feat(plugin): dialectic_list_arguments tool + clarify topic_detail desc

Two changes that fix bug #1 from the first e2e debate run (judge could
not see arguments, returned a hollow 'tie' verdict despite real pro/con
posts being in the DB):

1. New tool `dialectic_list_arguments` — hits the existing backend
   endpoint GET /api/topics/{id}/arguments and returns the full
   transcript (pro/con/judge entries with camp, agent_id, content,
   posted_at) in posted order. Used by judges composing verdicts and
   by debaters reading what opponents have said.

2. Updated `dialectic_topic_detail` description to make the split
   explicit: it returns the new camps array (added in the matching
   backend commit) so agents can locate their own allocation, but
   does NOT return arguments — list_arguments is the right tool.

Manifest contracts.tools updated (jiti loader requires this — see
[[reference-meridian-plugin-contract]]) plus internal logger count
bumped from 7 → 8 tools.

E2e verified on sim:
  - main agent calls topic_detail → sees camps array with self as 'pro'
  - judge agent calls list_arguments → reads pro/con content
  - judge rationale directly quotes claims from both sides
  - topic → completed with non-trivial binary verdict

Deploy note: jiti prefers .js when colocated; deploy must rm src/*.js
or pre-build before the new .ts takes effect (see e2e findings memory).

plugin/openclaw.plugin.json

@@ -15,7 +15,8 @@
       "dialectic_signup",
       "dialectic_post_argument",
       "dialectic_submit_verdict",
-      "dialectic_view_verdict"
+      "dialectic_view_verdict",
+      "dialectic_list_arguments"
     ]
   },
   "configSchema": {

plugin/src/tools.ts

@@ -73,8 +73,10 @@ export function registerDialecticTools(api: ToolApi): void {
   api.registerTool((ctx: { agentId?: string }) => ({
     name: 'dialectic_topic_detail',
     description:
-      'Get full detail for one Dialectic topic — lifecycle timestamps, status, ' +
+      'Get one Dialectic topic — lifecycle timestamps, status, verdict_schema_id, ' +
-      'verdict_schema_id, allocated camps if past signup_close, and verdict if completed.',
+      "and the `camps` array (0 rows pre-signup_close, 3 rows after — use this to " +
+      "find which camp YOU were allocated to: scan camps[].agent_id for your id). " +
+      "Does NOT include arguments — call dialectic_list_arguments for the transcript.",
     parameters: {
       type: 'object',
       additionalProperties: false,
@@ -88,6 +90,30 @@ export function registerDialecticTools(api: ToolApi): void {
       }),
   }));
 
+  api.registerTool((ctx: { agentId?: string }) => ({
+    name: 'dialectic_list_arguments',
+    description:
+      "Fetch the full argument transcript for a topic in posted order " +
+      "(pro / con / judge entries with author agent_id, content, posted_at). " +
+      "Use this when you need to read what other camps have argued — e.g. " +
+      "before posting your own rebuttal, or as the judge composing a verdict. " +
+      "Backend filters by topic visibility (public readable by anyone, private " +
+      "requires auth). Empty array if the topic is still pre-debate.",
+    parameters: {
+      type: 'object',
+      additionalProperties: false,
+      properties: { topic_id: { type: 'string' } },
+      required: ['topic_id'],
+    },
+    execute: async (_id: string, params: Record<string, any>) =>
+      asContent(async () => {
+        const client = new BackendClient({ baseUrl: backendUrl, agentId: ctx.agentId ?? '' });
+        return await client.get(
+          `/api/topics/${encodeURIComponent(params.topic_id)}/arguments`
+        );
+      }),
+  }));
+
   api.registerTool((ctx: { agentId?: string }) => ({
     name: 'dialectic_propose_topic',
     description:
@@ -280,7 +306,7 @@ export function registerDialecticTools(api: ToolApi): void {
       }),
   }));
 
-  api.logger.info(`[dialectic] registered 7 tools (backend=${backendUrl})`);
+  api.logger.info(`[dialectic] registered 8 tools (backend=${backendUrl})`);
 }
 
 /** Wraps an async backend call and converts result/error into MCP content shape. */