> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mellea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# mellea.plugins.hooks.generation

> Generation pipeline hook payloads.

export const SidebarFix = () => <script dangerouslySetInnerHTML={{
  __html: `
        (function () {
          const INTERVAL_MS = 500;

          const upgradeSidebar = () => {
            const links = document.querySelectorAll('a[href^="#"]');

            links.forEach((link) => {
              if (link.dataset.badged === "true") return;

              const rawText = (link.textContent || "").trim();

              // ========== FUNC ==========
              if (rawText.startsWith("FUNC ")) {
                const label = rawText.replace(/^FUNC\\s+/, "").trim();

                while (link.firstChild) link.removeChild(link.firstChild);

                // 👉 Make the whole link a single flex row & prevent wrapping
                link.style.display = "flex";
                link.style.alignItems = "center";
                link.style.whiteSpace = "nowrap";
                link.style.columnGap = "0.5rem";

                const badge = document.createElement("span");
                badge.style.marginRight = "0.5rem";
                badge.style.display = "inline-flex";
                badge.style.alignItems = "center";
                badge.style.borderRadius = "9999px";
                badge.style.padding = "0rem 0.6rem";
                badge.style.fontSize = "0.5rem";
                badge.style.fontWeight = "700";
                badge.style.letterSpacing = "0.05em";
                badge.style.backgroundColor = "rgba(48, 100, 227, 0.20)";
                badge.style.color = "#1D4ED8";

                badge.textContent = "FUNC";

                link.appendChild(badge);
                link.appendChild(document.createTextNode(label));
                link.dataset.badged = "true";
                return;
              }

              // ========== CLASS ==========
              if (rawText.startsWith("CLASS ")) {
                const label = rawText.replace(/^CLASS\\s+/, "").trim();

                while (link.firstChild) link.removeChild(link.firstChild);

                // 👉 Same flex / nowrap treatment for class links
                link.style.display = "flex";
                link.style.alignItems = "center";
                link.style.whiteSpace = "nowrap";
                link.style.columnGap = "0.5rem";

                const badge = document.createElement("span");
                badge.style.marginRight = "0.5rem";
                badge.style.display = "inline-flex";
                badge.style.alignItems = "center";
                badge.style.borderRadius = "9999px";
                badge.style.padding = "0rem 0.6rem";
                badge.style.fontSize = "0.5rem";
                badge.style.fontWeight = "700";
                badge.style.letterSpacing = "0.05em";
                badge.style.backgroundColor = "rgba(74, 222, 128, 0.20)";
                badge.style.color = "#15803D";

                badge.textContent = "CLASS";

                link.appendChild(badge);
                link.appendChild(document.createTextNode(label));
                link.dataset.badged = "true";
                return;
              }
            });
          };

          upgradeSidebar();
          setInterval(upgradeSidebar, INTERVAL_MS);
        })();
      `
}} />;

<SidebarFix />

Generation pipeline hook payloads.

## Classes

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `GenerationPreCallPayload` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/plugins/hooks/generation.py#L10" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Payload for `generation_pre_call` — before LLM backend call.

**Attributes:**

* `action`: The [`Component`](../../core/base#class-component) or [`CBlock`](../../core/base#class-cblock) about to be sent to the backend.
* `context`: The [`Context`](../../core/base#class-context) being used for this generation call.
* `model_options`: Dict of model options (writable — plugins may adjust temperature, etc.).
* `format`: Optional `BaseModel` subclass for constrained decoding (writable).
* `tool_calls`: Whether tool calls are enabled for this generation (writable).

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `GenerationPostCallPayload` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/plugins/hooks/generation.py#L30" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Payload for `generation_post_call` — fires once the model output is fully computed.

For lazy [`ModelOutputThunk`](../../core/base#class-modeloutputthunk) objects this hook fires inside
`ModelOutputThunk.astream` after `post_process` completes, so
`model_output.value` is guaranteed to be available. For already-computed
thunks (e.g. cached responses) it fires before `generate_from_context`
returns.

**Attributes:**

* `prompt`: The formatted prompt sent to the backend (str or list of message dicts).
* `model_output`: The fully-computed [`ModelOutputThunk`](../../core/base#class-modeloutputthunk).
* `latency_ms`: Elapsed milliseconds from the `generate_from_context` call
  to when the value was fully materialized.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />

### <span className="ml-2 inline-flex items-center rounded-full px-2 py-1 text-[0.7rem] font-bold tracking-wide bg-[#4ADE8033]/20 text-[#15803D]">CLASS</span> `GenerationErrorPayload` <sup><a href="https://github.com/generative-computing/mellea/blob/v0.6.0/mellea/plugins/hooks/generation.py#L51" target="_blank"><Icon icon="github" style="width: 14px; height: 14px;" /></a></sup>

Payload for `generation_error` — fires when the LLM backend raises an exception.

This hook fires inside `ModelOutputThunk.astream` just before the exception
is re-raised, giving plugins a chance to observe (but not suppress) the error.

**Attributes:**

* `exception`: The exception raised by the backend.
* `model_output`: The [`ModelOutputThunk`](../../core/base#class-modeloutputthunk) at the time of the error. `model`
  and `provider` are set when the backend set them early (before the
  async task); otherwise they are `None`.

<div className="w-full h-px bg-gray-200 dark:bg-gray-700 my-4" />