fix several issues

Author: fswair

.agents/skills/codex-auth-helper/SKILL.md

@@ -155,7 +155,7 @@ This helper is usually upstream of the adapter, not a replacement for it.
 
 ### Build a Codex-backed `pydantic-ai` model
 
-Use `create_codex_responses_model(...)`.
+Use `create_codex_responses_model(...)` and pass explicit `instructions=...`.
 
 ### Build a lower-level client first
 
@@ -164,7 +164,8 @@ Use `create_codex_async_openai(...)` when you need the transport/client object e
 ### Build a LangChain model
 
 Use `create_codex_chat_openai(...)` when the upstream runtime is LangChain or LangGraph and you
-want the Responses API path instead of hand-wiring `langchain-openai`.
+want the Responses API path instead of hand-wiring `langchain-openai`. Pass explicit
+`instructions=...` here too.
 
 ### Debug refresh behavior
 

.agents/skills/codex-auth-helper/examples/codex_chat_openai_graph.py

@@ -19,7 +19,13 @@ def describe_codex_surface() -> str:
 
 
 graph = create_agent(
-    model=create_codex_chat_openai(MODEL_NAME),
+    model=create_codex_chat_openai(
+        MODEL_NAME,
+        instructions=(
+            "You are a helpful coding assistant. "
+            "Explain concrete workspace observations and use tools when helpful."
+        ),
+    ),
     tools=[describe_codex_surface],
     name="codex-chat-openai-graph",
 )

.agents/skills/codex-auth-helper/examples/codex_responses_agent.py

@@ -9,11 +9,14 @@
 MODEL_NAME = os.getenv("CODEX_MODEL", "gpt-5.4")
 
 agent = Agent(
-    create_codex_responses_model(MODEL_NAME),
-    name="codex-responses-agent",
-    instructions=(
-        "You are a concise coding assistant. Ask for clarification when the task is underspecified."
+    create_codex_responses_model(
+        MODEL_NAME,
+        instructions=(
+            "You are a concise coding assistant. "
+            "Ask for clarification when the task is underspecified."
+        ),
     ),
+    name="codex-responses-agent",
 )
 
 

.gitignore

@@ -96,3 +96,6 @@ scripts/check_releases.py
 connect*.py
 expose*.py
 CHANGELOG
+/.acprouter-state
+/.deepagents-graph
+/.workspace-graph

VERSION

@@ -1 +1 @@
-1.0.0
+0.9.1

docs/bridges.md

@@ -106,8 +106,6 @@ ACP Kit models those callable shapes locally and passes them through the public
 
 That means:
 
-- bridge extension code should import history-processor aliases from
-  `pydantic_acp`, not from `pydantic_ai._history_processor`
 - the adapter is no longer directly coupled to upstream private
   history-processor imports
 

docs/examples/deepagents.md

@@ -8,6 +8,7 @@ This example is the maintained DeepAgents-facing showcase for `langchain-acp`.
 
 It demonstrates:
 
+- a Codex-backed `ChatOpenAI` model created through `codex-auth-helper`
 - wiring a DeepAgents graph through `langchain-acp`
 - `DeepAgentsCompatibilityBridge`
 - `DeepAgentsProjectionMap`
@@ -30,6 +31,12 @@ Run it:
 uv run python -m examples.langchain.deepagents_graph
 ```
 
+Required local state:
+
+```text
+~/.codex/auth.json
+```
+
 If you want the module-level compiled graph directly, the example exports `graph` when `deepagents` is installed:
 
 ```bash

docs/examples/langchain-codex.md

@@ -10,6 +10,15 @@ This example demonstrates the helper-to-adapter path for LangChain:
 - `langchain.agents.create_agent(...)` owns the graph
 - `langchain-acp` exposes that graph through ACP
 
+The model factory call must pass `instructions=` explicitly:
+
+```python
+model = create_codex_chat_openai(
+    "gpt-5.4",
+    instructions="You are a helpful coding assistant.",
+)
+```
+
 Run it:
 
 ```bash
@@ -22,6 +31,12 @@ Required local state:
 ~/.codex/auth.json
 ```
 
+Override the default model when needed:
+
+```bash
+CODEX_MODEL=gpt-5.4-mini uv run python -m examples.langchain.codex_graph
+```
+
 If you have not logged in yet:
 
 ```bash

docs/examples/langchain-workspace.md

@@ -8,6 +8,7 @@ This example is the maintained plain-LangChain showcase.
 
 It demonstrates:
 
+- a Codex-backed `ChatOpenAI` model created through `codex-auth-helper`
 - a module-level `graph`, `config`, and `main()`
 - a session-aware `graph_from_session(...)` factory
 - `acpkit run examples.langchain.workspace_graph:graph`
@@ -21,6 +22,18 @@ Run it:
 uv run python -m examples.langchain.workspace_graph
 ```
 
+Required local state:
+
+```text
+~/.codex/auth.json
+```
+
+Override the default model when needed:
+
+```bash
+CODEX_MODEL=gpt-5.4-mini uv run python -m examples.langchain.workspace_graph
+```
+
 Or expose the graph directly through the root CLI:
 
 ```bash

docs/getting-started/langchain-quickstart.md

@@ -29,7 +29,10 @@ from codex_auth_helper import create_codex_chat_openai
 from langchain.agents import create_agent
 
 graph = create_agent(
-    model=create_codex_chat_openai("gpt-5.4"),
+    model=create_codex_chat_openai(
+        "gpt-5.4",
+        instructions="Answer directly and keep responses short.",
+    ),
     tools=[],
     name="codex-graph",
 )
@@ -38,6 +41,9 @@ graph = create_agent(
 That path keeps the model on the OpenAI Responses API while reusing
 `~/.codex/auth.json` and the helper's refresh flow.
 
+`create_codex_chat_openai(...)` requires `instructions=`. Pass them at model
+construction time, including inside `graph_factory=` flows.
+
 ## 2. Expose The Graph Through ACP
 
 Wrap the graph with `run_acp(...)`: