mirror of
https://github.com/pydantic/pydantic-ai-harness.git
synced 2026-07-21 10:55:35 +00:00
docs: point at the new per-capability pages in core's Capabilities section (#391)
Pydantic AI's docs restructure gives Capabilities a top-level section (/ai/capabilities/) with a page per built-in capability. Update all /ai/core-concepts/capabilities/ links accordingly, and make the core built-ins explicit in the 'What goes where?' breakdown — naming and linking web search, web fetch, image generation, compaction, tool search, on-demand loading, thinking, and MCP, plus the full built-in list on the Capabilities overview. Merge together with the pydantic-ai docs restructure release: the new /ai/capabilities/ URLs only exist once that release is synced to pydantic.dev.
This commit is contained in:
Douwe Maan
@@ -34,7 +34,7 @@ Before implementing or reviewing a capability change:
|
||||
1. Read `agent_docs/index.md`.
|
||||
2. Read the linked `agent_docs/` guide for the task.
|
||||
3. Read the public Pydantic AI docs for every integration point you touch:
|
||||
- capabilities: <https://pydantic.dev/docs/ai/core-concepts/capabilities/>
|
||||
- capabilities: <https://pydantic.dev/docs/ai/capabilities/overview/>
|
||||
- hooks: <https://pydantic.dev/docs/ai/core-concepts/hooks/>
|
||||
- toolsets: <https://pydantic.dev/docs/ai/tools-toolsets/toolsets/>
|
||||
- advanced tools: <https://pydantic.dev/docs/ai/tools-toolsets/tools-advanced/>
|
||||
@@ -55,7 +55,7 @@ Before implementing or reviewing a capability change:
|
||||
|
||||
When implementing a new capability, reference these docs:
|
||||
|
||||
- <https://pydantic.dev/docs/ai/core-concepts/capabilities/> -- main capabilities documentation, usage patterns, built-in capabilities
|
||||
- <https://pydantic.dev/docs/ai/capabilities/overview/> -- main capabilities documentation, usage patterns, built-in capabilities
|
||||
- <https://pydantic.dev/docs/ai/core-concepts/hooks/> -- lifecycle hooks reference, hook ordering, all hook categories
|
||||
- <https://pydantic.dev/docs/ai/guides/extensibility/> -- publishing capabilities as packages, spec serialization
|
||||
- <https://pydantic.dev/docs/ai/tools-toolsets/toolsets/> -- toolset abstraction, building tools for capabilities
|
||||
|
||||
+1
-1
@@ -36,7 +36,7 @@ Pydantic AI toolsets.
|
||||
|
||||
## Pydantic AI References
|
||||
|
||||
- Capabilities: <https://pydantic.dev/docs/ai/core-concepts/capabilities/>
|
||||
- Capabilities: <https://pydantic.dev/docs/ai/capabilities/overview/>
|
||||
- Hooks: <https://pydantic.dev/docs/ai/core-concepts/hooks/>
|
||||
- Toolsets: <https://pydantic.dev/docs/ai/tools-toolsets/toolsets/>
|
||||
- Advanced tools: <https://pydantic.dev/docs/ai/tools-toolsets/tools-advanced/>
|
||||
|
||||
+1
-1
@@ -243,4 +243,4 @@ Source: [`pydantic_ai_harness/experimental/acp/`](https://github.com/pydantic/py
|
||||
- [Agent Client Protocol](https://agentclientprotocol.com) -- protocol specification
|
||||
- [Zed external agents](https://zed.dev/docs/ai/external-agents) -- editor-side configuration
|
||||
- [Human-in-the-loop tool approval](/ai/tools-toolsets/deferred-tools/#human-in-the-loop-tool-approval) (Pydantic AI)
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
|
||||
+1
-1
@@ -330,7 +330,7 @@ capabilities:
|
||||
|
||||
- [Tool use via code](https://www.anthropic.com/engineering/code-execution-with-mcp) (Anthropic)
|
||||
- [Code mode in production](https://blog.cloudflare.com/code-mode/) (Cloudflare)
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
|
||||
## API reference
|
||||
|
||||
|
||||
+1
-1
@@ -105,7 +105,7 @@ RepoContext(
|
||||
|
||||
## Further reading
|
||||
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Pydantic AI hooks](/ai/core-concepts/hooks/)
|
||||
|
||||
## API reference
|
||||
|
||||
@@ -206,7 +206,7 @@ DynamicWorkflow(
|
||||
)
|
||||
```
|
||||
|
||||
`defer_loading=True` needs a stable `id`. See [on-demand capabilities](/ai/core-concepts/capabilities/#on-demand-capabilities) for the full picture.
|
||||
`defer_loading=True` needs a stable `id`. See [on-demand capabilities](/ai/capabilities/on-demand/) for the full picture.
|
||||
|
||||
## What runs in the sandbox
|
||||
|
||||
@@ -262,4 +262,4 @@ Source: [`pydantic_ai_harness/dynamic_workflow/`](https://github.com/pydantic/py
|
||||
- [Code Mode](code-mode.md) -- the same sandbox, calling the agent's own tools instead of sub-agents.
|
||||
- [Subagents](subagents.md) -- one-delegation-per-tool-call sub-agents, without the scripted choreography.
|
||||
- [Rewriting Bun in Rust](https://bun.com/blog/bun-in-rust) (Bun) -- the same pattern at scale, via Claude Code's dynamic workflows.
|
||||
- [Capabilities](/ai/core-concepts/capabilities/) and [on-demand capabilities](/ai/core-concepts/capabilities/#on-demand-capabilities).
|
||||
- [Capabilities](/ai/capabilities/overview/) and [on-demand capabilities](/ai/capabilities/on-demand/).
|
||||
|
||||
+1
-1
@@ -179,7 +179,7 @@ Pass `custom_capability_types` so the spec loader knows how to instantiate
|
||||
|
||||
## Further reading
|
||||
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Toolsets](/ai/tools-toolsets/toolsets/)
|
||||
- [the capabilities overview](index.md)
|
||||
|
||||
|
||||
+8
-8
@@ -7,22 +7,22 @@ description: The official capability library for Pydantic AI -- pick-and-choose
|
||||
|
||||
**The batteries for your [Pydantic AI](/ai/) agent.**
|
||||
|
||||
Pydantic AI's [capabilities](/ai/core-concepts/capabilities/) and [hooks](/ai/core-concepts/hooks/) API is how you give an agent its harness -- bundles of tools, lifecycle hooks, instructions, and model settings that extend what the agent can do without any framework changes.
|
||||
Pydantic AI's [capabilities](/ai/capabilities/overview/) and [hooks](/ai/core-concepts/hooks/) API is how you give an agent its harness -- bundles of tools, lifecycle hooks, instructions, and model settings that extend what the agent can do without any framework changes.
|
||||
|
||||
**Pydantic AI Harness** is the official capability library for Pydantic AI, maintained by the [Pydantic AI](https://github.com/pydantic/pydantic-ai) team. Pydantic AI core ships the capabilities that require model or framework support, plus the ones fundamental to every agent -- [web search](/ai/core-concepts/capabilities/#provider-adaptive-tools), [tool search](/ai/tools-toolsets/deferred-tools/), [thinking](/ai/core-concepts/capabilities/#thinking). Everything else lives here: standalone building blocks you pick and choose to turn your agent into a coding agent, a research assistant, or anything else. This is also where new capabilities start -- as they stabilize and prove themselves broadly essential, they can graduate into core.
|
||||
**Pydantic AI Harness** is the official capability library for Pydantic AI, maintained by the [Pydantic AI](https://github.com/pydantic/pydantic-ai) team. Pydantic AI core ships the capabilities that require model or framework support, plus the ones fundamental to every agent -- [web search](/ai/capabilities/web-search/), [tool search](/ai/capabilities/tool-search/), [thinking](/ai/capabilities/thinking/). Everything else lives here: standalone building blocks you pick and choose to turn your agent into a coding agent, a research assistant, or anything else. This is also where new capabilities start -- as they stabilize and prove themselves broadly essential, they can graduate into core.
|
||||
|
||||
## What goes where?
|
||||
|
||||
Pydantic AI core ships the agent loop, model providers, the capabilities/hooks abstraction, and two kinds of capabilities:
|
||||
|
||||
- **Capabilities that require model or framework support** -- anything backed by provider native tools (like [image generation](/ai/core-concepts/capabilities/#provider-adaptive-tools)), provider-specific APIs (like compaction via the OpenAI or Anthropic APIs), or deep agent graph integration. These go hand-in-hand with model class code and need to ship together.
|
||||
- **Capabilities that are fundamental to the agent experience** -- things nearly every agent benefits from, like [web search](/ai/core-concepts/capabilities/#provider-adaptive-tools), [tool search](/ai/tools-toolsets/deferred-tools/), and [thinking](/ai/core-concepts/capabilities/#thinking). These feel like qualities of the agent itself, not accessories.
|
||||
- **Capabilities that require model or framework support** -- anything backed by provider native tools (like [image generation](/ai/capabilities/image-generation/)), provider-specific APIs (like [compaction](/ai/capabilities/compaction/) via the OpenAI or Anthropic APIs), or deep agent graph integration (like [tool search](/ai/capabilities/tool-search/) and [on-demand loading](/ai/capabilities/on-demand/)). These go hand-in-hand with model class code and need to ship together.
|
||||
- **Capabilities that are fundamental to the agent experience** -- things nearly every agent benefits from, like [web search](/ai/capabilities/web-search/), [web fetch](/ai/capabilities/web-fetch/), [thinking](/ai/capabilities/thinking/), and [MCP](/ai/capabilities/mcp/). These feel like qualities of the agent itself, not accessories. See [built-in capabilities](/ai/capabilities/overview/#built-in-capabilities) for the full list.
|
||||
|
||||
**Pydantic AI Harness** is where everything else lives: standalone capabilities that make specific categories of agents powerful, or that are still finding their final shape. Context management, memory, guardrails, file system access, code execution, multi-agent orchestration -- these are the building blocks you pick and choose based on what your agent needs to do.
|
||||
|
||||
The harness is also where new capabilities *start*. It ships as a separate package so capabilities can iterate faster without the strict backward-compatibility requirements of core. As a capability stabilizes and proves itself broadly essential, it can graduate into core -- [code mode](code-mode.md) is an early candidate.
|
||||
|
||||
Many capabilities benefit from a "fall up" pattern: they typically start as a local implementation that works with every model, then gain provider-native support that uses the provider's built-in API when available -- auto-switching between the two. This is how [web search](/ai/core-concepts/capabilities/#provider-adaptive-tools), [web fetch](/ai/core-concepts/capabilities/#provider-adaptive-tools), and [image generation](/ai/core-concepts/capabilities/#provider-adaptive-tools) already work in core, and the same approach is coming for skills, code mode, and context compaction.
|
||||
Many capabilities benefit from a "fall up" pattern: they typically start as a local implementation that works with every model, then gain provider-native support that uses the provider's built-in API when available -- auto-switching between the two. This is how [web search](/ai/capabilities/web-search/), [web fetch](/ai/capabilities/web-fetch/), and [image generation](/ai/capabilities/image-generation/) already work in core, and the same approach is coming for skills, code mode, and context compaction.
|
||||
|
||||
## Installation
|
||||
|
||||
@@ -107,7 +107,7 @@ practices and warning of a "normalization of deviance" as engineers stop reviewi
|
||||
|
||||
## Capabilities
|
||||
|
||||
Each capability is a self-contained battery you drop into an agent's `capabilities=[...]` list. They compose with each other and with Pydantic AI's [built-in capabilities](/ai/core-concepts/capabilities/).
|
||||
Each capability is a self-contained battery you drop into an agent's `capabilities=[...]` list. They compose with each other and with Pydantic AI's [built-in capabilities](/ai/capabilities/overview/).
|
||||
|
||||
| Capability | What it does | Extra |
|
||||
|---|---|---|
|
||||
@@ -133,7 +133,7 @@ Most capabilities are stable within the [version policy](#version-policy) below.
|
||||
|
||||
## Build your own
|
||||
|
||||
[Capabilities](/ai/core-concepts/capabilities/#building-custom-capabilities) are the primary extension point for Pydantic AI. Any of the capabilities in this library can serve as a reference for building your own.
|
||||
[Capabilities](/ai/capabilities/custom/) are the primary extension point for Pydantic AI. Any of the capabilities in this library can serve as a reference for building your own.
|
||||
|
||||
Publishing as a standalone package? Use the `pydantic-ai-<name>` naming convention -- see [Publishing capability packages](/ai/guides/extensibility/#publishing-capability-packages).
|
||||
|
||||
@@ -143,7 +143,7 @@ Pydantic AI Harness uses **0.x versioning** to signal that APIs are still stabil
|
||||
|
||||
## Pydantic AI references
|
||||
|
||||
- [Capabilities](/ai/core-concepts/capabilities/) -- what capabilities are, built-in capabilities, building your own
|
||||
- [Capabilities](/ai/capabilities/overview/) -- what capabilities are, built-in capabilities, building your own
|
||||
- [Hooks](/ai/core-concepts/hooks/) -- lifecycle hooks reference, ordering, error handling
|
||||
- [Extensibility](/ai/guides/extensibility/) -- publishing packages, third-party ecosystem
|
||||
- [Toolsets](/ai/tools-toolsets/toolsets/) -- building tools for capabilities
|
||||
|
||||
+1
-1
@@ -217,7 +217,7 @@ Memory records do not carry source citations or verified provenance. If an appli
|
||||
## API reference
|
||||
|
||||
- [`pydantic_ai_harness.memory` source](https://github.com/pydantic/pydantic-ai-harness/tree/main/pydantic_ai_harness/memory/)
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Pydantic AI hooks](/ai/core-concepts/hooks/)
|
||||
|
||||
The public module exports `Memory`, `MemoryToolset`, the bundled stores, the store protocols, mutation and search result models, and conflict exceptions. Import them from `pydantic_ai_harness.memory`.
|
||||
|
||||
+1
-1
@@ -133,7 +133,7 @@ capabilities:
|
||||
|
||||
## Further reading
|
||||
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Hooks](/ai/core-concepts/hooks/) -- `wrap_model_request` is the ephemeral injection point used here
|
||||
- [Anthropic prompt caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching)
|
||||
- [Code Mode](code-mode.md) -- another prompt-cache-aware harness capability
|
||||
|
||||
+2
-2
@@ -19,7 +19,7 @@ Agents frequently need to run a build, a test suite, a linter, or a quick
|
||||
killing runaway processes, and cleaning up background jobs at the end of a run --
|
||||
is fiddly boilerplate that every agent reinvents.
|
||||
|
||||
`Shell` bundles that plumbing into a single [capability](/ai/core-concepts/capabilities/):
|
||||
`Shell` bundles that plumbing into a single [capability](/ai/capabilities/overview/):
|
||||
configurable allow/deny lists, output truncation tuned to keep the useful tail,
|
||||
optional sticky working directory, environment control that can keep host
|
||||
secrets out of spawned commands, and automatic cleanup of background processes
|
||||
@@ -247,7 +247,7 @@ Pass `custom_capability_types` so the spec loader knows how to instantiate
|
||||
|
||||
## Further reading
|
||||
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Toolsets](/ai/tools-toolsets/toolsets/)
|
||||
|
||||
## API reference
|
||||
|
||||
+1
-1
@@ -215,7 +215,7 @@ SubAgent(
|
||||
|
||||
## Further reading
|
||||
|
||||
- [Pydantic AI capabilities](/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](/ai/capabilities/overview/)
|
||||
- [Multi-agent applications](/ai/guides/multi-agent-applications/)
|
||||
|
||||
## API reference
|
||||
|
||||
@@ -455,7 +455,7 @@ DynamicWorkflow(
|
||||
```
|
||||
|
||||
`defer_loading=True` needs a stable `id`. See
|
||||
[on-demand capabilities](https://pydantic.dev/docs/ai/core-concepts/capabilities/#on-demand-capabilities)
|
||||
[on-demand capabilities](https://pydantic.dev/docs/ai/capabilities/on-demand/)
|
||||
for the full picture.
|
||||
|
||||
## What runs in the sandbox
|
||||
@@ -532,6 +532,6 @@ WorkflowAgent(
|
||||
(Anthropic), the orchestration patterns a script can express.
|
||||
- [Rewriting Bun in Rust](https://bun.com/blog/bun-in-rust) (Bun), the same pattern at scale: Jarred
|
||||
Sumner's port of Bun from Zig to Rust with Claude Code dynamic workflows.
|
||||
- [Capabilities](https://pydantic.dev/docs/ai/core-concepts/capabilities/) and
|
||||
[on-demand capabilities](https://pydantic.dev/docs/ai/core-concepts/capabilities/#on-demand-capabilities).
|
||||
- [Capabilities](https://pydantic.dev/docs/ai/capabilities/overview/) and
|
||||
[on-demand capabilities](https://pydantic.dev/docs/ai/capabilities/on-demand/).
|
||||
- [Monty](https://github.com/pydantic/monty), the sandbox.
|
||||
|
||||
@@ -212,7 +212,7 @@ Memory records do not carry source citations or verified provenance. If an appli
|
||||
## API reference
|
||||
|
||||
- [`pydantic_ai_harness.memory` source](https://github.com/pydantic/pydantic-ai-harness/tree/main/pydantic_ai_harness/memory/)
|
||||
- [Pydantic AI capabilities](https://pydantic.dev/docs/ai/core-concepts/capabilities/)
|
||||
- [Pydantic AI capabilities](https://pydantic.dev/docs/ai/capabilities/overview/)
|
||||
- [Pydantic AI hooks](https://pydantic.dev/docs/ai/core-concepts/hooks/)
|
||||
|
||||
The public module exports `Memory`, `MemoryToolset`, the bundled stores, the store protocols, mutation and search result models, and conflict exceptions. Import them from `pydantic_ai_harness.memory`.
|
||||
|
||||
Reference in New Issue
Block a user