agentomatic 0.1.1__tar.gz → 0.3.0__tar.gz

{agentomatic-0.1.1 → agentomatic-0.3.0}/CHANGELOG.md

@@ -1,6 +1,36 @@
 # CHANGELOG
 
 
+## v0.3.0 (2026-06-14)
+
+### Features
+
+- Implement memory management, platform features, and router updates
+  ([`5cf8aa8`](https://github.com/UnicoLab/agentomatic/commit/5cf8aa88ef750e2fa443948981aad2f1f9f1f9c4))
+
+
+## v0.2.0 (2026-06-14)
+
+### Documentation
+
+- Add telemetry and feedback correlation notes for A/B testing
+  ([`2c27a86`](https://github.com/UnicoLab/agentomatic/commit/2c27a86ac83b44a022e5d002d88316953f01ab35))
+
+### Features
+
+- Implement advanced platform features (HITL, checkpointer, structured output, fork, A/B routing,
+  fallbacks, hooks) and update documentation
+  ([`c1a55c3`](https://github.com/UnicoLab/agentomatic/commit/c1a55c39b1efd24084f1453946df27a830d3d7ec))
+
+- Increase core test coverage over 85% and enhance homepage aesthetics
+  ([`98f28f5`](https://github.com/UnicoLab/agentomatic/commit/98f28f56308b7540d642149aa2a7edc20b2eeafb))
+
+### Testing
+
+- Enhance unit test coverage for sqlalchemy store, sync checkpointers, and structured fallbacks
+  ([`91ab042`](https://github.com/UnicoLab/agentomatic/commit/91ab04254a623fb4fbd108303265ad8d4b3aeba5))
+
+
 ## v0.1.1 (2026-06-13)
 
 ### Bug Fixes

{agentomatic-0.1.1 → agentomatic-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentomatic
-Version: 0.1.1
+Version: 0.3.0
 Summary: Drop agents, not code — zero-code multi-agent API platform framework
 Project-URL: Homepage, https://github.com/UnicoLab/agentomatic
 Project-URL: Documentation, https://unicolab.github.io/agentomatic
@@ -132,7 +132,7 @@ Create production-ready AI agent APIs with auto-discovery, auto-routing, streami
 | Feature | Description |
 |---|---|
 | 🔍 **Auto-Discovery** | Drop an agent folder → endpoints appear automatically |
-| 🚀 **12+ Endpoints Per Agent** | invoke, stream, chat, A2A, health, config, threads |
+| 🚀 **25+ Endpoints Per Agent** | invoke, stream, chat, A2A, health, config, threads, memory, feedback |
 | 🗄️ **Pluggable Storage** | MemoryStore, SQLAlchemy, or bring your own |
 | 🔐 **Middleware Pipeline** | Auth, rate limiting, Prometheus metrics — all toggleable |
 | 🎨 **Built-in Debug UI** | ChatGPT-like interface via Chainlit |
@@ -143,6 +143,17 @@ Create production-ready AI agent APIs with auto-discovery, auto-routing, streami
 | ⚡ **Prompt Optimizer** | DSPy-inspired prompt optimization (7 strategies) |
 | 🧪 **Data Synthesizer** | Auto-generate & augment eval datasets via LLM |
 | 📊 **HTML Reports** | SVG charts, prompt diffs, experiment tracking |
+| 🚦 **Human-in-the-Loop** | Suspend/resume execution with human approval gates |
+| 🌳 **Thread Lineage** | First-class parent/child tracking with ancestry traversal |
+| ⏰ **HITL TTL Expiry** | Auto-cleanup of stale suspended states (7-day default) |
+| 🛡️ **LLM Failover** | Multi-provider fallback chains with telemetry |
+| 🧬 **Thread Forking** | Clone conversations at any message index |
+| 🔀 **A/B Prompt Routing** | Weight-based prompt version selection |
+| 🪝 **State Hooks** | Before/after node interceptors for audit & telemetry |
+| 🧠 **Conversation Memory** | Automatic session + long-term memory with windowing |
+| 📝 **Auto-Summarization** | LLM-powered compression of long conversations |
+| 📋 **Thread CRUD** | Full thread lifecycle management (create/update/delete/clear) |
+| 💬 **Message Persistence** | Every turn auto-saved — history survives restarts |
 
 ## 🚀 Quick Start
 
@@ -317,6 +328,11 @@ Every agent gets 12+ endpoints automatically:
 | `GET` | `/api/v1/{agent}/card` | A2A agent card |
 | `POST` | `/api/v1/{agent}/a2a/tasks` | A2A task submission |
 | `GET` | `/api/v1/{agent}/threads` | List threads |
+| `POST` | `/api/v1/{agent}/threads/{id}/approve` | HITL: approve suspended state |
+| `POST` | `/api/v1/{agent}/threads/{id}/reject` | HITL: reject suspended state |
+| `GET` | `/api/v1/{agent}/threads/{id}/pending` | HITL: list pending approvals |
+| `POST` | `/api/v1/{agent}/threads/{id}/fork` | Fork thread at message index |
+| `GET` | `/api/v1/{agent}/threads/{id}/lineage` | Thread ancestry/descendant tree |
 | ... | ... | + config, prompts, thread messages |
 
 ## 🛠️ Development

{agentomatic-0.1.1 → agentomatic-0.3.0}/README.md

@@ -28,7 +28,7 @@ Create production-ready AI agent APIs with auto-discovery, auto-routing, streami
 | Feature | Description |
 |---|---|
 | 🔍 **Auto-Discovery** | Drop an agent folder → endpoints appear automatically |
-| 🚀 **12+ Endpoints Per Agent** | invoke, stream, chat, A2A, health, config, threads |
+| 🚀 **25+ Endpoints Per Agent** | invoke, stream, chat, A2A, health, config, threads, memory, feedback |
 | 🗄️ **Pluggable Storage** | MemoryStore, SQLAlchemy, or bring your own |
 | 🔐 **Middleware Pipeline** | Auth, rate limiting, Prometheus metrics — all toggleable |
 | 🎨 **Built-in Debug UI** | ChatGPT-like interface via Chainlit |
@@ -39,6 +39,17 @@ Create production-ready AI agent APIs with auto-discovery, auto-routing, streami
 | ⚡ **Prompt Optimizer** | DSPy-inspired prompt optimization (7 strategies) |
 | 🧪 **Data Synthesizer** | Auto-generate & augment eval datasets via LLM |
 | 📊 **HTML Reports** | SVG charts, prompt diffs, experiment tracking |
+| 🚦 **Human-in-the-Loop** | Suspend/resume execution with human approval gates |
+| 🌳 **Thread Lineage** | First-class parent/child tracking with ancestry traversal |
+| ⏰ **HITL TTL Expiry** | Auto-cleanup of stale suspended states (7-day default) |
+| 🛡️ **LLM Failover** | Multi-provider fallback chains with telemetry |
+| 🧬 **Thread Forking** | Clone conversations at any message index |
+| 🔀 **A/B Prompt Routing** | Weight-based prompt version selection |
+| 🪝 **State Hooks** | Before/after node interceptors for audit & telemetry |
+| 🧠 **Conversation Memory** | Automatic session + long-term memory with windowing |
+| 📝 **Auto-Summarization** | LLM-powered compression of long conversations |
+| 📋 **Thread CRUD** | Full thread lifecycle management (create/update/delete/clear) |
+| 💬 **Message Persistence** | Every turn auto-saved — history survives restarts |
 
 ## 🚀 Quick Start
 
@@ -213,6 +224,11 @@ Every agent gets 12+ endpoints automatically:
 | `GET` | `/api/v1/{agent}/card` | A2A agent card |
 | `POST` | `/api/v1/{agent}/a2a/tasks` | A2A task submission |
 | `GET` | `/api/v1/{agent}/threads` | List threads |
+| `POST` | `/api/v1/{agent}/threads/{id}/approve` | HITL: approve suspended state |
+| `POST` | `/api/v1/{agent}/threads/{id}/reject` | HITL: reject suspended state |
+| `GET` | `/api/v1/{agent}/threads/{id}/pending` | HITL: list pending approvals |
+| `POST` | `/api/v1/{agent}/threads/{id}/fork` | Fork thread at message index |
+| `GET` | `/api/v1/{agent}/threads/{id}/lineage` | Thread ancestry/descendant tree |
 | ... | ... | + config, prompts, thread messages |
 
 ## 🛠️ Development

{agentomatic-0.1.1 → agentomatic-0.3.0}/docs/guide/configuration.md

@@ -37,6 +37,8 @@ platform = AgentPlatform.from_folder(
     enable_metrics=True,
     enable_feedback=True,
     enable_telemetry=True,
+    max_history_messages=50,
+    summarize_after=30,
 )
 ```
 
@@ -62,9 +64,17 @@ platform = AgentPlatform.from_folder(
 
 ### 4. Storage Backend
 
-- **`store`** (type: `BaseStore | None`, default: `None`): Instance of a storage adapter (e.g. `MemoryStore` or `SQLAlchemyStore`) used to save message threads and rating logs.
+- **`store`** (type: `BaseStore | None`, default: `None`): Instance of a storage adapter (e.g. `MemoryStore` or `SQLAlchemyStore`) used to save message threads, conversation history, and rating logs.
 
-### 5. Security & Rate Limiting
+### 5. Memory & Conversation
+
+- **`max_history_messages`** (type: `int`, default: `50`): Maximum number of messages to load from the thread store into the agent's context window. When the conversation exceeds this limit, older messages are windowed out or summarised.
+- **`summarize_after`** (type: `int`, default: `30`): When the message count in a thread exceeds this threshold, older messages are automatically summarised using the configured LLM and prepended as a `[Conversation Summary]` system message.
+
+> [!TIP]
+> These values can also be overridden per-request using the `max_history` field on `AgentChatRequest`, giving frontends full control over how much context each invocation receives.
+
+### 6. Security & Rate Limiting
 
 - **`enable_auth`** (type: `bool`, default: `False`): If `True`, mounts Key Authentication middleware on all agent routes.
 - **`auth_api_key`** (type: `str`, default: `""`): The secret API key token required by clients when `enable_auth` is enabled.