release(llamaindex): v0.1.3

hindsight-docs/src/pages/changelog/integrations/llamaindex.md

@@ -10,6 +10,12 @@ For the source code, see [`hindsight-integrations/llamaindex`](https://github.co
 
 ← [Back to main changelog](/changelog)
 
+## [0.1.3](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.3)
+
+**Bug Fixes**
+
+- Fixed LlamaIndex integration issues with document IDs, the memory API, and ReAct trace handling to improve reliability and correctness. ([`d93dfea8`](https://github.com/vectorize-io/hindsight/commit/d93dfea8))
+
 ## [0.1.2](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.2)
 
 **Features**

hindsight-integrations/llamaindex/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hindsight-llamaindex"
-version = "0.1.2"
+version = "0.1.3"
 description = "LlamaIndex integration for Hindsight - persistent memory for AI agents"
 readme = "README.md"
 requires-python = ">=3.10"

skills/hindsight-docs/references/changelog/integrations/llamaindex.md

@@ -10,6 +10,12 @@ For the source code, see [`hindsight-integrations/llamaindex`](https://github.co
 
 ← [Back to main changelog](../index.md)
 
+## [0.1.3](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.3)
+
+**Bug Fixes**
+
+- Fixed LlamaIndex integration issues with document IDs, the memory API, and ReAct trace handling to improve reliability and correctness. ([`d93dfea8`](https://github.com/vectorize-io/hindsight/commit/d93dfea8))
+
 ## [0.1.2](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.2)
 
 **Features**

skills/hindsight-docs/references/developer/configuration.md

@@ -464,6 +464,7 @@ Supported OpenAI embedding dimensions:
 | `HINDSIGHT_API_RERANKER_LITELLM_MAX_TOKENS_PER_DOC` | Truncate documents to this many tokens before sending to the reranker (applies to both `litellm` and `litellm-sdk`). Use for models with small context windows (e.g. set to `900` for a 1024-token limit model). Unset by default (no truncation). | - |
 | `HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY` | ZeroEntropy API key for reranking | - |
 | `HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL` | ZeroEntropy rerank model (`zerank-2`, `zerank-2-small`) | `zerank-2` |
+| `HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL` | Custom base URL for ZeroEntropy-compatible API (e.g., mock server, proxy, or self-hosted deployment) | `https://api.zeroentropy.dev` |
 | `HINDSIGHT_API_RERANKER_FLASHRANK_MODEL` | FlashRank model for fast CPU-based reranking | `ms-marco-MiniLM-L-12-v2` |
 | `HINDSIGHT_API_RERANKER_FLASHRANK_CACHE_DIR` | Cache directory for FlashRank models | System default |
 | `HINDSIGHT_API_RERANKER_JINA_MLX_MODEL_PATH` | Local path to downloaded `jina-reranker-v3-mlx` model (auto-downloads from HuggingFace if unset) | - |
@@ -498,6 +499,7 @@ export HINDSIGHT_API_RERANKER_COHERE_BASE_URL=https://your-azure-cohere-endpoint
 export HINDSIGHT_API_RERANKER_PROVIDER=zeroentropy
 export HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY=your-api-key
 export HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL=zerank-2  # or zerank-2-small
+# export HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL=https://your-custom-endpoint.com  # optional
 
 # LiteLLM proxy - unified gateway for multiple reranking providers (requires running LiteLLM proxy server)
 export HINDSIGHT_API_RERANKER_PROVIDER=litellm

skills/hindsight-docs/references/sdks/integrations/llamaindex.md

@@ -37,8 +37,8 @@ async def main():
         mission="Track user preferences and project context",
     )
 
-    agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o"), memory=memory)
+    agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o"))
-    response = await agent.run("Remember that I prefer dark mode")
+    response = await agent.run("Remember that I prefer dark mode", memory=memory)
     print(response)
 
 asyncio.run(main())
@@ -48,8 +48,8 @@ asyncio.run(main())
 
 | Event | What Happens |
 |-------|-------------|
-| Agent receives input | `get(input)` recalls relevant memories from Hindsight, prepends as system message |
+| Agent receives input | `aget(input)` recalls relevant memories from Hindsight, prepends as system message |
-| Agent produces output | `put(message)` retains the message to Hindsight for future recall |
+| Agent produces output | `aput(message)` retains the message to Hindsight for future recall |
 | New session starts | Previous memories are available via recall; local chat buffer starts empty |
 
 ### `HindsightMemory.from_client()`
@@ -236,7 +236,10 @@ tools = create_hindsight_tools(
     include_reflect=True,   # agent can still explicitly reflect
 )
 
-agent = ReActAgent(tools=tools, llm=llm, memory=memory)
+agent = ReActAgent(tools=tools, llm=llm)
+
+# Pass memory to run()
+response = await agent.run("What should I prioritize?", memory=memory)
 ```
 
 ## Requirements