q "|aiProvider|"; then
+    log "adding AI configuration columns to UserPreferences"
+    sqlite3 "$DB_PATH" "ALTER TABLE UserPreferences ADD COLUMN aiProvider TEXT;"
+    sqlite3 "$DB_PATH" "ALTER TABLE UserPreferences ADD COLUMN aiModel TEXT;"
+    sqlite3 "$DB_PATH" "ALTER TABLE UserPreferences ADD COLUMN aiBaseUrl TEXT;"
+    sqlite3 "$DB_PATH" "ALTER TABLE UserPreferences ADD COLUMN aiApiKey TEXT;"
+  fi
+
+  # v1.1.0:2 also added AIPromptTemplate + AIGeneration tables.
+  if ! sqlite3 "$DB_PATH" \
+    "SELECT name FROM sqlite_master WHERE type='table' AND name='AIPromptTemplate';" \
+    2>/dev/null | grep -q AIPromptTemplate; then
+    log "creating AIPromptTemplate table"
+    sqlite3 "$DB_PATH" "
+      CREATE TABLE AIPromptTemplate (
+        id                 TEXT PRIMARY KEY,
+        userId             TEXT,
+        name               TEXT NOT NULL,
+        description        TEXT,
+        systemPrompt       TEXT NOT NULL,
+        userPromptTemplate TEXT NOT NULL,
+        isBuiltIn          INTEGER NOT NULL DEFAULT 0,
+        createdAt          DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+        updatedAt          DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+        FOREIGN KEY (userId) REFERENCES User(id) ON DELETE CASCADE
+      );
+      CREATE INDEX AIPromptTemplate_userId_idx ON AIPromptTemplate(userId);
+      CREATE INDEX AIPromptTemplate_isBuiltIn_idx ON AIPromptTemplate(isBuiltIn);
+    "
+  fi
+
+  if ! sqlite3 "$DB_PATH" \
+    "SELECT name FROM sqlite_master WHERE type='table' AND name='AIGeneration';" \
+    2>/dev/null | grep -q AIGeneration; then
+    log "creating AIGeneration table"
+    sqlite3 "$DB_PATH" "
+      CREATE TABLE AIGeneration (
+        id                 TEXT PRIMARY KEY,
+        userId             TEXT NOT NULL,
+        templateId         TEXT,
+        templateName       TEXT,
+        userInput          TEXT NOT NULL,
+        systemPrompt       TEXT NOT NULL,
+        userPrompt         TEXT NOT NULL,
+        rawResponse        TEXT,
+        parsedProgram      TEXT,
+        provider           TEXT NOT NULL,
+        model              TEXT NOT NULL,
+        tokensIn           INTEGER,
+        tokensOut          INTEGER,
+        status             TEXT NOT NULL DEFAULT 'pending',
+        errorMessage       TEXT,
+        appliedProgramId   TEXT,
+        createdAt          DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+        updatedAt          DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+        FOREIGN KEY (userId) REFERENCES User(id) ON DELETE CASCADE
+      );
+      CREATE INDEX AIGeneration_userId_createdAt_idx ON AIGeneration(userId, createdAt);
+      CREATE INDEX AIGeneration_status_idx ON AIGeneration(status);
+      CREATE INDEX AIGeneration_appliedProgramId_idx ON AIGeneration(appliedProgramId);
+    "
+  fi
+
   if ! sqlite3 "$DB_PATH" \
     "SELECT name FROM sqlite_master WHERE type='table' AND name='InstanceSettings';" \
     2>/dev/null | grep -q InstanceSettings; then
@@ -173,6 +240,19 @@ else
   log "skipping library ensure (json or db not found)"
 fi
 
+# v1.1.0:2 — reconcile built-in AI prompt templates from the curated
+# JSON. Same INSERT-or-UPDATE pattern as the exercise library, scoped
+# to userId IS NULL so user-created templates are never touched.
+TEMPLATES_JSON_PATH="${WORKOUT_TEMPLATES_JSON_PATH:-/app/prisma/aiTemplates.seed.json}"
+TEMPLATES_SCRIPT="/app/prisma/ensurePromptTemplates.cjs"
+if [ -f "$TEMPLATES_JSON_PATH" ] && [ -f "$TEMPLATES_SCRIPT" ] && [ -f "$DB_PATH" ]; then
+  log "ensuring built-in AI prompt templates are present"
+  node "$TEMPLATES_SCRIPT" \
+    --db "$DB_PATH" \
+    --json "$TEMPLATES_JSON_PATH" \
+    || log "WARNING: ensurePromptTemplates failed; continuing boot"
+fi
+
 # -----------------------------------------------------------------------------
 # Step 4 — launch the app.
 # -----------------------------------------------------------------------------

start9/0.4/startos/versions/index.ts

@@ -7,6 +7,7 @@ import { v_1_0_0_5 } from './v1.0.0.5'
 import { v_1_0_0_6 } from './v1.0.0.6'
 import { v_1_0_0_7 } from './v1.0.0.7'
 import { v_1_1_0_1 } from './v1.1.0.1'
+import { v_1_1_0_2 } from './v1.1.0.2'
 
 /**
  * Version graph for the `proof-of-work` package.
@@ -22,9 +23,11 @@ import { v_1_1_0_1 } from './v1.1.0.1'
  * v1.0.0:6 — paginate workout history (infinite scroll).
  * v1.0.0:7 — exercise library cleanup, photo-import removal.
  * v1.1.0:1 — Programs UI (manual create / save / follow).
+ * v1.1.0:2 — AI program generation, 5 providers (Claude / OpenAI /
+ *            OpenAI-compatible / Gemini / Ollama).
  */
 export const versionGraph = VersionGraph.of({
-  current: v_1_1_0_1,
+  current: v_1_1_0_2,
   other: [
     v_1_0_0_1,
     v_1_0_0_2,
@@ -33,5 +36,6 @@ export const versionGraph = VersionGraph.of({
     v_1_0_0_5,
     v_1_0_0_6,
     v_1_0_0_7,
+    v_1_1_0_1,
   ],
 })

start9/0.4/startos/versions/v1.1.0.2.ts

@@ -0,0 +1,62 @@
+import { IMPOSSIBLE, VersionInfo } from '@start9labs/start-sdk'
+
+/**
+ * v1.1.0:2 — model-agnostic AI program generation.
+ *
+ * Five providers behind one streaming abstraction:
+ *
+ *   - claude              (Anthropic)
+ *   - openai              (api.openai.com)
+ *   - openai-compatible   (any base URL — OpenRouter / LiteLLM /
+ *                          vLLM / Together / your own gateway)
+ *   - gemini              (Google)
+ *   - ollama              (self-hosted; no key; uses LAN URL)
+ *
+ * The "self-hosted Ollama on Start9" angle is the killer use case —
+ * point Settings → AI integration → Base URL at
+ * `http://ollama.embassy:11434` (or whatever Ollama service you have
+ * on the same StartOS host) and no API keys ever leave your network.
+ *
+ * Workflow
+ *   1. Settings → AI integration: pick provider + model + key/URL.
+ *   2. AI → Generate program: pick a template, type your specifics
+ *      ("8 weeks heavy leg emphasis"), click Generate.
+ *   3. Watch the response stream in word-by-word via SSE.
+ *   4. Server validates the JSON output against a Zod schema and
+ *      stores both raw + parsed in AIGeneration.
+ *   5. Preview UI shows the program tree. Unknown exercises (the
+ *      model picked something not in your library) are highlighted
+ *      and you can map them to existing entries or remove them.
+ *   6. Apply → materializes into a real Program (same schema/UI as
+ *      the v1.1.0:1 manual programs).
+ *
+ * Ships with 5 built-in prompt templates (hypertrophy block,
+ * strength block, endurance/running block, recovery week, custom).
+ * Built-ins reconcile per-boot the same way curated exercises do.
+ * Both admin and regular users can create their own templates.
+ *
+ * Schema additions
+ *   - UserPreferences: aiProvider, aiModel, aiBaseUrl, aiApiKey
+ *     (plaintext — consistent with the rest of /data/app.db; the
+ *     host-level threat model assumes the operator owns /data).
+ *   - AIPromptTemplate (built-ins userId=NULL, user templates
+ *     userId=<them>).
+ *   - AIGeneration (one row per generate request; raw response,
+ *     parsed program, status, applied program id, token counts).
+ *
+ * Backward compatible: existing UserPreferences rows get the new
+ * columns added with NULL defaults (compat ALTER on first boot);
+ * the dead enableClaudeAI / claudeApiKey columns from v1.0.0:1-7
+ * stay as no-op fields.
+ */
+export const v_1_1_0_2 = VersionInfo.of({
+  version: '1.1.0:2',
+  releaseNotes: {
+    en_US:
+      'AI program generation. Pick from Claude / OpenAI / Gemini / OpenAI-compatible / self-hosted Ollama. Settings → AI integration to configure (Ollama on Start9 needs no API key). AI → Generate program to pick a template, describe what you want, watch the response stream in, review the parsed program, and apply it to your Programs library. Ships 5 starter templates; both admin and regular users can create their own. Generation history is kept until you delete it (per-row Trash; admin-only "clear all" via /api/admin/ai/generations).',
+  },
+  migrations: {
+    up: async () => {},
+    down: IMPOSSIBLE,
+  },
+})