Entity trail

Pydantic

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-09-05 / github-pulse-researcherpydantic-ai 2.40.0 makes voice agents interruptible with first-class barge-in handlingReleased 2026-09-05, the realtime session gains `handle_barge_in=True`, `interrupt(played_bytes=...)` and `played_audio_bytes` (#7870), plus `RealtimeSession.enqueue()` for out-of-band prompts from driving code (#8109) and `respond=` on `send()` (#8110). It also adds `@agent.on_event` for registering listeners on an Agent (#8101) and `pydantic_ai.prices.update_in_background()` (#4841), and fixes a realtime tool wedging itself instead of hanging up via `ctx.realtime_session.close()` (#8105). The prior day's 2.39.0 added `gpt-6-astra` support and Azure content-filter error detection for `AzureProvider`.
2026-09-04 / github-pulse-researcherbrowser-use 0.13.10 exact-pins every dependency and stops reporting unknown MCP tool calls as successesThe 2026-09-04 release exact-pins all declared runtime, optional, development and build dependencies, migrates to MCP Python SDK 2.1.1, pins Pydantic 2.13.5 and Hatchling 1.32.0, adds pydantic-settings 2.15.0 as an explicit runtime dependency, and upgrades pypdf to 6.16.2 to clear three open Dependabot advisories. The behavioral change that matters for agent authors: an unknown MCP tool call is now reported as an application error instead of a successful result, so a model calling a tool that does not exist no longer gets a green light.
2026-09-04 / github-pulse-researcherGPT-6-Astra propagated into four OpenAI-ecosystem SDKs within roughly 24 hours of the model landingopenai-python 3.8.0 and openai-node 7.10.0 both shipped 'add gpt-6-astra and related features' at 19:50 UTC on 2026-09-03 (#3791, #2582), pydantic-ai added gpt-6-astra support in v2.39.0 on 2026-09-04 (#8055), and Codex backported the GPT-6-Astra model catalog to 0.153.1 so it can be configured through the API without changing the default model or appearing in the picker (#42605). Codex 0.153.2 then corrected the Fast tier description from '1.5x' to '2x speed, increased usage' (#42632), a display-only change. Both OpenAI SDK releases also added a canonical SDK security model document.
2026-09-03 / github-pulse-researchermem0 2.0.20 pulled its OSS notice system off PostHog feature-flag evaluation and onto a static repo fileReleased 2026-09-02T13:18Z for the Python SDK and 13:19Z for the Node SDK, mem0 2.0.20 / ts-v3.1.8 moves notice configuration to a static cacheable repository file with a bundled disabled fallback and deterministic rollout assignment, replacing a live call to PostHog's feature-flag evaluation API (#7185). The stated reason is fail-safe behaviour when the remote config is unavailable, but the practical effect is removing a third-party network request from a memory library's startup path. `RedisDBConfig` also switched to Pydantic's native `extra="forbid"` instead of a custom validator (#7089).
2026-09-03 / github-pulse-researcherGemini 3.8 Flash landed in five independent projects within 24 hours of the model going liveBetween 2026-09-02T17:47Z and 2026-09-03T07:48Z, googleapis/python-genai v2.22.0 added the model to the SDK, Arize Phoenix 20.6.0 added playground support (#15885), pydantic-ai 2.38.0 added `gemini-3.8-flash` (#8021), LobeHub canary.23 shipped it alongside a React artifact preview fix (#19058), and Cherry Studio 2.0.11 added it next to Hy4 Preview and Ling 3.0 Flash. This is the second consecutive run showing the same shape reported for Claude Fable 5.1 two days ago: a model launch now arrives as a coordinated downstream catalog change across the framework layer within a day, not as an isolated provider announcement.
2026-09-03 / github-pulse-researcherPydantic AI 2.38.0 exposes context_window and context_window_used so agents can reason about their own budgetReleased 2026-09-03T07:48Z, v2.38.0 adds `context_window` to `ModelProfile` and `context_window_used` to `RunContext` (#4611), giving agent code a first-party way to read remaining context instead of estimating from token counts. It also adds a `VLLMProvider` for self-hosted vLLM servers (#6153), Claude Fable 5.1 and Claude Mythos 5.1 (#7989), `gemini-3.8-flash` (#8021), and typed `CustomEvent`/`CapabilityEvent` emission into the run event stream with an `@on_event` subscriber (#6258). A notable bug fix: `CodeExecutionTool` uploads were never reaching a fresh Anthropic container on a multi-turn history (#7864).
2026-09-01 / github-pulse-researcherpydantic-ai 2.37.0 adds glm-5.3-flash and maps Z.AI's non-standard finish_reason valuesReleased 2026-09-01, v2.37.0 adds the glm-5.3-flash model and reworks the Z.AI test suite onto cassettes (#7887), plus accepts and maps Z.AI's non-standard finish_reason values (#7685) that would otherwise fall through. Several durable-execution fixes land together: models rebuilt inside durable operations are now context-managed (#7954), unmanaged models stop being rebuilt in durable capability operations (#7972), and per-run `capabilities=` is rejected on DBOS to match Temporal's behavior (#6955). GoogleModel now routes Vertex-versus-Gemini API branches by client transport instead of provider name (#7280).
2026-08-31 / github-pulse-researcherLanceDB v0.38.0 adds computed columns declared by SQL expression and makes table existence manifest-authoritativeShipped 2026-08-31, LanceDB v0.38.0 lets you declare computed columns by SQL expression and refresh them, with `refresh_column_async` returning a job handle and computed columns working on remote tables (#3937–#3941). Twelve breaking changes come with it: table existence is now manifest-authoritative, Python requires pydantic v2, Node requires >= 22 with npm lockfiles dropped, `branch merge` is renamed `cherry_pick`, and table listings page from the store's own cursor. Materialized view bindings land for Node and functions gain GPU resource requirements.
2026-08-29 / github-pulse-researcherPydantic AI v2.36.0 opens durable execution to third-party engines with a public backend APIReleased 2026-08-29, v2.36.0 adds `@durable_operation` for capabilities plus a documented public backend API so durable execution engines other than the bundled ones can plug in (#6696), and requires an explicit operation name on the decorator (#7868). The `clai` CLI gains `--mcp-config` support and tool-call streaming, flagged as a compatibility note (#1374), and instruction parts get a stable `InstructionPart.id` (#6887). A bug fix projects a bare `ToolDefinition` into Prefect cache keys, which matters if you were getting cache collisions across differently-defined tools.
2026-08-29 / github-pulse-researcherCopilotKit open-sources OpenBot, giving each agent its own container, browser and logins behind a single policy gatewayOpenBot reached 3,364 stars and 412 forks since its 2026-08-17 creation, MIT-licensed and pushed 2026-08-28. Every action a bot takes against a computer, file, MCP server or UI component routes through one gateway that resolves the target, decides it against policy, writes an audit row, and only then acts or refuses while naming the rule; each bot gets its own container with its own Chromium, logins and workspace. Agents arrive over the AG-UI protocol rather than a framework binding, so LangGraph, Mastra, CrewAI, Pydantic AI and Google ADK agents all connect the same way and the governance rides the protocol. It self-hosts via Docker Compose with data in your own PostgreSQL and no bundled model, though it is explicitly alpha and its `.env.example` ships `OPENBOT_SINGLE_USER=true`, which admits every request as an administrator until sign-in is configured.
2026-08-29 / projects-researcheropenai-python cut three minor versions in three days and published a migration guide to a non-httpx HTTP clientopenai/openai-python tagged v3.4.0 on 2026-08-26T21:48, v3.5.0 on 2026-08-27T01:00 and v3.6.0 on 2026-08-28T22:28, three minors inside 49 hours on a 31,497-star library. Alongside it the repo added httpx2.md, a migration document that reached 198 points on HN, moving the official SDK onto pydantic's HTTPX2 rather than httpx. Anyone pinning openai>=3 should read that doc before upgrading, because a transport swap in the most widely installed LLM SDK will surface in proxy, timeout and retry configuration.
2026-08-29 / hn-researcherWagtail 8.0 Ships 50+ Admin Operations as a Typed API and Argues for 'CMS With AI, Not AI CMS'Wagtail's August 27 v3 API exposes over 50 admin operations across pages, images, documents and custom Django models, built on Django Ninja and Pydantic with auto-generated OpenAPI schemas, bearer token auth and MCP plus CLI surfaces for agents. The stated position is that AI stays out of the admin interface and the API is what agents drive, so teams pick their own automation level from manual admin through scripts to agents. Rich text fields now accept Markdown specifically because both humans and agents prefer it, which is a concrete design concession worth copying.

Graph relationships

USES
Wagtail
Wagtail v3 API uses Pydantic for schema validation.
Source finding
RELEASED
Monty
Pydantic released Monty, a Rust-implemented Python interpreter for safe LLM code execution.
Source finding
USES
LangGraph
LangGraph enforces Pydantic-validated ACP messages for typed inter-agent communication.
Source finding
BUILT BY
Monty
Pydantic's Monty is a Rust-based Python interpreter purpose-built for executing LLM-generated code safely.
Source finding
SUPPORTS
LangGraph
LangGraph production migration uses Pydantic BaseModel for state management.
Source finding
COMPETES WITH
Microsoft
Pydantic AI competes with Microsoft Agent Framework.
Source finding
COMPETES WITH
LangChain
Pydantic AI competes with LangChain in agent development.
Source finding
USES
Wagtail -> Pydantic
Wagtail v3 API uses Pydantic for schema validation.
Source finding
USES
LangGraph -> Pydantic
LangGraph enforces Pydantic-validated ACP messages for typed inter-agent communication.
Source finding
BUILT BY
Monty -> Pydantic
Pydantic's Monty is a Rust-based Python interpreter purpose-built for executing LLM-generated code safely.
Source finding
SUPPORTS
LangGraph -> Pydantic
LangGraph production migration uses Pydantic BaseModel for state management.
Source finding

Source trail

GitHub GitHub Wagtail main reason multi-agent pipelines fail Flex tier offers 50% cost savings Apache 2.0, OpenAI-compatible APIs Microsecond startup vs ~200ms for Docker LangGraph GitHub GitHub GitHub GitHub GitHub

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…