fss-link 1.7.7 → 1.9.2

package/docs/CONFIGURATION.md

@@ -10,21 +10,6 @@ FSS Link supports multiple LLM providers. Configure via CLI flags, environment v
 2. **Database config** — persistent, survives restarts
 3. **Environment variables** — traditional fallback
 
-### Ollama
-
-Local models via Ollama. Default port 11434.
-
-```bash
-# CLI
-fss-link --provider ollama --model qwen3:4b
-
-# Or set the context window for large conversations
-fss-link --provider ollama --model qwen3:4b
-# Then use /context 32768 inside the session
-```
-
-**Context window**: Defaults to 32,768 tokens. Use the `/context` command to set a custom value that persists to the database.
-
 ### LM Studio
 
 Local models via LM Studio. Default port 1234.
@@ -65,7 +50,7 @@ fss-link --provider gemini-api-key --model gemini-2.0-flash
 
 ## Database Configuration
 
-FSS Link stores model configuration in a SQLite database at `~/.fss-link/config.db`. This is the persistent source of truth for model settings.
+FSS Link stores model configuration in a SQLite database at `~/.fss-link/fss-link.db`. This is the persistent source of truth for model settings.
 
 <!-- bobai:image-card width="6" -->
 ![Database Persistence System](./assets/batch_0003_database-persistence-system-a.png)
@@ -77,19 +62,19 @@ Your model choice survives restarts. CLI flags override, environment fallback.
 
 ```bash
 # View current config
-sqlite3 ~/.fss-link/config.db "SELECT auth_type, model_name, endpoint_url, is_active FROM model_configs"
+sqlite3 ~/.fss-link/fss-link.db "SELECT auth_type, model_name, endpoint_url, is_active FROM model_configs"
 
 # Switch active model
-sqlite3 ~/.fss-link/config.db "UPDATE model_configs SET is_active = 0"
-sqlite3 ~/.fss-link/config.db "UPDATE model_configs SET is_active = 1 WHERE auth_type = 'ollama' AND model_name = 'qwen3:4b'"
+sqlite3 ~/.fss-link/fss-link.db "UPDATE model_configs SET is_active = 0"
+sqlite3 ~/.fss-link/fss-link.db "UPDATE model_configs SET is_active = 1 WHERE auth_type = 'bob-ai' AND model_name = 'qwen3.5-35b-a3b'"
 
 # Change endpoint
-sqlite3 ~/.fss-link/config.db "UPDATE model_configs SET endpoint_url = 'http://your-server:1234/v1' WHERE auth_type = 'lm-studio'"
+sqlite3 ~/.fss-link/fss-link.db "UPDATE model_configs SET endpoint_url = 'http://your-server:1234/v1' WHERE auth_type = 'lm-studio'"
 ```
 
 ### Database Location
 
-- Linux/macOS: `~/.fss-link/config.db`
+- Linux/macOS: `~/.fss-link/fss-link.db`
 - Data directory: `~/.fss-link/`
 - Todos: `~/.fss-link/todos/`
 
@@ -103,10 +88,9 @@ The context window is the maximum number of tokens the model can process in a si
 
 1. **Manual override** in `settings.json` (`chatCompression.contextWindow`)
 2. **LM Studio API query** (auto-detected from server)
-3. **Ollama `num_ctx`** from `/context` command or sampling params
-4. **OpenAI-compatible `/models` endpoint** (vLLM `max_model_len`)
-5. **Static lookup** for known models (Gemini variants)
-6. **Provider defaults**: Ollama 32k, LM Studio 32k, OpenAI-compat 128k
+3. **OpenAI-compatible `/models` endpoint** (vLLM `max_model_len`)
+4. **Static lookup** for known models (Gemini variants)
+5. **Provider defaults**: LM Studio 32k, OpenAI-compat 128k
 
 ### Compression
 
@@ -128,7 +112,7 @@ Full detail on recent context, compressed summaries for older messages.
 
 ### The `/context` Command
 
-Set the context window for Ollama models:
+Set the context window size:
 
 ```
 /context 32768    # Set to 32k

package/docs/README.md

@@ -21,7 +21,7 @@ $ fss-link
 ## Key Features
 
 <!-- bobai:badges -->
-Ollama, LM Studio, OpenAI, Gemini, vLLM
+LM Studio, BobAI, OpenAI, Gemini, vLLM
 <!-- /bobai:badges -->
 
 - **Multi-provider support** — Connect to any LLM (local or cloud)
@@ -40,7 +40,7 @@ Ollama, LM Studio, OpenAI, Gemini, vLLM
 <!-- bobai:image-card width="6" -->
 ![Multi-Provider Connection Hub](./assets/batch_0002_multiprovider-connection-hub-a.png)
 ### Connect Anywhere
-Local models via Ollama. Cloud providers (OpenAI, Gemini). Custom endpoints (vLLM, LM Studio).
+Local models via LM Studio and BobAI. Cloud providers (OpenAI, Gemini). Custom endpoints (vLLM).
 <!-- /bobai:image-card -->
 
 ## Installation
@@ -65,14 +65,11 @@ npm install -g .
 
 ## Quick Start
 
-### With Ollama (Local)
+### With BobAI / vLLM (Local)
 
 ```bash
-# Start Ollama with a model
-ollama run qwen3:4b
-
-# Launch FSS Link
-fss-link --provider ollama --model qwen3:4b
+export BOB_AI_BASE_URL="http://your-server:8000/v1"
+fss-link --provider bob-ai --model qwen3.5-35b-a3b
 ```
 
 ### With LM Studio (Local)
@@ -186,6 +183,7 @@ npx vitest run packages/cli/src/config/database.test.ts
 
 - [Configuration Guide](CONFIGURATION.md) — providers, models, database, context settings
 - [Tools Reference](TOOLS.md) — all available tools and their parameters
+- [Slash Commands](SLASH-COMMANDS.md) — `/resume`, `/rewind`, `/sessions`, and the Welcome Back dialog
 - [Tool Flow Diagrams](../fss-docs/tool-flow-diagrams/) — visual documentation with Mermaid diagrams
 
 ## License

package/docs/SLASH-COMMANDS.md

@@ -0,0 +1,186 @@
+# Slash Commands — Session Management
+
+## `/resume` — List and Resume Saved Sessions
+
+Resume a previous conversation session by number, title, or session ID.
+
+### Usage
+
+```
+/resume                          # List recent sessions
+/resume <number>                 # Resume by list position
+/resume <title substring>        # Resume by title match
+/resume <session-id>             # Resume by exact session ID
+```
+
+### Alternatives
+
+`/sessions`, `/continue` — all three names invoke the same command.
+
+### Listing Sessions
+
+Running `/resume` with no arguments displays a numbered list of up to 50 recent sessions for the current project, sorted by most recently updated:
+
+```
+Recent sessions:
+
+  1. Implement auth middleware for API endpoints    2 hours ago    14 turns
+  2. Fix login bug on password reset flow           1 day ago      8 turns
+  3. Set up CI pipeline with GitHub Actions         3 days ago     22 turns
+
+Type a number to resume, or /resume <partial title> to match by name.
+```
+
+Titles are truncated at 55 characters. The list is scoped to the current project (identified by project hash).
+
+### Selection Methods
+
+| Method | Example | Behavior |
+|--------|---------|----------|
+| **Numeric index** | `/resume 2` | Selects the second item in the listed order (1-based) |
+| **Title substring** | `/resume auth` | First session whose title contains "auth" (case-insensitive) |
+| **Exact session ID** | `/resume abc123def` | Matches the session's unique ID exactly |
+
+### Matching Rules
+
+- **Numeric index** is checked first. If the number is out of range (fewer sessions than the number given), it falls through to title matching.
+- **Title substring** uses `String.prototype.includes()` — any part of the title matching the input selects the first such session. There is no ranking or scoring; the first match wins.
+- **Exact session ID** is the final fallback if neither numeric nor title matching succeeds.
+- If no match is found at all, an error message is shown: `No session matched "foo". Use /resume to list sessions.`
+
+### Tab Completion
+
+Pressing Tab while typing `/resume <partial>` shows completions for session titles that **start with** the partial text (`startsWith`). This is intentionally stricter than the action's own matching (`includes`) — tab completion may show fewer options than what `/resume <text>` would actually match.
+
+### What Happens When You Resume
+
+The selected session's full conversation history is restored:
+- The Gemini client's history is replaced with the saved history from the session
+- The session ID is set so subsequent exchanges update the same session record
+- Turn count is restored from the session record
+- The UI displays the restored history as a scrollable message list
+
+### Session Storage
+
+Sessions are stored in `~/.fss-link/sessions.db` (a dedicated SQLite database). Each session record includes:
+- `id` — unique session identifier
+- `title` — auto-generated from the first user message (truncated to 80 chars)
+- `project_path`, `project_hash` — project identification
+- `provider`, `model_name` — which model was used
+- `created_at`, `updated_at` — timestamps
+- `turn_count`, `total_input_tokens`, `total_output_tokens` — usage metrics
+- `history_json` — full conversation history as JSON
+
+Sessions are created on the first exchange in a conversation and updated after each subsequent exchange. An auto-save timer flushes changes every 30 seconds.
+
+---
+
+## `/rewind` — Rewind to a Previous Turn
+
+Rewind the conversation to a selected past turn, discarding everything after it.
+
+### Usage
+
+```
+/rewind                          # Open rewind dialog
+```
+
+No arguments are accepted — `/rewind foo` behaves identically to `/rewind`.
+
+### How It Works
+
+Running `/rewind` opens an interactive dialog that shows all user-initiated turns in the current conversation. Selecting a turn discards everything after it, effectively rewinding the conversation to that point.
+
+### Turn Extraction
+
+The dialog filters the conversation history to show only meaningful user turns:
+- **Included**: User messages with text content
+- **Excluded**: Tool-response turns (all parts are `functionResponse`), system notes (`[System note:`), steering messages (`[Steering message`)
+
+Turns are displayed in reverse-chronological order (most recent first), numbered T1, T2, T3… from oldest to newest.
+
+### Navigation & Search
+
+| Key | Action |
+|-----|--------|
+| `↑` / `↓` | Move selection up/down |
+| `Enter` | Confirm selection and rewind |
+| `Esc` (first press) | Clear the search filter |
+| `Esc` (second press) | Close the dialog without rewinding |
+| `Backspace` | Delete one character from the search filter |
+| Any printable character | Type into the search filter box |
+
+### Search
+
+The dialog has a working text filter. Type any characters to narrow the visible turns:
+
+- **Case-insensitive substring match** on turn text
+- Selection resets to the top (index 0) when the filter changes
+- Shows "No turns match" if the filter produces zero results
+- First `Esc` clears the filter and restores the full list; second `Esc` closes the dialog
+
+**Limitations:**
+- Single-term only — multi-word queries like "auth middleware" won't work as two separate terms
+- Searches only user message text, not tool calls, results, or delta events
+- No ranking or scoring — just `includes` substring match
+
+### What Happens When You Rewind
+
+1. The conversation history is cleared
+2. A preview message is built from the selected turn's content
+3. All turns after the selected one are discarded
+4. The model can then continue from the rewound point
+
+### Known Behavior
+
+The rewind point uses `fullHistory.slice(0, contentIndex)` — the selected turn is **included** in the rewound history. The dialog help text says "conversation after selected turn will be discarded," which is accurate: the selected turn itself is preserved, everything after it is removed.
+
+---
+
+## `/sessions` — Alias for `/resume`
+
+`/sessions` and `/continue` are aliases for `/resume`. All three names invoke the same command with identical behavior. See `/resume` above for full details.
+
+---
+
+## Welcome Back Dialog — Project-Level Resume
+
+The **Welcome Back dialog** is a separate feature from `/resume`. It appears automatically when you launch FSS Link in a project that has prior session history, offering a high-level choice to continue from where you left off or start fresh.
+
+### When It Appears
+
+- On startup, when `enableWelcomeBack` is enabled in settings (default: on)
+- Only when the project has existing conversation history
+- Uses `ProjectSummaryParser` to analyze project state — not `sessions.db` directly
+
+### Options
+
+| Option | Keyboard Shortcut | Behavior |
+|--------|-------------------|----------|
+| **Continue Project** | `C` | Resumes from the most recent session with contextual summary |
+| **Start Fresh Session** | `R` | Begins a new conversation with no history |
+| **Cancel** | `Q` / `Escape` | Exits without starting a session |
+
+### What It Shows
+
+The dialog displays project-level information including:
+- Project goal (if available)
+- Time since last activity
+- Session count and active sessions
+- Momentum indicator (high / building / stale / none)
+- Git status (branch, staged/unstaged changes, last commit)
+- Efficiency metrics and recent activity summary
+- Next suggestion (if available)
+
+### Key Differences from `/resume`
+
+| Aspect | Welcome Back Dialog | `/resume` |
+|--------|---------------------|-----------|
+| **Trigger** | Automatic on project launch | Manual slash command |
+| **Scope** | Project-level (one choice) | Per-session picker (up to 50) |
+| **Data source** | `ProjectSummaryParser` (analysis of project state) | `sessions.db` (direct session records) |
+| **Selection** | Continue / Restart / Cancel | Number, title substring, or session ID |
+| **Context** | Smart summary built from project analysis | Full conversation history restored verbatim |
+| **Search** | None — single decision point | Substring search across session titles |
+
+The Welcome Back dialog is best for quick decisions at project launch. `/resume` is for browsing and selecting from multiple saved sessions within an active conversation.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "fss-link",
-  "version": "1.7.7",
+  "version": "1.9.2",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -13,7 +13,7 @@
     "url": "git+https://github.com/FSSCoding/fss-link.git"
   },
   "config": {
-    "sandboxImageUri": "ghcr.io/fsscoding/fss-link:1.7.5"
+    "sandboxImageUri": "ghcr.io/fsscoding/fss-link:1.9.2"
   },
   "scripts": {
     "start": "node scripts/start.js",
@@ -82,6 +82,7 @@
     "LICENSE"
   ],
   "devDependencies": {
+    "@testing-library/dom": "^10.4.1",
     "@types/ink-testing-library": "^1.0.4",
     "@vitest/coverage-v8": "^4.1.8",
     "concurrently": "^9.2.0",

package/scripts/build_package.js

@@ -18,7 +18,7 @@
 // limitations under the License.
 
 import { execSync } from 'child_process';
-import { writeFileSync } from 'fs';
+import { writeFileSync, rmSync } from 'fs';
 import { join } from 'path';
 
 if (!process.cwd().includes('packages')) {
@@ -26,6 +26,13 @@ if (!process.cwd().includes('packages')) {
   process.exit(1);
 }
 
+// Clean dist first — `tsc --build` is incremental and trusts its
+// .tsbuildinfo cache. Any prior partial `rm -rf dist` or interrupted build
+// leaves that cache out of sync with what's actually on disk, which surfaces
+// as TS5055 "Cannot write file ... because it would overwrite input file".
+// Same fix already applied in prebundle-sync-dist.js for the bundle path.
+rmSync(join(process.cwd(), 'dist'), { recursive: true, force: true });
+
 // build typescript files
 execSync('tsc --build', { stdio: 'inherit' });
 

package/scripts/prebundle-sync-dist.js

@@ -24,6 +24,14 @@ const root = resolve(__dirname, '..');
 const packages = ['packages/core', 'packages/cli'];
 
 for (const pkg of packages) {
+  // Clean dist first to avoid incremental build cache corruption that
+  // produces mangled output (e.g. #; private fields, broken syntax).
+  // See: incremental tsbuildinfo gets out of sync with source changes.
+  const { execSync } = await import('child_process');
+  const { rm } = await import('fs/promises');
+  const { resolve } = await import('path');
+  const distDir = resolve(root, pkg, 'dist');
+  try { await rm(distDir, { recursive: true, force: true }); } catch {}
   const tsconfig = resolve(root, pkg, 'tsconfig.json');
   try {
     execSync(`npx tsc --noCheck -p ${tsconfig}`, {

package/scripts/version.js

@@ -36,33 +36,44 @@ if (!versionType) {
 // 2. Bump the version in the root and all workspace package.json files.
 run(`npm version ${versionType} --no-git-tag-version --allow-same-version`);
 
-// 3. Get all workspaces and filter out the ones we don't want to version.
-const workspacesToExclude = [];
+// 3. Resolve workspace globs and collect all workspace names.
+const workspacesToExclude = [
+  'fss-link-vscode-ide-companion',
+  '@fsscoding/fss-link-web-client',
+];
 const rootPkg = readJson(resolve(process.cwd(), 'package.json'));
 const workspaceDirs = rootPkg.workspaces || [];
+const { glob } = await import('glob');
 const workspacesToVersion = [];
-for (const dir of workspaceDirs) {
-  const pkgPath = resolve(process.cwd(), dir, 'package.json');
-  try {
-    const wsPkg = readJson(pkgPath);
-    if (!workspacesToExclude.includes(wsPkg.name)) {
-      workspacesToVersion.push(wsPkg.name);
+for (const pattern of workspaceDirs) {
+  const matches = await glob(pattern, { cwd: process.cwd(), absolute: false });
+  for (const dir of matches) {
+    const pkgPath = resolve(process.cwd(), dir, 'package.json');
+    try {
+      const wsPkg = readJson(pkgPath);
+      if (!workspacesToExclude.includes(wsPkg.name)) {
+        workspacesToVersion.push({ name: wsPkg.name, dir });
+      }
+    } catch {
+      // Skip directories without package.json
     }
-  } catch {
-    // Skip directories without package.json
   }
 }
 
-for (const workspaceName of workspacesToVersion) {
-  run(
-    `npm version ${versionType} --workspace ${workspaceName} --no-git-tag-version --allow-same-version`,
-  );
-}
-
-// 4. Get the new version number from the root package.json
+// 4. Get the new version number from the root package.json (AFTER npm version bump)
 const rootPackageJsonPath = resolve(process.cwd(), 'package.json');
 const newVersion = readJson(rootPackageJsonPath).version;
 
+for (const { name, dir } of workspacesToVersion) {
+  // npm version doesn't support --legacy-peer-deps, so we update the file directly
+  // and let the final npm install reconcile everything
+  const pkgPath = resolve(process.cwd(), dir, 'package.json');
+  const wsPkg = readJson(pkgPath);
+  wsPkg.version = newVersion;
+  writeJson(pkgPath, wsPkg);
+  console.log(`Updated ${name} to v${newVersion}`);
+}
+
 // 6. Update the sandboxImageUri in the root package.json
 const rootPackageJson = readJson(rootPackageJsonPath);
 if (rootPackageJson.config?.sandboxImageUri) {
@@ -86,6 +97,6 @@ if (cliPackageJson.config?.sandboxImageUri) {
 
 // 8. Run `npm install` to update package-lock.json.
 // --ignore-scripts prevents the prepare hook (bundle) from firing before deps exist.
-run('npm install --ignore-scripts');
+run('npm install --ignore-scripts --legacy-peer-deps');
 
 console.log(`Successfully bumped versions to v${newVersion}.`);