superlocalmemory 3.6.9 → 3.6.11

package/src/superlocalmemory/server/unified_daemon.py

@@ -1183,18 +1183,31 @@ def create_app() -> FastAPI:
     # API keys (x-api-key, Authorization), NOT the SLM API key. Auth-exempt
     # path prefixes are configured below in the auth_middleware block.
     try:
-        from superlocalmemory.optimize.config.store import ConfigStore
+        from superlocalmemory.optimize.config import _set_config_store, get_shared_store
         from superlocalmemory.optimize.proxy.server import ProxyApp, build_proxy_router
 
-        _opt_cfg = ConfigStore().get()
+        # ONE shared ConfigStore for daemon + routes + watchdog + proxy reload
+        # (fixes W-05 fresh-store-per-request; powers runtime hot-reload).
+        _opt_store = get_shared_store()
+        _set_config_store(_opt_store)
+        _opt_cfg = _opt_store.get()
+        # W-03 fix: the proxy path is gated by proxy_enabled ALONE. The master
+        # `enabled` gates only the SDK adapter, never the proxy mount.
         if _opt_cfg.proxy_enabled:
             _proxy = ProxyApp(config=_opt_cfg)
             application.state.optimize_proxy = _proxy
             _proxy_router = build_proxy_router(_proxy)
             # prefix="" — proxy claims /v1/*, /v1beta/* directly.
             application.include_router(_proxy_router, prefix="")
+            # v3.6.10: runtime hot-reload — rebuild the proxy HookChain whenever
+            # optimize.json changes so cache_enabled / compress_enabled can be
+            # toggled INDEPENDENTLY from the UI with no restart. UI save fires the
+            # callback immediately; external edits are caught by the 2s watchdog.
+            _opt_store.register_change_callback(_proxy.reload_from_config)
+            _opt_store.start_watchdog()
             logger.info(
-                "optimize.proxy mounted on /v1/*, /v1beta/*  port=8765"
+                "optimize.proxy mounted on /v1/*, /v1beta/*  port=8765 "
+                "(runtime cache/compress hot-reload enabled)"
             )
         else:
             application.state.optimize_proxy = None
@@ -1246,8 +1259,16 @@ def create_app() -> FastAPI:
             logger.info("MCP transport security: allowed_hosts=%r", _mcp_allowed)
         global _mcp_app
         _mcp_app = _mcp_fastmcp.streamable_http_app()
-        application.mount("/mcp", _mcp_app)
-        logger.info("MCP HTTP transport mounted at /mcp (Streamable HTTP, port 8765)")
+
+        # v3.6.10: per-agent-ID routing — /mcp/{agent_id} extracts the agent
+        # identity from the URL path and places it in a ContextVar so all MCP
+        # tools (remember, recall, etc.) automatically use the correct namespace.
+        # AgentIDExtractorASGI lives in mcp/agent_context so it is unit-testable
+        # (tests/test_mcp/test_agent_context.py) rather than buried inline here.
+        from superlocalmemory.mcp.agent_context import AgentIDExtractorASGI
+
+        application.mount("/mcp", AgentIDExtractorASGI(_mcp_app))
+        logger.info("MCP HTTP transport mounted at /mcp (Streamable HTTP, port 8765; per-agent routing enabled)")
     except Exception as _mcp_exc:  # pragma: no cover — defensive
         logger.warning("MCP HTTP mount failed (non-fatal, stdio still works): %s", _mcp_exc)
 

package/src/superlocalmemory/ui/index.html

@@ -1248,6 +1248,16 @@
                                     <input class="form-check-input" type="checkbox" id="opt-enabled">
                                     <label class="form-check-label" for="opt-enabled">Optimize Enabled</label>
                                 </div>
+                                <div class="form-check form-switch mb-2">
+                                    <input class="form-check-input" type="checkbox" id="opt-proxy-enabled">
+                                    <label class="form-check-label" for="opt-proxy-enabled">
+                                        Proxy Enabled
+                                        <span class="text-muted small ms-1">(restart required)</span>
+                                    </label>
+                                </div>
+                                <div id="opt-restart-notice" class="alert alert-warning py-1 px-2 small mb-2 d-none">
+                                    Proxy setting changed. Run <code>slm restart</code> to apply.
+                                </div>
                                 <div class="form-check form-switch mb-2">
                                     <input class="form-check-input" type="checkbox" id="opt-cache-enabled">
                                     <label class="form-check-label" for="opt-cache-enabled">Cache Enabled</label>
@@ -1263,26 +1273,14 @@
                                 <div class="mb-2">
                                     <label for="opt-compress-mode" class="form-label">Compression Mode</label>
                                     <select class="form-select form-select-sm" id="opt-compress-mode">
-                                        <option value="safe">Safe</option>
-                                        <option value="aggressive">Aggressive</option>
+                                        <option value="safe">Safe (lossless)</option>
+                                        <option value="aggressive">Aggressive (LLMLingua-2, prose only)</option>
                                     </select>
                                 </div>
-                                <div class="form-check form-switch mb-2">
-                                    <input class="form-check-input" type="checkbox" id="opt-compress-code">
-                                    <label class="form-check-label" for="opt-compress-code">Code Compression</label>
-                                </div>
                                 <div class="form-check form-switch mb-2">
                                     <input class="form-check-input" type="checkbox" id="opt-compress-prose">
                                     <label class="form-check-label" for="opt-compress-prose">Prose Compression</label>
                                 </div>
-                                <div class="form-check form-switch mb-2">
-                                    <input class="form-check-input" type="checkbox" id="opt-compress-ccr">
-                                    <label class="form-check-label" for="opt-compress-ccr">CCR</label>
-                                </div>
-                                <div class="form-check form-switch mb-2">
-                                    <input class="form-check-input" type="checkbox" id="opt-compress-align">
-                                    <label class="form-check-label" for="opt-compress-align">Alignment Compression</label>
-                                </div>
                             </div>
                             <div class="col-md-6">
                                 <h6>Savings</h6>
@@ -1299,6 +1297,12 @@
                                 <div class="small text-muted">Config version: <span id="opt-config-version">-</span></div>
                                 <div id="opt-stale-warning" class="text-warning small mt-1"></div>
                                 <button class="btn btn-sm btn-outline-primary mt-2" id="opt-copy-url">Copy URL</button>
+                                <div class="mt-2 small text-muted">
+                                    <strong>Point agents at the proxy:</strong><br>
+                                    <code>slm wrap claude</code> — Claude Code<br>
+                                    <code>--openai-api-base http://localhost:8765/v1</code> — Aider<br>
+                                    <code>OPENAI_BASE_URL=http://localhost:8765/v1</code> — OpenAI SDK
+                                </div>
                             </div>
                         </div>
                     </div>

package/src/superlocalmemory/ui/js/auto-settings.js

@@ -324,10 +324,12 @@ async function testConnection() {
     if (resultEl) { resultEl.textContent = 'Testing...'; resultEl.className = 'ms-2 small text-muted'; }
 
     try {
+        var testBody = {provider: provider, model: model};
+        if (apiKey) testBody.api_key = apiKey;
         var resp = await fetch('/api/v3/provider/test', {
             method: 'POST',
             headers: {'Content-Type': 'application/json'},
-            body: JSON.stringify({provider: provider, model: model, api_key: apiKey})
+            body: JSON.stringify(testBody)
         });
         var data = await resp.json();
         if (data.success) {

package/src/superlocalmemory/ui/js/ng-shell.js

@@ -338,6 +338,9 @@
   // ── Lazy Load Tab Data ─────────────────────────────────────
   function triggerTabLoad(tabId) {
     switch(tabId) {
+      case 'brain-pane':
+        if (typeof loadBrain === 'function') loadBrain();
+        break;
       case 'graph-pane':
         if (typeof loadGraph === 'function') loadGraph();
         // v3.4.4: Initialize chat panel if not already present

package/src/superlocalmemory/ui/js/optimize.js

@@ -23,14 +23,12 @@
       if (!resp.ok) return;
       var cfg = await resp.json();
       _setToggle('opt-enabled', cfg.enabled);
+      _setToggle('opt-proxy-enabled', cfg.proxy_enabled);
       _setToggle('opt-cache-enabled', cfg.cache_enabled);
       _setToggle('opt-semantic-enabled', cfg.semantic_enabled);
       _setToggle('opt-compress-enabled', cfg.compress_enabled);
       _setSelect('opt-compress-mode', cfg.compress_mode);
-      _setToggle('opt-compress-code', cfg.compress_code);
       _setToggle('opt-compress-prose', cfg.compress_prose);
-      _setToggle('opt-compress-ccr', cfg.compress_ccr);
-      _setToggle('opt-compress-align', cfg.compress_align);
       var verEl = document.getElementById('opt-config-version');
       if (verEl) verEl.textContent = cfg.config_version || '-';
     } catch (e) {
@@ -70,14 +68,12 @@
     var val = e.target.checked;
 
     var fieldMap = {
-      'opt-enabled': 'enabled',
-      'opt-cache-enabled': 'cache_enabled',
+      'opt-enabled':          'enabled',
+      'opt-proxy-enabled':    'proxy_enabled',
+      'opt-cache-enabled':    'cache_enabled',
       'opt-semantic-enabled': 'semantic_enabled',
       'opt-compress-enabled': 'compress_enabled',
-      'opt-compress-code': 'compress_code',
-      'opt-compress-prose': 'compress_prose',
-      'opt-compress-ccr': 'compress_ccr',
-      'opt-compress-align': 'compress_align'
+      'opt-compress-prose':   'compress_prose'
     };
 
     if (id === 'opt-compress-mode') {
@@ -109,6 +105,10 @@
       var body = {};
       body[field] = val;
       _putConfig(body);
+      if (id === 'opt-proxy-enabled' || id === 'opt-enabled') {
+        var notice = document.getElementById('opt-restart-notice');
+        if (notice) notice.classList.remove('d-none');
+      }
     }
   });
 

package/src/superlocalmemory.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.6.9
+Version: 3.6.11
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: AGPL-3.0-or-later
@@ -58,6 +58,7 @@ Requires-Dist: huggingface_hub==0.36.2
 Requires-Dist: torch==2.11.0
 Requires-Dist: scikit-learn==1.8.0
 Requires-Dist: sqlite-vec==0.1.9
+Requires-Dist: llmlingua==0.2.2
 Provides-Extra: search
 Requires-Dist: sentence-transformers==5.3.0; extra == "search"
 Requires-Dist: optimum==2.1.0; extra == "search"
@@ -94,18 +95,18 @@ Dynamic: license-file
   <img src="https://superlocalmemory.com/assets/logo-mark.png" alt="SuperLocalMemory" width="200"/>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.6</h1>
-<p align="center"><strong>Save up to 90% on every LLM API call. Cache. Compress. Remember.</strong><br/><em>The only local-first memory system that SKIPS repeat calls (100% saved), SHRINKS prompts 60-95%, and REMEMBERS everything — locally, for free. For Claude Code, Cursor, Windsurf, and any AI client.</em></p>
-<p align="center"><code>v3.6.0 "Optimize"</code> — <strong>Cache & Compress & Align. Save up to 90% on every LLM API call — locally.</strong> One command: <code>slm wrap claude</code><br>Also includes v3.5 Scale-Ready: 6-channel recall &lt;1s, CozoDB + LanceDB, Core Memory Block. Your database auto-migrates.</p>
+<h1 align="center">SuperLocalMemory V3.6.11</h1>
+<p align="center"><strong>Cache. Compress. Remember. Three surfaces — proxy, MCP tools, or skill. Every setup covered.</strong><br/><em>The only local-first layer that pairs persistent memory with compression + caching across every Claude plan. Full 1M window preserved in MCP and skill mode.</em></p>
+<p align="center"><code>v3.6.11 "Optimize Everywhere"</code> — <strong>Compress + cache on any plan, three ways in.</strong><br/>Proxy (full-turn cache): <code>slm wrap claude</code> &nbsp;·&nbsp; MCP (proxy-free): add <code>slm_compress</code> to your MCP config &nbsp;·&nbsp; Skill (zero-config): <code>~/.claude/skills/slm-optimize/</code></p>
 <p align="center"><strong>Backed by 3 published research papers</strong> (arXiv preprints + Zenodo-archived) · <a href="https://arxiv.org/abs/2603.02240">arXiv:2603.02240</a> · <a href="https://arxiv.org/abs/2603.14588">arXiv:2603.14588</a> · <a href="https://arxiv.org/abs/2604.04514">arXiv:2604.04514</a></p>
 
 <p align="center">
-  <code>Saves up to 90% on LLM API costs</code> &nbsp;·&nbsp; <code>+10.6pp vs Mem0 zero-LLM</code> &nbsp;·&nbsp; <code>85% Open-Domain (best zero-LLM score)</code> &nbsp;·&nbsp; <code>EU AI Act Ready</code>
+  <code>Proxy · MCP tools · Skill — three surfaces</code> &nbsp;·&nbsp; <code>+10.6pp vs Mem0 zero-LLM</code> &nbsp;·&nbsp; <code>85% Open-Domain (best zero-LLM score)</code> &nbsp;·&nbsp; <code>EU AI Act Ready</code>
 </p>
 
 <p align="center">
   <a href="https://arxiv.org/abs/2603.14588"><img src="https://img.shields.io/badge/arXiv-2603.14588-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"/></a>
-  <a href="https://img.shields.io/badge/Saves_90%25_on_LLM_Costs-22c55e?style=for-the-badge"><img src="https://img.shields.io/badge/Saves_90%25_on_LLM_Costs-22c55e?style=for-the-badge" alt="Saves 90% on LLM Costs"/></a>
+  <a href="#three-surfaces-proxy--mcp-tools--skill"><img src="https://img.shields.io/badge/Proxy_|_MCP_|_Skill-22c55e?style=for-the-badge" alt="Three Surfaces: Proxy, MCP Tools, Skill"/></a>
   <a href="https://pypi.org/project/superlocalmemory/"><img src="https://img.shields.io/pypi/v/superlocalmemory?style=for-the-badge&logo=pypi&logoColor=white" alt="PyPI"/></a>
   <a href="https://www.npmjs.com/package/superlocalmemory"><img src="https://img.shields.io/npm/v/superlocalmemory?style=for-the-badge&logo=npm&logoColor=white" alt="npm"/></a>
   <a href="https://www.gnu.org/licenses/agpl-3.0"><img src="https://img.shields.io/badge/License-AGPL_v3-blue.svg?style=for-the-badge" alt="AGPL v3"/></a>
@@ -125,18 +126,24 @@ Dynamic: license-file
 <details>
 <summary><strong>What's New in V3.6 — Optimize: SKIP, SHRINK, DISCOUNT, REMEMBER</strong> (click to expand)</summary>
 
-> V3.6 is the only local-first layer that SKIPS repeat LLM calls (cache: 100% saved), SHRINKS prompts 60-95% (compress: extractive + LLMLingua-2), and DISCOUNTS prefix costs (align: native KV-cache) — and remembers everything — in one install. **Your first cache hit pays for the install time. Hours of coding on repeat, minimal API cost.**
+> V3.6 is the only local-first layer that SKIPS repeat LLM calls (cache: 100% on a hit), SHRINKS tool outputs and injected context (compress: lossless-by-default, opt-in LLMLingua-2), and DISCOUNTS prefix costs (align: native KV-cache) — and remembers everything — in one install.
+>
+> **v3.6.11 "Optimize Everywhere":** Three surfaces. **Proxy** (Surface A) — full-turn cache + compress on transport; needs `ANTHROPIC_BASE_URL`, shrinks the context window. **MCP tools** (Surface B) — `slm_compress`, `slm_retrieve`, `slm_cache_set`, `slm_cache_get`, `slm_optimize_stats`; no proxy, no window shrink, works on any Claude subscription. **Skill** (Surface C) — `slm-optimize` installs in `~/.claude/skills/`; zero-config auto-compress for large tool outputs and CLAUDE.md. No proxy, full 1M window. [See Three Surfaces →](#three-surfaces-proxy--mcp-tools--skill)
+>
+> **v3.6.10:** cache and compression are now **independent runtime switches** (cache-only, compress-only, both, or neither — toggle live from the dashboard, no restart). Compression was rebuilt to be **lossless by default** (the old string/array/code truncation is gone); aggressive mode adds LLMLingua-2 for **prose only** — never code, numbers, structured data, or the current turn.
 
 ### The Three Levers
 
 | Lever | Mechanism | Saving | Off by default? |
 |-------|-----------|:------:|:---------------:|
-| **Cache** | Skip repeat calls — exact-match SQLite lookup, vCache-gated semantic (opt-in) | **100% on a hit** (input + output) | Cache ON, Semantic OFF |
-| **Compress** | Shrink prompts — extractive JSON/code (lossless) + LLMLingua-2 prose (opt-in) | **60–95% on a miss** (input only) | Safe mode ON, Aggressive OFF |
+| **Cache** | Skip repeat calls — exact-match SQLite lookup (zero false hits), vCache-gated semantic (opt-in) | **100% on a hit** (input + output) | Cache ON, Semantic OFF |
+| **Compress** | Shrink prompts — **safe = lossless** normalization; **aggressive = LLMLingua-2 prose only** (opt-in) | Safe: small + lossless · Aggressive: large on prose | Safe mode, Aggressive OFF |
 | **Align** | Stabilize prefix — maximize provider prefix-cache discounts | **Lossless extra** | ON when compression is ON |
 
 **Memory** (v3.5's existing engine) runs in parallel — it shapes *what is in* the prompt (relevant facts); Optimize decides *whether and how* it is sent.
 
+> **Independent at runtime:** enable caching only, compression only, both, or neither — from the dashboard Optimize tab, applied live (no restart). Each AI client can also get its own memory identity over HTTP MCP via `http://127.0.0.1:8765/mcp/{agent_id}`.
+
 ### Quick Start
 
 ```bash
@@ -152,7 +159,7 @@ slm wrap claude
 |:--------|:-------------|
 | `slm optimize status\|on\|off\|savings` | Master Optimize control + savings report (USD/INR/tokens) |
 | `slm cache status\|clear\|invalidate\|ttl\|semantic` | Cache sub-control — exact + semantic tiers |
-| `slm compress status\|mode\|code\|prose\|ccr\|align` | Compression control — per-channel toggles |
+| `slm compress status\|mode\|prose` | Compression control — safe (lossless) / aggressive (LLMLingua-2 prose) |
 | `slm proxy [--port] [--provider]` | Start the interception proxy (port 8765) |
 | `slm wrap <agent>` | Proxy-activate an agent — one command to start saving |
 | `slm help-optimize [topic]` | Full developer reference + per-agent setup recipes |
@@ -208,6 +215,57 @@ Full docs:
 
 ---
 
+## Three Surfaces: Proxy · MCP Tools · Skill
+
+v3.6.11 delivers one engine across **three ways in** — choose the surface that fits your setup:
+
+| Surface | How you use it | Requires proxy? | Window effect | Cache scope |
+|---------|---------------|:---------------:|:-------------:|-------------|
+| **A — Proxy** | `slm wrap claude` or `ANTHROPIC_BASE_URL=http://127.0.0.1:8765` | **Yes** | Shrinks (proxy intercepts full context) | Full-turn cache — every Claude call |
+| **B — MCP tools** | Add 5 tools to MCP config; call `slm_compress`, `slm_cache_set/get` | **No** | **Preserved** (full 1M) | Results you explicitly route through SLM |
+| **C — Skill** | Copy `skills/slm-optimize/SKILL.md` → `~/.claude/skills/` | **No** | **Preserved** (full 1M) | Auto-applied by the agent per skill rules |
+
+**How to choose:**
+- On a **metered API** (pay-per-token) and want to cache every call → **Proxy (A)**
+- On a **Pro/Max/Team subscription** or any plan where you can't or won't run a proxy → **MCP tools (B)** or **Skill (C)**
+- Want zero configuration → **Skill (C)**: install once, auto-compresses CLAUDE.md and large outputs
+- Want agent-controlled caching of repeated file reads and tool outputs → **MCP tools (B)**
+
+**The hard constraint:** The primary Claude conversation turn cannot be cached without a proxy — the MCP/skill path caches results you explicitly route through SLM (tool outputs, file reads, sub-model calls).
+
+### MCP Tools Setup (Surface B)
+
+Add to your `claude_desktop_config.json` or IDE MCP config alongside your existing SLM entry:
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
+      "command": "slm",
+      "args": ["mcp"]
+    }
+  }
+}
+```
+
+The 5 optimize tools (`slm_compress`, `slm_retrieve`, `slm_cache_set`, `slm_cache_get`, `slm_optimize_stats`) are included automatically from v3.6.11+. Verify with `slm_optimize_stats()`.
+
+### Skill Setup (Surface C)
+
+```bash
+mkdir -p ~/.claude/skills/slm-optimize
+cp $(pip show superlocalmemory | grep Location | awk '{print $2}')/superlocalmemory/skills/slm-optimize/SKILL.md \
+   ~/.claude/skills/slm-optimize/SKILL.md
+```
+
+Then reference in your `CLAUDE.md`:
+```markdown
+## Context Management
+Use the `slm-optimize` skill to compress large outputs and cache repeated reads.
+```
+
+---
+
 <details>
 <summary><strong>What's New in V3.3 — The Living Brain Evolves</strong> (click to expand)</summary>
 
@@ -384,6 +442,7 @@ No manual commands. No data loss. Zero downtime.
 
 | Version | Codename | Key Features |
 |---|---|---|
+| **v3.6.11** | Optimize Everywhere | **Three surfaces** — Proxy (A: full-turn cache), MCP tools (B: `slm_compress`/`slm_retrieve`/`slm_cache_set`/`slm_cache_get`/`slm_optimize_stats` — proxy-free, 1M window), Skill (C: `slm-optimize` zero-config). `CacheDB.get_value()` (pure KV lookup). 23 new tests. Links: [Three Surfaces →](#three-surfaces-proxy--mcp-tools--skill) · [docs/optimize-overview.md](docs/optimize-overview.md) |
 | **v3.6.0** | Optimize | **Cache** (skip repeat calls, 100% on hit) · **Compress** (shrink prompts 60-95%) · **Align** (KV-cache stabilization) · `slm optimize\|cache\|compress\|proxy\|wrap` CLI · Live savings dashboard (USD/INR/tokens) · Hot-reload config · Safe defaults · Links: [docs/optimize-overview.md](docs/optimize-overview.md) · [V3.6 Wiki](https://github.com/qualixar/superlocalmemory/wiki/V3.6-Overview) |
 | **v3.5.0** | Scale-Ready + Context Injection v2 | CozoDB/LanceDB migration, 6-channel recall <1s, Core Memory Block, BM25→FTS5, context injection v2, score normalization |
 | **v3.4.5** | Scale-Ready (foundation) | Tiered storage (active/warm/cold), graph pruning, BackendOrchestrator scaffolding, CozoDB + LanceDB init + migration code (read path wired in v3.5.0) |

package/src/superlocalmemory.egg-info/SOURCES.txt

@@ -271,6 +271,7 @@ src/superlocalmemory/mcp/__init__.py
 src/superlocalmemory/mcp/_daemon_proxy.py
 src/superlocalmemory/mcp/_pool_adapter.py
 src/superlocalmemory/mcp/_stdin_guard.py
+src/superlocalmemory/mcp/agent_context.py
 src/superlocalmemory/mcp/resources.py
 src/superlocalmemory/mcp/server.py
 src/superlocalmemory/mcp/shared.py
@@ -282,6 +283,7 @@ src/superlocalmemory/mcp/tools_core.py
 src/superlocalmemory/mcp/tools_evolution.py
 src/superlocalmemory/mcp/tools_learning.py
 src/superlocalmemory/mcp/tools_mesh.py
+src/superlocalmemory/mcp/tools_optimize.py
 src/superlocalmemory/mcp/tools_v28.py
 src/superlocalmemory/mcp/tools_v3.py
 src/superlocalmemory/mcp/tools_v33.py
@@ -309,8 +311,6 @@ src/superlocalmemory/optimize/cache/stampede.py
 src/superlocalmemory/optimize/compress/__init__.py
 src/superlocalmemory/optimize/compress/align.py
 src/superlocalmemory/optimize/compress/ccr.py
-src/superlocalmemory/optimize/compress/extractive_code.py
-src/superlocalmemory/optimize/compress/extractive_json.py
 src/superlocalmemory/optimize/compress/prose_llmlingua.py
 src/superlocalmemory/optimize/compress/router.py
 src/superlocalmemory/optimize/config/__init__.py
@@ -325,6 +325,7 @@ src/superlocalmemory/optimize/metrics/persistence.py
 src/superlocalmemory/optimize/proxy/__init__.py
 src/superlocalmemory/optimize/proxy/_helpers.py
 src/superlocalmemory/optimize/proxy/anthropic_surface.py
+src/superlocalmemory/optimize/proxy/capture.py
 src/superlocalmemory/optimize/proxy/gemini_surface.py
 src/superlocalmemory/optimize/proxy/lifecycle.py
 src/superlocalmemory/optimize/proxy/openai_surface.py

package/src/superlocalmemory.egg-info/requires.txt

@@ -29,6 +29,7 @@ huggingface_hub==0.36.2
 torch==2.11.0
 scikit-learn==1.8.0
 sqlite-vec==0.1.9
+llmlingua==0.2.2
 
 [dev]
 pytest>=8.0