From 191a17391a0302439fdcb943b620b62398b7186d Mon Sep 17 00:00:00 2001 From: Lucas Gomide Date: Tue, 14 Jul 2026 18:16:36 -0300 Subject: [PATCH] docs: use /edge prefix for links to edge-only hooks pages The `/en/learn/...` form still resolves against the default frozen version, where `step-hooks` and `execution-boundary-hooks` do not exist yet, so the link checker kept failing. Links now use the explicit `/edge/en/learn/...` form, matching how `consuming-streams.mdx` linked to edge-only streaming pages before they were frozen. --- docs/edge/en/learn/execution-boundary-hooks.mdx | 10 +++++----- docs/edge/en/learn/execution-hooks.mdx | 14 +++++++------- docs/edge/en/learn/llm-hooks.mdx | 12 ++++++------ docs/edge/en/learn/step-hooks.mdx | 8 ++++---- docs/edge/en/learn/tool-hooks.mdx | 10 +++++----- 5 files changed, 27 insertions(+), 27 deletions(-) diff --git a/docs/edge/en/learn/execution-boundary-hooks.mdx b/docs/edge/en/learn/execution-boundary-hooks.mdx index fe53a783f..5b7a2ffe8 100644 --- a/docs/edge/en/learn/execution-boundary-hooks.mdx +++ b/docs/edge/en/learn/execution-boundary-hooks.mdx @@ -38,7 +38,7 @@ def boundary_hook(ctx) -> Any | None: Boundary hooks follow the standard contract: proceed (`return None`), mutate in place, replace by returning, or abort by raising -[`HookAborted`](/en/learn/execution-hooks#aborting-an-operation). An abort at any +[`HookAborted`](/edge/en/learn/execution-hooks#aborting-an-operation). An abort at any boundary propagates out of `kickoff()` with its reason. ## Context Schema @@ -157,7 +157,7 @@ clear_all_hooks() # Clears every point, including boundaries ## Related Documentation -- [Execution Hooks Overview →](/en/learn/execution-hooks) -- [Step Hooks →](/en/learn/step-hooks) -- [LLM Call Hooks →](/en/learn/llm-hooks) -- [Tool Call Hooks →](/en/learn/tool-hooks) +- [Execution Hooks Overview →](/edge/en/learn/execution-hooks) +- [Step Hooks →](/edge/en/learn/step-hooks) +- [LLM Call Hooks →](/edge/en/learn/llm-hooks) +- [Tool Call Hooks →](/edge/en/learn/tool-hooks) diff --git a/docs/edge/en/learn/execution-hooks.mdx b/docs/edge/en/learn/execution-hooks.mdx index 3eca670b3..1c54dc8d2 100644 --- a/docs/edge/en/learn/execution-hooks.mdx +++ b/docs/edge/en/learn/execution-hooks.mdx @@ -87,7 +87,7 @@ class MyProjCrew: Each family has a detailed guide covering its context schema, payload semantics, and examples. -### [Execution boundaries](/en/learn/execution-boundary-hooks) +### [Execution boundaries](/edge/en/learn/execution-boundary-hooks) | Point | When | `ctx.payload` | |-------|------|---------------| @@ -96,7 +96,7 @@ semantics, and examples. | `OUTPUT` | Final result is ready | the output object | | `EXECUTION_END` | A crew or flow has finished | the output object | -### [Model boundaries](/en/learn/llm-hooks) & [tool boundaries](/en/learn/tool-hooks) +### [Model boundaries](/edge/en/learn/llm-hooks) & [tool boundaries](/edge/en/learn/tool-hooks) | Point | When | Hook receives | |-------|------|---------------| @@ -110,7 +110,7 @@ its argument — there is no separate `ctx.payload`. Mutate `ctx.messages` / `ctx.tool_input` in place, and return a string from a post hook to replace the response / tool result. -### [Step points](/en/learn/step-hooks) +### [Step points](/edge/en/learn/step-hooks) | Point | When | `ctx.payload` | |-------|------|---------------| @@ -272,10 +272,10 @@ You might still prefer them for existing codebases that already use For the detailed guides — context attributes, patterns, and management APIs (`register_*` / `unregister_*` / `clear_*`) — see: -- [LLM Call Hooks →](/en/learn/llm-hooks) -- [Tool Call Hooks →](/en/learn/tool-hooks) +- [LLM Call Hooks →](/edge/en/learn/llm-hooks) +- [Tool Call Hooks →](/edge/en/learn/tool-hooks) ## Related documentation -- [Before and After Kickoff Hooks →](/en/learn/before-and-after-kickoff-hooks) -- [Human-in-the-Loop →](/en/learn/human-in-the-loop) +- [Before and After Kickoff Hooks →](/edge/en/learn/before-and-after-kickoff-hooks) +- [Human-in-the-Loop →](/edge/en/learn/human-in-the-loop) diff --git a/docs/edge/en/learn/llm-hooks.mdx b/docs/edge/en/learn/llm-hooks.mdx index 7d19d74a3..738097385 100644 --- a/docs/edge/en/learn/llm-hooks.mdx +++ b/docs/edge/en/learn/llm-hooks.mdx @@ -18,7 +18,7 @@ LLM hooks are executed at two interception points: | `PRE_MODEL_CALL` | Before every LLM call | `LLMCallHookContext` | | `POST_MODEL_CALL` | After every LLM call | `LLMCallHookContext` (with `response` set) | -Write them with the [`@on` decorator](/en/learn/execution-hooks). The +Write them with the [`@on` decorator](/edge/en/learn/execution-hooks). The [legacy `@before_llm_call` / `@after_llm_call` decorators](#legacy-decorators) keep working unchanged — both styles register on the same engine and run in one ordered chain. @@ -48,7 +48,7 @@ string to replace the response after it. Blocking a call raises `ValueError("LLM call blocked by before_llm_call hook")` inside the executor; the `HookAborted` reason and source are recorded in -[telemetry](/en/learn/execution-hooks#telemetry). +[telemetry](/edge/en/learn/execution-hooks#telemetry). ## LLM Hook Context @@ -276,7 +276,7 @@ there is no behavioral penalty. ## Related Documentation -- [Execution Hooks Overview →](/en/learn/execution-hooks) -- [Tool Call Hooks →](/en/learn/tool-hooks) -- [Execution Boundary Hooks →](/en/learn/execution-boundary-hooks) -- [Step Hooks →](/en/learn/step-hooks) +- [Execution Hooks Overview →](/edge/en/learn/execution-hooks) +- [Tool Call Hooks →](/edge/en/learn/tool-hooks) +- [Execution Boundary Hooks →](/edge/en/learn/execution-boundary-hooks) +- [Step Hooks →](/edge/en/learn/step-hooks) diff --git a/docs/edge/en/learn/step-hooks.mdx b/docs/edge/en/learn/step-hooks.mdx index c5772e497..7aa104e4b 100644 --- a/docs/edge/en/learn/step-hooks.mdx +++ b/docs/edge/en/learn/step-hooks.mdx @@ -136,7 +136,7 @@ clear_all_hooks() # Clears every point, including steps ## Related Documentation -- [Execution Hooks Overview →](/en/learn/execution-hooks) -- [Execution Boundary Hooks →](/en/learn/execution-boundary-hooks) -- [LLM Call Hooks →](/en/learn/llm-hooks) -- [Tool Call Hooks →](/en/learn/tool-hooks) +- [Execution Hooks Overview →](/edge/en/learn/execution-hooks) +- [Execution Boundary Hooks →](/edge/en/learn/execution-boundary-hooks) +- [LLM Call Hooks →](/edge/en/learn/llm-hooks) +- [Tool Call Hooks →](/edge/en/learn/tool-hooks) diff --git a/docs/edge/en/learn/tool-hooks.mdx b/docs/edge/en/learn/tool-hooks.mdx index 6f4b2c89e..793fd9e62 100644 --- a/docs/edge/en/learn/tool-hooks.mdx +++ b/docs/edge/en/learn/tool-hooks.mdx @@ -18,7 +18,7 @@ Tool hooks are executed at two interception points: | `PRE_TOOL_CALL` | Before every tool execution | `ToolCallHookContext` | | `POST_TOOL_CALL` | After every tool execution | `ToolCallHookContext` (with results set) | -Write them with the [`@on` decorator](/en/learn/execution-hooks). The +Write them with the [`@on` decorator](/edge/en/learn/execution-hooks). The [legacy `@before_tool_call` / `@after_tool_call` decorators](#legacy-decorators) keep working unchanged — both styles register on the same engine and run in one ordered chain. @@ -334,7 +334,7 @@ there is no behavioral penalty. ## Related Documentation -- [Execution Hooks Overview →](/en/learn/execution-hooks) -- [LLM Call Hooks →](/en/learn/llm-hooks) -- [Execution Boundary Hooks →](/en/learn/execution-boundary-hooks) -- [Step Hooks →](/en/learn/step-hooks) +- [Execution Hooks Overview →](/edge/en/learn/execution-hooks) +- [LLM Call Hooks →](/edge/en/learn/llm-hooks) +- [Execution Boundary Hooks →](/edge/en/learn/execution-boundary-hooks) +- [Step Hooks →](/edge/en/learn/step-hooks)