This is an automated email from the ASF dual-hosted git repository.
Lee-W pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push:
new 10529542d48 Update retired model ids and fill doc gaps in common.ai
provider docs (#69711)
10529542d48 is described below
commit 10529542d482c6293f454748fa87cd46d93c0aef
Author: Wei Lee <[email protected]>
AuthorDate: Tue Jul 14 23:08:02 2026 +0800
Update retired model ids and fill doc gaps in common.ai provider docs
(#69711)
---
providers/common/ai/docs/connections/mcp.rst | 8 ++---
.../common/ai/docs/connections/pydantic_ai.rst | 11 ++++--
providers/common/ai/docs/hitl_review.rst | 6 ++--
providers/common/ai/docs/hooks/index.rst | 4 +++
providers/common/ai/docs/hooks/langchain.rst | 2 +-
providers/common/ai/docs/operators/agent.rst | 39 +++++++++++++++++-----
providers/common/ai/docs/operators/index.rst | 2 +-
.../ai/docs/operators/llamaindex_retrieval.rst | 2 +-
providers/common/ai/docs/operators/llm.rst | 12 +++----
providers/common/ai/docs/operators/llm_branch.rst | 4 +--
.../common/ai/docs/operators/llm_file_analysis.rst | 15 +++++++--
providers/common/ai/docs/quickstart.rst | 4 +--
providers/common/ai/docs/retry_policies.rst | 5 +--
providers/common/ai/docs/toolsets.rst | 18 +++++-----
providers/common/ai/provider.yaml | 4 +--
.../providers/common/ai/get_provider_info.py | 4 +--
.../providers/common/ai/hooks/pydantic_ai.py | 6 ++--
.../tests/unit/common/ai/hooks/test_pydantic_ai.py | 34 +++++++++----------
18 files changed, 111 insertions(+), 69 deletions(-)
diff --git a/providers/common/ai/docs/connections/mcp.rst
b/providers/common/ai/docs/connections/mcp.rst
index 07be621e9a1..a324bbdffe6 100644
--- a/providers/common/ai/docs/connections/mcp.rst
+++ b/providers/common/ai/docs/connections/mcp.rst
@@ -150,9 +150,9 @@ into task logs) without ever being written to the
connection:
token_provider=mint_snowflake_jwt,
)
-``token_provider`` is resolved in DAG code (it is a Python callable, not a
stored
+``token_provider`` is resolved in Dag code (it is a Python callable, not a
stored
connection field), so the signing key stays in your environment and is never
baked
-into the serialized DAG.
+into the serialized Dag.
Secrets in stdio subprocess environments
-----------------------------------------
@@ -193,5 +193,5 @@ managed as its own Airflow connection:
:start-after: [START howto_toolset_mcp_env_provider]
:end-before: [END howto_toolset_mcp_env_provider]
-Like ``token_provider``, ``env_provider`` is resolved in DAG code, so the
secret is
-fetched at task-execution time and never baked into the serialized DAG.
+Like ``token_provider``, ``env_provider`` is resolved in Dag code, so the
secret is
+fetched at task-execution time and never baked into the serialized Dag.
diff --git a/providers/common/ai/docs/connections/pydantic_ai.rst
b/providers/common/ai/docs/connections/pydantic_ai.rst
index a7aa0c85a50..a77fce140a6 100644
--- a/providers/common/ai/docs/connections/pydantic_ai.rst
+++ b/providers/common/ai/docs/connections/pydantic_ai.rst
@@ -38,9 +38,14 @@ Model
dedicated input in the connection form (via ``conn-fields``) and stores its
value in ``extra["model"]``.
- Examples: ``openai:gpt-5.3``, ``anthropic:claude-sonnet-4-20250514``,
+ Examples: ``openai:gpt-5.6-sol``, ``anthropic:claude-sonnet-5``,
``bedrock:us.anthropic.claude-opus-4-6-v1:0``, ``google:gemini-2.0-flash``
+ See `Anthropic's models overview
<https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison>`__
+ for the current list of Claude model IDs across the Claude API, Amazon
Bedrock, and Google Cloud.
+ See `OpenAI's models reference
<https://developers.openai.com/api/docs/models/all>`__
+ for the current list of OpenAI model IDs.
+
The model can also be overridden at the hook/operator level via the
``model_id`` parameter.
@@ -64,7 +69,7 @@ Extra (JSON, optional)
.. code-block:: json
- {"model": "openai:gpt-5.3"}
+ {"model": "openai:gpt-5.6-sol"}
When using the UI, the "Model" field above writes to this same location
automatically.
@@ -79,7 +84,7 @@ Examples
{
"conn_type": "pydanticai",
"password": "sk-...",
- "extra": "{\"model\": \"openai:gpt-5.3\"}"
+ "extra": "{\"model\": \"openai:gpt-5.6-sol\"}"
}
**Anthropic**
diff --git a/providers/common/ai/docs/hitl_review.rst
b/providers/common/ai/docs/hitl_review.rst
index 26735622e96..699d51c5e56 100644
--- a/providers/common/ai/docs/hitl_review.rst
+++ b/providers/common/ai/docs/hitl_review.rst
@@ -131,7 +131,7 @@ instance page. Use the **HITL Review** extra link on the
task instance, or
navigate to
``/dags/{dag_id}/runs/{run_id}/tasks/{task_id}/plugin/hitl-review``.
-**Example DAG**
+**Example Dag**
.. exampleinclude::
/../../ai/src/airflow/providers/common/ai/example_dags/example_agent.py
:language: python
@@ -150,8 +150,8 @@ The plugin exposes a FastAPI app at ``/hitl-review``. Base
URL:
**Common query parameters** (where applicable):
-- ``dag_id`` — DAG ID.
-- ``run_id`` — DAG run ID.
+- ``dag_id`` — Dag ID.
+- ``run_id`` — Dag run ID.
- ``task_id`` — Task ID.
- ``map_index`` — Map index for mapped tasks. Use ``-1`` for non-mapped tasks
or index for dynamic mapping.
diff --git a/providers/common/ai/docs/hooks/index.rst
b/providers/common/ai/docs/hooks/index.rst
index 2786cd1b0ce..13455cdf896 100644
--- a/providers/common/ai/docs/hooks/index.rst
+++ b/providers/common/ai/docs/hooks/index.rst
@@ -47,6 +47,10 @@ Choosing a hook
by default). For non-OpenAI vendors, pass a pre-built
``BaseEmbedding`` / ``LLM`` instance straight to the operator and
bypass the hook.
+ * - :class:`~airflow.providers.common.ai.hooks.mcp.MCPHook`
+ - Backs ``MCPToolset`` (see :doc:`../toolsets`) for agent tasks that call
+ tools on a remote MCP server. Configure the connection via
+ :doc:`../connections/mcp`.
Hook guides
-----------
diff --git a/providers/common/ai/docs/hooks/langchain.rst
b/providers/common/ai/docs/hooks/langchain.rst
index e7ee2e95d7d..5485f39ab2a 100644
--- a/providers/common/ai/docs/hooks/langchain.rst
+++ b/providers/common/ai/docs/hooks/langchain.rst
@@ -57,7 +57,7 @@ Any model identifier accepted by
works out of the box. Common identifiers:
- ``openai:gpt-4o``, ``openai:gpt-4o-mini`` -- requires ``langchain-openai``
-- ``anthropic:claude-3-7-sonnet`` -- requires ``langchain-anthropic``
+- ``anthropic:claude-sonnet-5`` -- requires ``langchain-anthropic``
- ``groq:llama-3.3-70b-versatile`` -- requires ``langchain-groq``
- ``mistralai:mistral-large-latest`` -- requires ``langchain-mistralai``
- ``ollama:llama3`` -- requires ``langchain-ollama`` (point ``host`` at the
Ollama URL)
diff --git a/providers/common/ai/docs/operators/agent.rst
b/providers/common/ai/docs/operators/agent.rst
index 63cf575c131..578513469e2 100644
--- a/providers/common/ai/docs/operators/agent.rst
+++ b/providers/common/ai/docs/operators/agent.rst
@@ -125,11 +125,11 @@ attribute access (``result.field``).
The declared ``output_type`` (and any ``BaseModel`` reachable from
``Union``/``Optional``/``list`` shapes) is registered for XCom deserialization
by
-the worker when it loads the DAG, before any task runs. The Pydantic class must
+the worker when it loads the Dag, before any task runs. The Pydantic class must
be defined at **module scope** and bound to an attribute matching its
-``__name__``. Same-DAG downstream tasks need no configuration. The UI's XCom
+``__name__``. Same-Dag downstream tasks need no configuration. The UI's XCom
viewer renders the value via the ``stringify`` path (no configuration needed;
-see the ``LLMOperator`` guide for the exact representation). Cross-DAG
+see the ``LLMOperator`` guide for the exact representation). Cross-Dag
``xcom_pull`` consumers still need the class ``qualname`` added to
``[core] allowed_deserialization_classes``.
@@ -309,9 +309,9 @@ invalidate cached responses -- clear the cache to force a
fully fresh run.
After the run, a single INFO summary line reports how many steps were
replayed vs executed fresh. Per-step detail is available at DEBUG level.
-The cache is scoped to a single task instance (DAG id, run id, task id, and
+The cache is scoped to a single task instance (Dag id, run id, task id, and
map index), so each run replays only its own steps. On Airflow >= 3.3 the cache
-lives in the task state store and is removed when the DAG run is cleaned up; on
+lives in the task state store and is removed when the Dag run is cleaned up; on
Airflow < 3.3 it is a JSON file named ``{dag_id}_{task_id}_{run_id}.json``
(with
``_{map_index}`` appended for mapped tasks) under the configured
``durable_cache_path``.
@@ -319,8 +319,8 @@ Airflow < 3.3 it is a JSON file named
``{dag_id}_{task_id}_{run_id}.json`` (with
.. note::
Runs that fail permanently (exhaust all retries) leave their cached steps
- behind. These do not affect future DAG runs (each run is scoped
separately).
- On Airflow >= 3.3 they are reclaimed when the DAG run is removed; on
Airflow
+ behind. These do not affect future Dag runs (each run is scoped
separately).
+ On Airflow >= 3.3 they are reclaimed when the Dag run is removed; on
Airflow
< 3.3 the orphaned JSON files consume storage until cleaned up, so add a
lifecycle policy to the storage backend or remove them periodically.
@@ -380,7 +380,7 @@ Capabilities compose with toolsets -- pydantic-ai merges
tools from both.
``agent_params`` is a templated field, which Airflow serializes by calling
``str()`` on values it doesn't natively understand. Capability instances
- are not yet round-trip-safe through DAG serialization, so the examples
+ are not yet round-trip-safe through Dag serialization, so the examples
below construct them inside the ``@dag`` function -- not at module level.
First-class ``capabilities=`` support on ``AgentOperator`` (with proper
serializer hooks) is tracked as a follow-up.
@@ -489,6 +489,29 @@ Parameters
When set, the post-run transcript is pushed to XCom under the key
``message_history`` for the next run to resume. Default ``None``
(single-turn).
See `Multi-turn Sessions`_.
+- ``serialize_output``: If ``True`` and ``output_type`` is a Pydantic
+ ``BaseModel`` subclass, the model instance is dumped to a ``dict`` via
+ ``model_dump()`` before being pushed to XCom. Default ``False`` -- the
+ Pydantic instance flows through XCom unchanged. Set to ``True`` when a
+ downstream consumer needs the dict shape.
+
+**HITL Review parameters** (requires the ``hitl_review`` plugin -- see
+:doc:`../hitl_review` for the full review workflow):
+
+- ``enable_hitl_review``: When ``True``, the operator enters an iterative
+ review loop after the first generation. A human reviewer can approve,
+ reject, or request changes via the plugin's REST API at ``/hitl-review``
+ or through the **HITL Review** extra link on the task instance. Default
+ ``False``.
+- ``max_hitl_iterations``: Maximum outputs shown to the reviewer (1 = initial
+ output). When the reviewer requests changes at iteration >= this limit, the
+ task fails with ``HITLMaxIterationsError`` without calling the LLM. E.g. 5
+ allows changes at iterations 1-4. Default ``5``.
+- ``hitl_timeout``: Maximum wall-clock time to wait for all review rounds
+ combined. ``None`` means no timeout (the operator blocks until a terminal
+ action).
+- ``hitl_poll_interval``: Seconds between XCom polls while waiting for a
+ human response. Default ``10``.
Logging
diff --git a/providers/common/ai/docs/operators/index.rst
b/providers/common/ai/docs/operators/index.rst
index 7eaf414fe3a..e8b043bf374 100644
--- a/providers/common/ai/docs/operators/index.rst
+++ b/providers/common/ai/docs/operators/index.rst
@@ -62,7 +62,7 @@ via an ``output_type`` Pydantic model.
**LLMFileAnalysisOperator / @task.llm_file_analysis** — stateless, single-turn
file analysis.
Use this when the prompt should reason over file contents or multimodal
attachments already chosen
-by the DAG author. The operator resolves files via ``ObjectStoragePath`` and
keeps the interaction
+by the Dag author. The operator resolves files via ``ObjectStoragePath`` and
keeps the interaction
read-only.
**AgentOperator / @task.agent** — multi-turn tool-calling loop. The model
decides which tools to
diff --git a/providers/common/ai/docs/operators/llamaindex_retrieval.rst
b/providers/common/ai/docs/operators/llamaindex_retrieval.rst
index 6e0793604ab..3f064a2b825 100644
--- a/providers/common/ai/docs/operators/llamaindex_retrieval.rst
+++ b/providers/common/ai/docs/operators/llamaindex_retrieval.rst
@@ -40,7 +40,7 @@ Basic usage
:start-after: [START howto_hook_llamaindex_retrieve]
:end-before: [END howto_hook_llamaindex_retrieve]
-``query`` is templated, so DAG-run params, XCom, and Variables all flow
+``query`` is templated, so Dag-run params, XCom, and Variables all flow
through cleanly.
Cloud-persisted indexes
diff --git a/providers/common/ai/docs/operators/llm.rst
b/providers/common/ai/docs/operators/llm.rst
index 28187d1c183..426a2573206 100644
--- a/providers/common/ai/docs/operators/llm.rst
+++ b/providers/common/ai/docs/operators/llm.rst
@@ -51,7 +51,7 @@ so downstream tasks can type-hint the class directly
The declared ``output_type`` (and any ``BaseModel`` reachable from
``Union``/``Optional``/``list`` shapes) is registered for XCom deserialization
by
-the worker when it loads the DAG, before any task runs -- so no edit to
+the worker when it loads the Dag, before any task runs -- so no edit to
``[core] allowed_deserialization_classes`` is needed. The Pydantic class must
be
defined at **module scope** and bound to an attribute matching its
``__name__``;
classes nested inside a function or ``@dag``-decorated body, parameterized
@@ -69,9 +69,9 @@ warning at worker startup and the value fails to deserialize
at the consumer.
:start-after: [START howto_operator_llm_structured]
:end-before: [END howto_operator_llm_structured]
-Registration covers downstream tasks in the **same DAG**: every worker walks
the
-loaded DAG's tasks at startup and registers each declared class, so it also
works
-for mapped producers (``.expand(...)``) and for workers that load DAGs from a
+Registration covers downstream tasks in the **same Dag**: every worker walks
the
+loaded Dag's tasks at startup and registers each declared class, so it also
works
+for mapped producers (``.expand(...)``) and for workers that load Dags from a
cache that bypasses operator construction.
The Airflow UI's XCom viewer renders Pydantic instances via the
@@ -80,8 +80,8 @@ The Airflow UI's XCom viewer renders Pydantic instances via
the
allow-list. It is not pretty (no field-by-field rendering today), but the value
shows up; no configuration is required.
-The remaining gap is **cross-DAG** ``xcom_pull`` -- a task in a different DAG
-that pulls this XCom only parses its own DAG file, not the producer's, so the
+The remaining gap is **cross-Dag** ``xcom_pull`` -- a task in a different Dag
+that pulls this XCom only parses its own Dag file, not the producer's, so the
class is not auto-registered. Add the class qualified name to
``[core] allowed_deserialization_classes`` (or a glob that matches it) to make
that pattern work.
diff --git a/providers/common/ai/docs/operators/llm_branch.rst
b/providers/common/ai/docs/operators/llm_branch.rst
index 3c9e6490823..42db970427a 100644
--- a/providers/common/ai/docs/operators/llm_branch.rst
+++ b/providers/common/ai/docs/operators/llm_branch.rst
@@ -24,7 +24,7 @@ Use
:class:`~airflow.providers.common.ai.operators.llm_branch.LLMBranchOperator`
for LLM-driven branching — where the LLM decides which downstream task(s) to
execute.
-The operator discovers downstream tasks automatically from the DAG topology
+The operator discovers downstream tasks automatically from the Dag topology
and presents them to the LLM as a constrained enum via pydantic-ai structured
output. No text parsing or manual validation is needed.
@@ -80,7 +80,7 @@ How It Works
At execution time, the operator:
-1. Reads ``self.downstream_task_ids`` from the DAG topology.
+1. Reads ``self.downstream_task_ids`` from the Dag topology.
2. Creates a dynamic ``Enum`` with one member per downstream task ID.
3. Passes that enum as ``output_type`` to ``pydantic-ai``, constraining the
LLM to
valid task IDs only.
diff --git a/providers/common/ai/docs/operators/llm_file_analysis.rst
b/providers/common/ai/docs/operators/llm_file_analysis.rst
index 5e38851ef86..8b2733ab05a 100644
--- a/providers/common/ai/docs/operators/llm_file_analysis.rst
+++ b/providers/common/ai/docs/operators/llm_file_analysis.rst
@@ -80,12 +80,12 @@ back from the LLM instead of a plain string. The model
instance is pushed to
XCom unchanged so downstream tasks can type-hint the class directly. The
declared ``output_type`` (and any ``BaseModel`` reachable from
``Union``/``Optional``/``list`` shapes) is registered for deserialization by
the
-worker when it loads the DAG. Define the class at **module scope** and bind it
to
+worker when it loads the Dag. Define the class at **module scope** and bind it
to
an attribute matching its ``__name__``: nested-in-function and
dynamically-built
classes cannot be re-imported, so they are skipped at worker startup and fail
to
-deserialize at the consumer. Same-DAG downstream tasks need no configuration;
the
+deserialize at the consumer. Same-Dag downstream tasks need no configuration;
the
UI XCom viewer renders the value
-via the ``stringify`` path (no configuration needed). Cross-DAG ``xcom_pull``
+via the ``stringify`` path (no configuration needed). Cross-Dag ``xcom_pull``
consumers still need the class ``qualname`` added to
``[core] allowed_deserialization_classes`` (see the ``LLMOperator`` guide for
details).
@@ -140,6 +140,15 @@ Parameters
``BaseModel`` for structured output.
- ``agent_params``: Additional keyword arguments passed to the pydantic-ai
``Agent`` constructor (e.g. ``retries``, ``model_settings``).
+- ``serialize_output``: If ``True`` and ``output_type`` is a Pydantic
+ ``BaseModel`` subclass, the model instance is dumped to a ``dict`` via
+ ``model_dump()`` before being pushed to XCom. Default ``False`` -- the
+ Pydantic instance flows through XCom unchanged. Set to ``True`` when a
+ downstream consumer needs the dict shape.
+
+This operator also inherits ``LLMOperator``'s HITL review parameters --
+``require_approval``, ``approval_timeout``, and ``allow_modifications`` -- see
+:doc:`llm` for details.
Supported Formats
-----------------
diff --git a/providers/common/ai/docs/quickstart.rst
b/providers/common/ai/docs/quickstart.rst
index ec3d07941eb..450932e3cb2 100644
--- a/providers/common/ai/docs/quickstart.rst
+++ b/providers/common/ai/docs/quickstart.rst
@@ -49,12 +49,12 @@ for the full reference, including providers that
don't need an API key (Bedrock, Vertex AI).
The quickest way to set one up is an environment variable. Replace
-``openai:gpt-5.3`` with a model you have access to and ``sk-...`` with your
+``openai:gpt-5.6-sol`` with a model you have access to and ``sk-...`` with your
actual API key:
.. code-block:: bash
- export AIRFLOW_CONN_PYDANTICAI_DEFAULT='{"conn_type": "pydanticai",
"password": "sk-...", "extra": {"model": "openai:gpt-5.3"}}'
+ export AIRFLOW_CONN_PYDANTICAI_DEFAULT='{"conn_type": "pydanticai",
"password": "sk-...", "extra": {"model": "openai:gpt-5.6-sol"}}'
Or add it through the Airflow UI (``Admin > Connections``) or the CLI
(``airflow connections add``).
diff --git a/providers/common/ai/docs/retry_policies.rst
b/providers/common/ai/docs/retry_policies.rst
index 036bc8e5908..8456b1262aa 100644
--- a/providers/common/ai/docs/retry_policies.rst
+++ b/providers/common/ai/docs/retry_policies.rst
@@ -18,7 +18,8 @@
LLM Retry Policies
===================
-.. versionadded:: 3.3.0
+.. note::
+ Requires Airflow >= 3.3.0.
The ``LLMRetryPolicy`` uses an LLM to classify task errors and make intelligent
retry decisions. It works with any LLM provider supported by pydantic-ai
@@ -40,7 +41,7 @@ Setup
- **Connection Id**: ``pydanticai_default``
- **Connection Type**: ``Pydantic AI``
- **Password**: Your API key
- - **Extra**: ``{"model": "anthropic:claude-haiku-4-5-20251001"}``
+ - **Extra**: ``{"model": "anthropic:claude-haiku-4-5"}``
Usage
-----
diff --git a/providers/common/ai/docs/toolsets.rst
b/providers/common/ai/docs/toolsets.rst
index d97a8fece2b..faa407d6676 100644
--- a/providers/common/ai/docs/toolsets.rst
+++ b/providers/common/ai/docs/toolsets.rst
@@ -364,7 +364,7 @@ For prototyping or when you want full PydanticAI control,
you can pass
)
This works because PydanticAI's ``MCPToolset`` implements ``AbstractToolset``.
-The tradeoff: URLs and credentials are hardcoded in DAG code instead of being
+The tradeoff: URLs and credentials are hardcoded in Dag code instead of being
managed through Airflow connections and secret backends.
@@ -392,8 +392,8 @@ extra to use it:
Each source is a local directory or a connection-resolved
:class:`~airflow.providers.common.ai.skills.GitSkills`. Sources are resolved
when
-the agent enters the toolset, on the worker -- never while the DAG processor
-parses the file -- so a Git token is never baked into the serialized DAG, and
+the agent enters the toolset, on the worker -- never while the Dag processor
+parses the file -- so a Git token is never baked into the serialized Dag, and
cloned repositories are removed when the run ends.
A local directory of ``SKILL.md`` bundles:
@@ -425,7 +425,7 @@ need strict isolation.
Skill bundles can contain scripts that the agent may run on the worker via
the ``run_skill_script`` tool. For a remote source, anyone who can modify
the
- repository can introduce code that executes on your worker, outside DAG
+ repository can introduce code that executes on your worker, outside Dag
review and versioning. Point ``GitSkills`` at a trusted repository, pin
``branch`` to a trusted ref, and treat skill contents as code that runs in
your environment.
@@ -544,8 +544,8 @@ before it runs. If no registered tool can read the
environment, the
filesystem, or other connections, the model cannot reach them, regardless of
what the prompt instructs it to do.
-This is what "untrusted" means in this context. The DAG file itself is
-author-written and trusted, exactly like any other DAG. What is untrusted is
+This is what "untrusted" means in this context. The Dag file itself is
+author-written and trusted, exactly like any other Dag. What is untrusted is
the model's *output*: the tool-call requests and text it generates. That output
is confined to your registered tools and bounded by the tool-call budget. An
agent cannot create a new connection, read another connection's credentials, or
@@ -570,13 +570,13 @@ No single layer is sufficient — they work together.
- What it does
- What it does NOT do
* - **Airflow Connections**
- - Credentials are stored in Airflow's secret backend, never in DAG code.
+ - Credentials are stored in Airflow's secret backend, never in Dag code.
The LLM agent cannot see API keys or database passwords.
- Does not prevent the agent from using the connection to access data
the connection has access to.
* - **HookToolset: explicit allow-list**
- Only methods listed in ``allowed_methods`` are exposed as tools.
- Auto-discovery is not supported. Methods are validated at DAG parse
+ Auto-discovery is not supported. Methods are validated at Dag parse
time.
- Does not restrict what arguments the agent passes to allowed methods.
* - **SQLToolset: read-only by default**
@@ -719,7 +719,7 @@ Production Checklist
Before deploying an agent task to production:
1. **Connection credentials**: Use Airflow's secret backend. Never hardcode
- API keys in DAG files.
+ API keys in Dag files.
2. **Database permissions**: Create a dedicated database user with minimum
required grants. Don't reuse the admin connection.
3. **Tool allow-list**: Review ``allowed_methods`` / ``allowed_tables``. The
diff --git a/providers/common/ai/provider.yaml
b/providers/common/ai/provider.yaml
index 0d63e6f4202..e5c26e60a55 100644
--- a/providers/common/ai/provider.yaml
+++ b/providers/common/ai/provider.yaml
@@ -158,7 +158,7 @@ connection-types:
conn-fields:
model:
label: Model
- description: "Model in provider:name format (e.g.
anthropic:claude-sonnet-4-20250514, openai:gpt-5)"
+ description: "Model in provider:name format (e.g.
anthropic:claude-sonnet-5, openai:gpt-5)"
schema:
type:
- string
@@ -388,7 +388,7 @@ connection-types:
description: >
Chat model in provider:name format dispatched via
langchain.chat_models.init_chat_model
- (e.g. openai:gpt-4o, anthropic:claude-3-7-sonnet).
+ (e.g. openai:gpt-4o, anthropic:claude-sonnet-5).
schema:
type:
- string
diff --git
a/providers/common/ai/src/airflow/providers/common/ai/get_provider_info.py
b/providers/common/ai/src/airflow/providers/common/ai/get_provider_info.py
index 4f31d62e84e..89d96737d94 100644
--- a/providers/common/ai/src/airflow/providers/common/ai/get_provider_info.py
+++ b/providers/common/ai/src/airflow/providers/common/ai/get_provider_info.py
@@ -128,7 +128,7 @@ def get_provider_info():
"conn-fields": {
"model": {
"label": "Model",
- "description": "Model in provider:name format (e.g.
anthropic:claude-sonnet-4-20250514, openai:gpt-5)",
+ "description": "Model in provider:name format (e.g.
anthropic:claude-sonnet-5, openai:gpt-5)",
"schema": {"type": ["string", "null"]},
}
},
@@ -305,7 +305,7 @@ def get_provider_info():
"conn-fields": {
"model": {
"label": "Chat Model",
- "description": "Chat model in provider:name format
dispatched via langchain.chat_models.init_chat_model (e.g. openai:gpt-4o,
anthropic:claude-3-7-sonnet).\n",
+ "description": "Chat model in provider:name format
dispatched via langchain.chat_models.init_chat_model (e.g. openai:gpt-4o,
anthropic:claude-sonnet-5).\n",
"schema": {"type": ["string", "null"]},
},
"embed_model": {
diff --git
a/providers/common/ai/src/airflow/providers/common/ai/hooks/pydantic_ai.py
b/providers/common/ai/src/airflow/providers/common/ai/hooks/pydantic_ai.py
index c46f974a59c..8f4e71a9a69 100644
--- a/providers/common/ai/src/airflow/providers/common/ai/hooks/pydantic_ai.py
+++ b/providers/common/ai/src/airflow/providers/common/ai/hooks/pydantic_ai.py
@@ -53,10 +53,10 @@ class PydanticAIHook(BaseHook):
Connection fields:
- **password**: API key
- **host**: Base URL (optional, e.g. ``https://api.openai.com/v1``)
- - **extra** JSON: ``{"model": "openai:gpt-5.3"}``
+ - **extra** JSON: ``{"model": "openai:gpt-5.6-sol"}``
:param llm_conn_id: Airflow connection ID for the LLM provider.
- :param model_id: Model identifier in ``provider:model`` format (e.g.
``"openai:gpt-5.3"``).
+ :param model_id: Model identifier in ``provider:model`` format (e.g.
``"openai:gpt-5.6-sol"``).
Overrides the model stored in the connection's extra field.
"""
@@ -90,7 +90,7 @@ class PydanticAIHook(BaseHook):
"relabeling": {"password": "API Key"},
"placeholders": {
"host": "https://api.openai.com/v1 (optional, for custom
endpoints / Ollama)",
- "extra": '{"model": "openai:gpt-5.3"}',
+ "extra": '{"model": "openai:gpt-5.6-sol"}',
},
}
diff --git a/providers/common/ai/tests/unit/common/ai/hooks/test_pydantic_ai.py
b/providers/common/ai/tests/unit/common/ai/hooks/test_pydantic_ai.py
index 4d7baf9b4e7..0290da3c133 100644
--- a/providers/common/ai/tests/unit/common/ai/hooks/test_pydantic_ai.py
+++ b/providers/common/ai/tests/unit/common/ai/hooks/test_pydantic_ai.py
@@ -41,9 +41,9 @@ class TestPydanticAIHookInit:
assert hook.model_id is None
def test_custom_conn_id(self):
- hook = PydanticAIHook(llm_conn_id="my_llm", model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="my_llm",
model_id="openai:gpt-5.6-sol")
assert hook.llm_conn_id == "my_llm"
- assert hook.model_id == "openai:gpt-5.3"
+ assert hook.model_id == "openai:gpt-5.6-sol"
def test_azure_hook_uses_own_default_conn_name(self):
"""Subclass default_conn_name is used, not the base class value."""
@@ -69,7 +69,7 @@ class TestPydanticAIHookGetConn:
mock_provider = MagicMock()
mock_infer_provider_class.return_value =
MagicMock(return_value=mock_provider)
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(
conn_id="test_conn",
conn_type="pydanticai",
@@ -82,7 +82,7 @@ class TestPydanticAIHookGetConn:
assert result is mock_model
mock_infer_model.assert_called_once()
call_args = mock_infer_model.call_args
- assert call_args[0][0] == "openai:gpt-5.3"
+ assert call_args[0][0] == "openai:gpt-5.6-sol"
# provider_factory should be passed as keyword arg
assert "provider_factory" in call_args[1]
@@ -120,7 +120,7 @@ class TestPydanticAIHookGetConn:
mock_infer_model.return_value = MagicMock(spec=Model)
mock_infer_provider_class.return_value =
MagicMock(return_value=MagicMock())
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(
conn_id="test_conn",
conn_type="pydanticai",
@@ -131,7 +131,7 @@ class TestPydanticAIHookGetConn:
hook.get_conn()
# model_id param takes priority over extra
- assert mock_infer_model.call_args[0][0] == "openai:gpt-5.3"
+ assert mock_infer_model.call_args[0][0] == "openai:gpt-5.6-sol"
def test_get_conn_raises_when_no_model(self):
hook = PydanticAIHook(llm_conn_id="test_conn")
@@ -188,7 +188,7 @@ class TestPydanticAIHookGetConn:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
with patch.object(hook, "get_connection", return_value=conn):
first = hook.get_conn()
@@ -205,7 +205,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(
conn_id="test_conn",
conn_type="pydanticai",
@@ -225,7 +225,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(
conn_id="test_conn",
conn_type="pydanticai",
@@ -245,7 +245,7 @@ class TestPydanticAIHookCreateAgent:
)
def test_create_agent_without_instructions_or_spec_file_raises(self):
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
with pytest.raises(ValueError, match="instructions is required"):
hook.create_agent()
@@ -256,7 +256,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
with patch.object(hook, "get_connection", return_value=conn):
hook.create_agent(spec_file="/path/to/agent.yaml")
@@ -293,7 +293,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
spec_path = Path("/path/to/agent.yaml")
with patch.object(hook, "get_connection", return_value=conn):
@@ -314,7 +314,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
with patch.object(hook, "get_connection", return_value=conn):
hook.create_agent(
@@ -336,7 +336,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
with patch.object(hook, "get_connection", return_value=conn):
hook.create_agent(output_type=dict,
spec_file="/path/to/agent.yaml")
@@ -354,7 +354,7 @@ class TestPydanticAIHookCreateAgent:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(conn_id="test_conn", conn_type="pydanticai")
with patch.object(hook, "get_connection", return_value=conn):
hook.create_agent(
@@ -377,7 +377,7 @@ class TestPydanticAIHookCreateAgentInstrumentation:
@staticmethod
def _hook() -> PydanticAIHook:
- return PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ return PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
@patch("airflow.providers.common.ai.hooks.pydantic_ai.genai_instrumentation_settings")
def test_instrument_set_when_settings_returned(self, mock_settings):
@@ -430,7 +430,7 @@ class TestPydanticAIHookTestConnection:
mock_model = MagicMock(spec=Model)
mock_infer_model.return_value = mock_model
- hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.3")
+ hook = PydanticAIHook(llm_conn_id="test_conn",
model_id="openai:gpt-5.6-sol")
conn = Connection(
conn_id="test_conn",
conn_type="pydanticai",
