feat(hooks): add trigger and channelId to plugin hook agent context (#28623)

* feat(hooks): add trigger and channelId to plugin hook agent context

Adds `trigger` and `channelId` fields to `PluginHookAgentContext` so
plugins can determine what initiated the agent run and which channel
it originated from, without session-key parsing or Redis bridging.

trigger values: "user", "heartbeat", "cron", "memory"
channelId values: "telegram", "discord", "whatsapp", etc.

Both fields are threaded through run.ts and attempt.ts hookCtx so all
hook phases receive them (before_model_resolve, before_prompt_build,
before_agent_start, llm_input, llm_output, agent_end).

channelId falls back from messageChannel to messageProvider when the
former is not set. followup-runner passes originatingChannel so queued
followup runs also carry channel context.

* docs(changelog): note hook context parity fix for #28623

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>

CHANGELOG.md

@@ -45,6 +45,7 @@ Docs: https://docs.openclaw.ai
 - CLI/Config validation and routing hardening: dedupe `openclaw config validate` failures to a single authoritative report, expose allowed-values metadata/hints across core Zod and plugin AJV validation (including `--json` fields), sanitize terminal-rendered validation text, and make command-path parsing root-option-aware across preaction/route/lazy registration (including routed `config get/unset` with split root options). Thanks @gumadeiras.
 - Models/config env propagation: apply `config.env.vars` before implicit provider discovery in models bootstrap so config-scoped credentials are visible to implicit provider resolution paths. (#32295) Thanks @hsiaoa.
 - Hooks/runtime stability: keep the internal hook handler registry on a `globalThis` singleton so hook registration/dispatch remains consistent when bundling emits duplicate module copies. (#32292) Thanks @Drickon.
+- Hooks/plugin context parity: ensure `llm_input` hooks in embedded attempts receive the same `trigger` and `channelId`-aware `hookCtx` used by the other hook phases, preserving channel/trigger-scoped plugin behavior. (#28623) Thanks @davidrudduck and @vincentkoc.
 - Restart sentinel formatting: avoid duplicate `Reason:` lines when restart message text already matches `stats.reason`, keeping restart notifications concise for users and downstream parsers. (#32083) Thanks @velamints2.
 - Voice-call/Twilio signature verification: retry signature validation across deterministic URL port variants (with/without port) to handle mixed Twilio signing behavior behind reverse proxies and non-standard ports. (#25140) Thanks @drvoss.
 - Hooks/webhook ACK compatibility: return `200` (instead of `202`) for successful `/hooks/agent` requests so providers that require `200` (for example Forward Email) accept dispatched agent hook deliveries. (#28204) Thanks @Glucksberg.

src/agents/pi-embedded-runner/run.ts

@@ -263,6 +263,8 @@ export async function runEmbeddedPiAgent(
         sessionId: params.sessionId,
         workspaceDir: resolvedWorkspace,
         messageProvider: params.messageProvider ?? undefined,
+        trigger: params.trigger,
+        channelId: params.messageChannel ?? params.messageProvider ?? undefined,
       };
       if (hookRunner?.hasHooks("before_model_resolve")) {
         try {
@@ -715,6 +717,7 @@ export async function runEmbeddedPiAgent(
           const attempt = await runEmbeddedAttempt({
             sessionId: params.sessionId,
             sessionKey: params.sessionKey,
+            trigger: params.trigger,
             messageChannel: params.messageChannel,
             messageProvider: params.messageProvider,
             agentAccountId: params.agentAccountId,

src/agents/pi-embedded-runner/run/attempt.ts

@@ -1356,6 +1356,8 @@ export async function runEmbeddedAttempt(
           sessionId: params.sessionId,
           workspaceDir: params.workspaceDir,
           messageProvider: params.messageProvider ?? undefined,
+          trigger: params.trigger,
+          channelId: params.messageChannel ?? params.messageProvider ?? undefined,
         };
         const hookResult = await resolvePromptBuildHookResult({
           prompt: params.prompt,

src/agents/pi-embedded-runner/run/params.ts

@@ -26,6 +26,8 @@ export type RunEmbeddedPiAgentParams = {
   messageChannel?: string;
   messageProvider?: string;
   agentAccountId?: string;
+  /** What initiated this agent run: "user", "heartbeat", "cron", or "memory". */
+  trigger?: string;
   /** Delivery target (e.g. telegram:group:123:topic:456) for topic/thread routing. */
   messageTo?: string;
   /** Thread/topic identifier for routing replies to the originating thread. */

src/auto-reply/reply/agent-runner-execution.ts

@@ -295,6 +295,7 @@ export async function runAgentTurnWithFallback(params: {
           });
           return runEmbeddedPiAgent({
             ...embeddedContext,
+            trigger: params.isHeartbeat ? "heartbeat" : "user",
             groupId: resolveGroupSessionKey(params.sessionCtx)?.id,
             groupChannel:
               params.sessionCtx.GroupChannel?.trim() ?? params.sessionCtx.GroupSubject?.trim(),

src/auto-reply/reply/agent-runner-memory.ts

@@ -487,6 +487,7 @@ export async function runMemoryFlushIfNeeded(params: {
           ...embeddedContext,
           ...senderContext,
           ...runBaseParams,
+          trigger: "memory",
           prompt: resolveMemoryFlushPromptForRun({
             prompt: memoryFlushSettings.prompt,
             cfg: params.cfg,

src/auto-reply/reply/followup-runner.ts

@@ -157,6 +157,8 @@ export function createFollowupRunner(params: {
               sessionId: queued.run.sessionId,
               sessionKey: queued.run.sessionKey,
               agentId: queued.run.agentId,
+              trigger: "user",
+              messageChannel: queued.originatingChannel ?? undefined,
               messageProvider: queued.run.messageProvider,
               agentAccountId: queued.run.agentAccountId,
               messageTo: queued.originatingTo,

src/commands/agent.ts

@@ -279,6 +279,7 @@ function runAgentAttempt(params: {
     sessionId: params.sessionId,
     sessionKey: params.sessionKey,
     agentId: params.sessionAgentId,
+    trigger: "user",
     messageChannel: params.messageChannel,
     agentAccountId: params.runContext.accountId,
     messageTo: params.opts.replyTo ?? params.opts.to,

src/cron/isolated-agent/run.ts

@@ -490,6 +490,7 @@ export async function runCronIsolatedAgentTurn(params: {
           sessionId: cronSession.sessionEntry.sessionId,
           sessionKey: agentSessionKey,
           agentId,
+          trigger: "cron",
           messageChannel,
           agentAccountId: resolvedDelivery.accountId,
           sessionFile,

src/plugins/types.ts

@@ -340,6 +340,10 @@ export type PluginHookAgentContext = {
   sessionId?: string;
   workspaceDir?: string;
   messageProvider?: string;
+  /** What initiated this agent run: "user", "heartbeat", "cron", or "memory". */
+  trigger?: string;
+  /** Channel identifier (e.g. "telegram", "discord", "whatsapp"). */
+  channelId?: string;
 };
 
 // before_model_resolve hook