The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Fix links in docs
Chirag Jainf94b3106d6eb
diff --git a/docs/api/overview.mdx b/docs/api/overview.mdxindex 2103d9f9a..dc8e2387f 100644--- a/docs/api/overview.mdx+++ b/docs/api/overview.mdx@@ -104,7 +104,7 @@ flowchart LR| **Turn 3** | Jane (or a support rep) | Approval: allow `process_refund` | Agent runs the refund and sends a confirmation. |<Note>- A turn can also pause when the agent asks a clarifying question ([`tool.response_required`](/create-agent/overview#whats-in-an-agent))+ A turn can also pause when the agent asks a clarifying question ([`tool.response_required`](/api/use-agent#tool-response_required))or needs MCP OAuth ([`mcp.auth_required`](/mcp-servers#in-chat-authentication)). You resume with a new turn, just likeTurn 3 above.</Note>@@ -145,7 +145,7 @@ Sample payload:}```-Every event carries an `id` and a `thread_id` (`"main"` for the root agent, a generated id for [subagents](/key-features/subagents), or `null` for run-level events), plus a **sequence number** used for [resuming after a disconnect](/api/use-agent). The stream always opens with `turn.created` and closes with `turn.done`. Field-level schemas for every event type are in the [turn events reference](/api/use-agent#turn-events-reference).+Every event carries an `id` and a `thread_id` (`"main"` for the root agent, a generated id for [subagents](/key-features/subagents), or `null` for run-level events), plus a **sequence number** used for [resuming after a disconnect](/api/use-agent#resume-a-stream). The stream always opens with `turn.created` and closes with `turn.done`. Field-level schemas for every event type are in the [turn events reference](/api/use-agent#turn-events-reference).### Deltadiff --git a/docs/api/use-agent.mdx b/docs/api/use-agent.mdxindex c7f5ebb04..6bc2e3e18 100644--- a/docs/api/use-agent.mdx+++ b/docs/api/use-agent.mdx@@ -287,8 +287,8 @@ Turn `input` accepts three item types (a single turn can't mix a `user.message`| `type` | Purpose || --- | --- || `user.message` | A message. `content` is a string, or an array of `text` / `file` parts (files as data URIs). |-| `user.tool_approval` | An [approval decision](/create-agent/overview#whats-in-an-agent) for a paused tool call. |-| `user.tool_response` | An [answer](/create-agent/overview#whats-in-an-agent) for a paused client-side tool call. |+| `user.tool_approval` | An [approval decision](/create-agent/overview#what’s-in-an-agent) for a paused tool call. |+| `user.tool_response` | An [answer](/create-agent/overview#what’s-in-an-agent) for a paused client-side tool call. |### Non-streaming turn@@ -490,7 +490,7 @@ For approvals and questions, each pending ref carries the `sourceEventId` of the### Tool approvals-A gated tool ([human approval](/create-agent/overview#whats-in-an-agent)) emits [`tool.approval_required`](#tool-approval-required). Collect the pending events while streaming, then resume with one `user.tool_approval` per pending call, either allowing it or denying it with a reason. Look up each ref in the [event index](#create-and-stream-a-turn).+A gated tool ([human approval](/create-agent/overview#what’s-in-an-agent)) emits [`tool.approval_required`](#tool-approval-required). Collect the pending events while streaming, then resume with one `user.tool_approval` per pending call, either allowing it or denying it with a reason. Look up each ref in the [event index](#create-and-stream-a-turn).<CodeGroup>```typescript TypeScript wrap@@ -594,7 +594,7 @@ for event in resume:### Agent questions-When the agent uses the built-in [`ask_user_question`](/create-agent/overview#whats-in-an-agent) tool, it emits [`tool.response_required`](#tool-response-required); the pending call's `arguments` carry the `question` and `options`. Resume with one `user.tool_response` per pending call.+When the agent uses the built-in [`ask_user_question`](/create-agent/overview#what’s-in-an-agent) tool, it emits [`tool.response_required`](#tool-response-required); the pending call's `arguments` carry the `question` and `options`. Resume with one `user.tool_response` per pending call.<CodeGroup>```typescript TypeScript wrap@@ -1236,7 +1236,7 @@ The result of a tool the harness executed, linked to its call by `tool_call_id`:#### `tool.approval_required`-A tool call needs [human approval](/create-agent/overview#whats-in-an-agent) before it can run. The turn ends after this event; resume with a `user.tool_approval` input.+A tool call needs [human approval](/create-agent/overview#what’s-in-an-agent) before it can run. The turn ends after this event; resume with a `user.tool_approval` input.| Field | Description || ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------- |@@ -1244,7 +1244,7 @@ A tool call needs [human approval](/create-agent/overview#whats-in-an-agent) bef#### `tool.response_required`-A client-side tool (e.g. [`ask_user_question`](/create-agent/overview#whats-in-an-agent)) needs a result from your app. Same shape as `tool.approval_required`; resume with a `user.tool_response` input.+A client-side tool (e.g. [`ask_user_question`](/create-agent/overview#what’s-in-an-agent)) needs a result from your app. Same shape as `tool.approval_required`; resume with a `user.tool_response` input.### Subagent thread eventsdiff --git a/docs/chat-ui.mdx b/docs/chat-ui.mdxindex d78ef572e..77a417a43 100644--- a/docs/chat-ui.mdx+++ b/docs/chat-ui.mdx@@ -23,7 +23,7 @@ When you run TrueForge ([Quickstart](/quickstart)), open the app URL (for exampl- The Build Agent page and [Agents](/agent-library)- Streaming chat with tool calls, approvals, and ask-user-questions- Settings for [models](/models), [connectors](/mcp-servers), [skills](/skills), and [sandbox](/sandbox)-- [Generative UI](/create-agent/overview#whats-in-an-agent) rendering out of the box+- [Generative UI](/create-agent/overview#what’s-in-an-agent) rendering out of the box<Frame caption="The bundled chat UI: an agent response with an expandable summary of its steps (tool calls and reasoning)."><img src="/images/chat-ui.png" alt="TrueForge chat UI with an agent response and a collapsed Agent steps summary of tool calls and thoughts" />diff --git a/docs/create-agent/overview.mdx b/docs/create-agent/overview.mdxindex 408d802a1..96d39d681 100644--- a/docs/create-agent/overview.mdx+++ b/docs/create-agent/overview.mdx@@ -6,7 +6,7 @@ description: 'Every option on an agent, what the UI covers today, and how to setAn agent is a saved, reusable definition: a model, instructions, the tools and skills it can use, and a set of runtime behaviors. You build one on the **Build Agent** page or via the [SDK](/api/overview) — either way, TrueForge stores the same **agent spec**, and any number of conversations can run against it.-- **[What's in an agent](#whats-in-an-agent)** — every option, explained.+- **[What's in an agent](#what’s-in-an-agent)** — every option, explained.- **[Create an agent via the UI](#create-an-agent-via-the-ui)** — the options available in the UI today.- **[Create an agent via the API](#create-an-agent-via-the-api)** — the full agent spec, with every field.@@ -361,7 +361,7 @@ Optional array. Each entry attaches a [configured MCP server](/mcp-servers) by n| `enable_tools` | `["@all"]` | API | Tools exposed to the agent: `@all`, `@read-only`, or literal tool names. || `disable_tools` | `[]` | API | Tools subtracted from the enabled set. || `preload_tools` | `[]` | API | Tools loaded eagerly into context while the rest stay deferred. |-| `require_approval_for_tools` | `["@destructive"]` | UI + API | Tools that pause for [human approval](#whats-in-an-agent): `@all`, `@write`, `@destructive`, or literal names. |+| `require_approval_for_tools` | `["@destructive"]` | UI + API | Tools that pause for [human approval](#tool-approval): `@all`, `@write`, `@destructive`, or literal names. || `preload` | `false` | UI + API | Load all tool schemas upfront instead of [on demand](/key-features/deferred-tool-loading). |The `@read-only`, `@write`, and `@destructive` selectors are resolved from the tool annotations published by the MCP server. `@write` matches `readOnlyHint: false` when the tool is not destructive; `@destructive` matches `destructiveHint: true`. A tool with no annotations, or one the server marks read-only, matches neither selector and runs without an approval pause. Name the tool, or use `@all`, to gate it anyway.@@ -385,8 +385,8 @@ Runtime behavior. Every field has a default, so `config` can be omitted entirely| Field | Default | Set via | Description || -------------------- | ---------------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------- || `sandbox` | `{ "enabled": false }` | UI + API | [Sandbox](/sandbox) for code execution, files, and skills. |-| `generative_ui` | `{ "enabled": true }` | UI + API | [Generative UI](#whats-in-an-agent) (OpenUI blocks). |-| `ask_user_questions` | `{ "enabled": true }` | UI + API | The [`ask_user_question`](#whats-in-an-agent) tool. |+| `generative_ui` | `{ "enabled": true }` | UI + API | [Generative UI](#generative-ui) (OpenUI blocks). |+| `ask_user_questions` | `{ "enabled": true }` | UI + API | The [`ask_user_question`](#ask-clarifying-questions) tool. || `dynamic_sub_agents` | `{ "enabled": true }` | UI + API | [Subagents](/key-features/subagents). || `context_management` | all enabled | API | [Compaction](/key-features/overview#context-compaction) and [large tool response offloading](/key-features/large-tool-responses). || `iteration_limit` | `100` | API | Max agent-loop iterations per turn (1–1024). A safety stop for runaway loops. |diff --git a/docs/docs.json b/docs/docs.jsonindex baa97e1db..b3a073b78 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -3,9 +3,9 @@"theme": "mint","redirects": [{ "source": "/api/turn-events", "destination": "/api/use-agent#turn-events-reference" },- { "source": "/create-agent/tool-approval", "destination": "/create-agent/overview#whats-in-an-agent" },- { "source": "/create-agent/ask-user-questions", "destination": "/create-agent/overview#whats-in-an-agent" },- { "source": "/create-agent/generative-ui", "destination": "/create-agent/overview#whats-in-an-agent" },+ { "source": "/create-agent/tool-approval", "destination": "/create-agent/overview#tool-approval" },+ { "source": "/create-agent/ask-user-questions", "destination": "/create-agent/overview#ask-clarifying-questions" },+ { "source": "/create-agent/generative-ui", "destination": "/create-agent/overview#generative-ui" },{ "source": "/create-agent/agent-spec", "destination": "/create-agent/overview#create-an-agent-via-the-api" }],"name": "TrueForge",diff --git a/docs/introduction.mdx b/docs/introduction.mdxindex cf7614d74..9d8ee6a3b 100644--- a/docs/introduction.mdx+++ b/docs/introduction.mdx@@ -45,7 +45,7 @@ TrueForge is an **open-source agent harness** with three parts: a **core server*Runs the agent loop. When a user sends a message, the server:- Plans the turn, calls the model, and executes tools — streaming every step back-- Pauses for [human approval](/create-agent/overview#whats-in-an-agent) on sensitive actions+- Pauses for [human approval](/create-agent/overview#what’s-in-an-agent) on sensitive actions- Keeps context lean on long tasks with [harness capabilities](/key-features/overview) like subagents and compaction- Persists sessions, so conversations survive reconnects and restartsdiff --git a/docs/key-features/code-mode.mdx b/docs/key-features/code-mode.mdxindex 69ffc6241..022497690 100644--- a/docs/key-features/code-mode.mdx+++ b/docs/key-features/code-mode.mdx@@ -55,7 +55,7 @@ sequenceDiagramCode Mode is available whenever the agent's [sandbox](/sandbox) is enabled. The agent decides at runtime whether a task is worth running in code or whether a single direct tool call is enough. Before writing a script, it can call [`get_tool_output_schema`](/key-features/deferred-tool-loading#how-it-works) so it knows the exact shape of a tool's response instead of guessing keys from raw JSON.<Note>- [Approval policies](/create-agent/overview#whats-in-an-agent) still apply in Code Mode — a script that calls a tool matching+ [Approval policies](/create-agent/overview#what’s-in-an-agent) still apply in Code Mode — a script that calls a tool matching`require_approval_for_tools` pauses for user approval just like a direct tool call.</Note>diff --git a/docs/key-features/overview.mdx b/docs/key-features/overview.mdxindex 0a83fa9b8..9b13a64ef 100644--- a/docs/key-features/overview.mdx+++ b/docs/key-features/overview.mdx@@ -8,11 +8,11 @@ TrueForge is more than model + tools. These harness features keep long agent run| Feature | What it does || --- | --- |-| [Sandbox as a tool](/sandbox) | Isolated code/file execution without putting secrets or the agent loop inside the sandbox |+| [Sandbox as a tool](#sandbox-as-a-tool) | Isolated code/file execution without putting secrets or the agent loop inside the sandbox || [Context engineering](#what-is-context-engineering) | Progressive skills, deferred tools, subagents, offloading, Code Mode, compaction |-| [Tool approval](/create-agent/overview#whats-in-an-agent) | Pause before write/destructive MCP tools |-| [Ask clarifying questions](/create-agent/overview#whats-in-an-agent) | Structured clarification mid-run |-| [Generative UI](/create-agent/overview#whats-in-an-agent) | Charts, tables, and cards streamed into chat |+| [Tool approval](/create-agent/overview#tool-approval) | Pause before write/destructive MCP tools |+| [Ask clarifying questions](/create-agent/overview#ask-clarifying-questions) | Structured clarification mid-run |+| [Generative UI](/create-agent/overview#generative-ui) | Charts, tables, and cards streamed into chat || [In-chat MCP OAuth](/mcp-servers#in-chat-authentication) | Connect button when a connector needs authorization |## Sandbox as a tool@@ -162,7 +162,7 @@ flowchart TD<Note>Compaction is **lossy in the working context** — fine-grained details from earlier messages are condensed into thesummary. The full event history of the session remains persisted and queryable via the [session events- API](/api/overview), but the agent works from the summary after compaction.+ API](/api-reference/agent-sessions/list-session-events), but the agent works from the summary after compaction.</Note>Configuration:diff --git a/docs/key-features/subagents.mdx b/docs/key-features/subagents.mdxindex d865787fb..6be1aa373 100644--- a/docs/key-features/subagents.mdx+++ b/docs/key-features/subagents.mdx@@ -64,7 +64,7 @@ flowchart LR<Note>- **Shared tools and sandbox** — subagents have access to the same MCP tools and sandbox environment as the root agent.- - **No user interaction** — subagents cannot ask the user questions. Only the root agent talks to the user. Subagent tool calls that require [approval](/create-agent/overview#whats-in-an-agent) still pause for the user, though.+ - **No user interaction** — subagents cannot ask the user questions. Only the root agent talks to the user. Subagent tool calls that require [approval](/create-agent/overview#what’s-in-an-agent) still pause for the user, though.- **No nesting** — subagents cannot create other subagents. Delegation is one level deep.- **Parallel execution** — multiple subagents run concurrently. The root agent waits for all of them before continuing.</Note>diff --git a/docs/mcp-servers.mdx b/docs/mcp-servers.mdxindex 88335a039..6fd8f2bb8 100644--- a/docs/mcp-servers.mdx+++ b/docs/mcp-servers.mdx@@ -57,5 +57,5 @@ If a server uses OAuth and the user has not yet authorized it, the turn pauses a## Next steps- Attach MCP servers when you [create an agent](/create-agent/overview).-- Configure which tools need [approval](/create-agent/overview#whats-in-an-agent) (API today).+- Configure which tools need [approval](/create-agent/overview#what’s-in-an-agent) (API today).- Keep tool schemas lean with [deferred loading](/key-features/deferred-tool-loading) in Harness Capabilities.