feat: implemented langchain adapter and added TrimConfig

.eslintignore

@@ -1,3 +1,4 @@
 dist
 node_modules
 examples
+locales

.github/copilot-instructions.md

@@ -11,7 +11,7 @@
 - **Installed Size**: ~106MB (including all dependencies in node_modules)
 - **Languages**: TypeScript (primary), JavaScript (compiled output)
 - **Target Runtime**: Node.js (CommonJS modules)
-- **Framework**: Model-agnostic, no AI framework dependencies
+- **Framework**: Model-agnostic core; optional adapters (LangChain)
 - **Package Manager**: pnpm (preferred) or npm (fallback)
 - **Testing**: vitest
 - **Linting**: ESLint with TypeScript support
@@ -52,7 +52,7 @@
    npm run test
    # Runs all vitest tests
    # Duration: ~5-10 seconds
-   # Should show: "Test Files 2 passed (2), Tests 7 passed (7)"
+   # Should show: "Test Files 3 passed (3), Tests 16 passed (16)"
    ```
 
 4. **Format Code**
@@ -97,20 +97,24 @@ The repository uses GitHub Actions CI that runs:
 
 ```
 /
-├── src/                      # TypeScript source code
-│   ├── index.ts             # Main exports (TrimCompressor, SummarizeCompressor, interfaces)
-│   ├── interfaces.ts        # Core type definitions (SlimContextMessage, etc.)
-│   └── strategies/          # Compression strategy implementations
-│       ├── trim.ts          # TrimCompressor: keeps first + last N messages
-│       └── summarize.ts     # SummarizeCompressor: AI-powered summarization
-├── tests/                   # vitest test files
-│   ├── trim.test.ts        # Tests for TrimCompressor
-│   └── summarize.test.ts   # Tests for SummarizeCompressor
-├── examples/               # Documentation-only examples (not code)
-│   ├── OPENAI_EXAMPLE.md  # Copy-paste OpenAI integration
-│   └── LANGCHAIN_EXAMPLE.md # Copy-paste LangChain integration
-├── dist/                   # Compiled JavaScript output (generated)
-└── package.json           # npm package configuration
+├── src/                           # TypeScript source code
+│   ├── index.ts                  # Main exports (trim, summarize, interfaces, adapters namespace)
+│   ├── interfaces.ts             # Core type definitions (SlimContextMessage, etc.)
+│   ├── adapters/                 # Integration adapters (optional)
+│   │   └── langchain.ts          # LangChain adapter + helpers (compressLangChainHistory, toSlimModel)
+│   └── strategies/               # Compression strategy implementations
+│       ├── trim.ts               # TrimCompressor: keeps first + last N messages
+│       └── summarize.ts          # SummarizeCompressor: AI-powered summarization
+├── tests/                        # vitest test files
+│   ├── trim.test.ts             # Tests for TrimCompressor
+│   ├── summarize.test.ts        # Tests for SummarizeCompressor
+│   └── langchain.test.ts        # Tests for LangChain adapter + helper
+├── examples/                    # Documentation-only examples (not code)
+│   ├── OPENAI_EXAMPLE.md        # Copy-paste OpenAI integration
+│   ├── LANGCHAIN_EXAMPLE.md     # Copy-paste LangChain integration
+│   └── LANGCHAIN_COMPRESS_HISTORY.md # One-call compressLangChainHistory usage
+├── dist/                        # Compiled JavaScript output (generated)
+└── package.json                # npm package configuration
 ```
 
 ### Configuration Files
@@ -134,12 +138,13 @@ The repository uses GitHub Actions CI that runs:
 - **TrimCompressor**: Simple strategy keeping first (system) message + last N-1 messages
 - **SummarizeCompressor**: AI-powered strategy that summarizes middle conversations when exceeding maxMessages
 
-**Framework Independence**: No dependencies on OpenAI, LangChain, or other AI frameworks. Users implement the minimal `SlimContextChatModel` interface to connect their preferred model.
+**Framework Independence**: Core library has no framework dependencies. An optional LangChain adapter is provided for convenience; core remains BYOM.
 
 ### Dependencies and Build Artifacts
 
-- **Production**: Zero dependencies (framework-agnostic design)
+- **Production**: Zero runtime dependencies (framework-agnostic design)
 - **Development**: TypeScript, ESLint, Prettier, vitest, various type definitions
+- **Optional peer**: `@langchain/core` (only if using the LangChain adapter). The adapter is exported under `slimcontext/adapters/langchain` and as a `langchain` namespace from the root export.
 - **Ignored Files**: dist/, node_modules/, examples/ (linting), \*.tgz
 - **Distributed Files**: Only dist/ directory (compiled JS + .d.ts files)
 
@@ -149,8 +154,8 @@ The repository uses GitHub Actions CI that runs:
 
 ```bash
 npm run test
-# Expects: 7 tests across 2 files, all passing
-# Tests cover both TrimCompressor and SummarizeCompressor functionality
+# Expects: ~16 tests across 3 files, all passing
+# Tests cover TrimCompressor, SummarizeCompressor, and the LangChain adapter/helper
 ```
 
 ### Manual Verification Steps
@@ -181,6 +186,17 @@ npm run test
 - **src/interfaces.ts**: Core type definitions - modify for interface changes
 - **src/strategies/trim.ts**: Simple compression logic
 - **src/strategies/summarize.ts**: AI-powered compression with alignment logic
+- **src/adapters/langchain.ts**: LangChain adapter and helpers (`compressLangChainHistory`, `toSlimModel`, conversions)
+
+### Adapters
+
+- LangChain adapter import options:
+  - Recommended (works across module systems): `import * as langchain from 'slimcontext/adapters/langchain'`
+  - Root namespace (available as a property on the root export; usage differs by module system):
+    - CommonJS: `const { langchain } = require('slimcontext')`
+    - ESM/TypeScript: `import * as slim from 'slimcontext'; const { langchain } = slim;`
+  - Note: `import { langchain } from 'slimcontext'` may not work in all environments due to CJS/ESM interop. Prefer one of the patterns above.
+  - Includes a one-call history helper: `compressLangChainHistory(history, options)`
 
 ---
 

CHANGELOG.md

@@ -4,7 +4,29 @@ All notable changes to this project will be documented in this file.
 
 The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
 
-## [Unreleased] - 2025-08-24
+## [2.1.0] - 2025-08-27
+
+### Added
+
+- LangChain adapter under `src/adapters/langchain.ts` with helpers:
+  - `extractContent`, `roleFromMessageType`, `baseToSlim`, `slimToLangChain`
+  - `toSlimModel(llm)` wrapper to use LangChain `BaseChatModel` with `SummarizeCompressor`.
+  - `compressLangChainHistory(history, options)` high-level helper for one-call compression on `BaseMessage[]`.
+- Tests for adapter behavior in `tests/langchain.test.ts`.
+- Examples:
+  - `examples/LANGCHAIN_EXAMPLE.md`: adapting a LangChain model to `SlimContextChatModel`.
+  - `examples/LANGCHAIN_COMPRESS_HISTORY.md`: using `compressLangChainHistory` directly.
+
+### Changed
+
+- README updated with a LangChain adapter section and one-call usage sample.
+
+### Notes
+
+- The adapter treats LangChain `tool` messages as `assistant` during compression.
+- `@langchain/core` is an optional peer dependency; only needed if you use the adapter.
+
+## [2.0.0] - 2025-08-24
 
 ### Breaking
 

README.md

@@ -7,13 +7,14 @@ Lightweight, model-agnostic chat history compression utilities for AI assistants
 ## Examples
 
 - OpenAI: see `examples/OPENAI_EXAMPLE.md` (copy-paste snippet; BYOM, no deps added here).
-- LangChain: see `examples/LANGCHAIN_EXAMPLE.md` (adapts a LangChain chat model to `SlimContextChatModel`).
+- LangChain: see `examples/LANGCHAIN_EXAMPLE.md` and `examples/LANGCHAIN_COMPRESS_HISTORY.md`.
 
 ## Features
 
 - Trim strategy: keep the first (system) message and last N messages.
 - Summarize strategy: summarize the middle portion using your own chat model.
 - Framework agnostic: plug in any model wrapper implementing a minimal `invoke()` interface.
+- Optional LangChain adapter with a one-call helper for compressing histories.
 
 ## Installation
 
@@ -113,8 +114,48 @@ if (history.length > 50) {
 
 ## Example Integration
 
-See `examples/LANGCHAIN_EXAMPLE.md` for a LangChain-style example.
-See `examples/OPENAI_EXAMPLE.md` for an OpenAI example (copy-paste snippet).
+- See `examples/OPENAI_EXAMPLE.md` for an OpenAI copy-paste snippet.
+- See `examples/LANGCHAIN_EXAMPLE.md` for a LangChain-style integration.
+- See `examples/LANGCHAIN_COMPRESS_HISTORY.md` for a one-call LangChain history compression helper.
+
+## Adapters
+
+### LangChain
+
+If you already use LangChain chat models, you can use the built-in adapter. It’s exported in two ways:
+
+- Namespaced: `import { langchain } from 'slimcontext'`
+- Direct path: `import * as langchain from 'slimcontext/adapters/langchain'`
+
+Common helpers:
+
+- `compressLangChainHistory(history, options)` – one-call compression for LangChain `BaseMessage[]`.
+- `toSlimModel(llm)` – wrap a LangChain `BaseChatModel` for `SummarizeCompressor`.
+
+Example (one-call history compression):
+
+```ts
+import { AIMessage, HumanMessage, SystemMessage } from '@langchain/core/messages';
+import { ChatOpenAI } from '@langchain/openai';
+import { langchain } from 'slimcontext';
+
+const lc = new ChatOpenAI({ model: 'gpt-4o-mini', temperature: 0 });
+
+const history = [
+  new SystemMessage('You are helpful.'),
+  new HumanMessage('Please summarize the discussion so far.'),
+  new AIMessage('Certainly!'),
+  // ...more messages
+];
+
+const compact = await langchain.compressLangChainHistory(history, {
+  strategy: 'summarize',
+  llm: lc, // BaseChatModel
+  maxMessages: 12,
+});
+```
+
+See `examples/LANGCHAIN_COMPRESS_HISTORY.md` for a fuller copy-paste example.
 
 ## API
 

examples/LANGCHAIN_COMPRESS_HISTORY.md

@@ -0,0 +1,42 @@
+# LangChain one-call history compression
+
+This example shows how to use `compressLangChainHistory` to compress a LangChain message history in a single call.
+
+```ts
+import { AIMessage, HumanMessage, SystemMessage } from '@langchain/core/messages';
+import { ChatOpenAI } from '@langchain/openai';
+import { langchain } from 'slimcontext';
+
+// 1) Create your LangChain chat model (any BaseChatModel works)
+const llm = new ChatOpenAI({ model: 'gpt-4o-mini', temperature: 0 });
+
+// 2) Build your existing LangChain-compatible history
+const history = [
+  new SystemMessage('You are a helpful assistant.'),
+  new HumanMessage('Hi! Help me plan a 3-day trip to Tokyo.'),
+  new AIMessage('Sure, what are your interests?'),
+  // ... many more messages
+];
+
+// 3) Compress with either summarize (default) or trim strategy
+const compact = await langchain.compressLangChainHistory(history, {
+  strategy: 'summarize',
+  llm, // pass your BaseChatModel
+  maxMessages: 12, // target total messages after compression (system + summary + recent)
+});
+
+// Alternatively, use trimming without an LLM:
+const trimmed = await langchain.compressLangChainHistory(history, {
+  strategy: 'trim',
+  messagesToKeep: 8,
+});
+
+console.log('Original size:', history.length);
+console.log('Summarized size:', compact.length);
+console.log('Trimmed size:', trimmed.length);
+```
+
+Notes
+
+- `@langchain/core` is an optional peer dependency. Install it only if you use the adapter.
+- `maxMessages` must be at least 4 for summarize (system + summary + 2 recent).

package.json

@@ -1,9 +1,13 @@
 {
   "name": "slimcontext",
-  "version": "2.0.1",
+  "version": "2.1.0",
   "description": "Lightweight, model-agnostic chat history compression (trim + summarize) for AI assistants.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
+  "exports": {
+    ".": "./dist/index.js",
+    "./adapters/langchain": "./dist/adapters/langchain.js"
+  },
   "files": [
     "dist"
   ],
@@ -37,6 +41,14 @@
   },
   "homepage": "https://github.com/Agentailor/slimcontext#readme",
   "packageManager": "pnpm@10.14.0",
+  "peerDependencies": {
+    "@langchain/core": ">=0.3.71 <1"
+  },
+  "peerDependenciesMeta": {
+    "@langchain/core": {
+      "optional": true
+    }
+  },
   "devDependencies": {
     "eslint": "^8.57.0",
     "@types/node": "^24.3.0",
@@ -47,6 +59,7 @@
     "eslint-plugin-unused-imports": "^4.2.0",
     "prettier": "^3.6.2",
     "typescript": "^5.9.2",
-    "vitest": "^3.2.4"
+    "vitest": "^3.2.4",
+    "@langchain/core": "^0.3.71"
   }
 }