fix: block memory agent prose-skip responses at prompt and runtime levels

Observer prompt now explicitly requires XML observation blocks or empty
responses — prose explanations like "Skipping" are discarded. ResponseProcessor
logs a warning when non-XML content is received. Recording focus expanded to
include concrete debugging findings.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

plugin/modes/code.json

@@ -87,8 +87,8 @@
     "system_identity": "You are a Claude-Mem, a specialized observer tool for creating searchable memory FOR FUTURE SESSIONS.\n\nCRITICAL: Record what was LEARNED/BUILT/FIXED/DEPLOYED/CONFIGURED, not what you (the observer) are doing.\n\nYou do not have access to tools. All information you need is provided in <observed_from_primary_session> messages. Create observations from what you observe - no investigation needed.",
     "spatial_awareness": "SPATIAL AWARENESS: Tool executions include the working directory (tool_cwd) to help you understand:\n- Which repository/project is being worked on\n- Where files are located relative to the project root\n- How to match requested paths to actual execution paths",
     "observer_role": "Your job is to monitor a different Claude Code session happening RIGHT NOW, with the goal of creating observations and progress summaries as the work is being done LIVE by the user. You are NOT the one doing the work - you are ONLY observing and recording what is being built, fixed, deployed, or configured in the other session.",
-    "recording_focus": "WHAT TO RECORD\n--------------\nFocus on deliverables and capabilities:\n- What the system NOW DOES differently (new capabilities)\n- What shipped to users/production (features, fixes, configs, docs)\n- Changes in technical domains (auth, data, UI, infra, DevOps, docs)\n\nUse verbs like: implemented, fixed, deployed, configured, migrated, optimized, added, refactored\n\n✅ GOOD EXAMPLES (describes what was built):\n- \"Authentication now supports OAuth2 with PKCE flow\"\n- \"Deployment pipeline runs canary releases with auto-rollback\"\n- \"Database indexes optimized for common query patterns\"\n\n❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS):\n- \"Analyzed authentication implementation and stored findings\"\n- \"Tracked deployment steps and logged outcomes\"\n- \"Monitored database performance and recorded metrics\"",
+    "recording_focus": "WHAT TO RECORD\n--------------\nFocus on durable technical signal:\n- What the system NOW DOES differently (new capabilities)\n- What shipped to users/production (features, fixes, configs, docs)\n- Changes in technical domains (auth, data, UI, infra, DevOps, docs)\n- Concrete debugging or investigative findings from logs, traces, queue state, database rows, and code-path inspection\n\nUse verbs like: implemented, fixed, deployed, configured, migrated, optimized, added, refactored, discovered, confirmed, traced\n\n✅ GOOD EXAMPLES (describes what was built or learned):\n- \"Authentication now supports OAuth2 with PKCE flow\"\n- \"Deployment pipeline runs canary releases with auto-rollback\"\n- \"Database indexes optimized for common query patterns\"\n- \"Observation queue for claude-mem session timed out waiting for an agent pool slot\"\n- \"Fallback processing abandoned pending messages after Gemini and OpenRouter returned 404\"\n\n❌ BAD EXAMPLES (describes observation process - DO NOT DO THIS):\n- \"Analyzed authentication implementation and stored findings\"\n- \"Tracked deployment steps and logged outcomes\"\n- \"Monitored database performance and recorded metrics\"",
-    "skip_guidance": "WHEN TO SKIP\n------------\nSkip routine operations:\n- Empty status checks\n- Package installations with no errors\n- Simple file listings\n- Repetitive operations you've already documented\n- If file related research comes back as empty or not found\n- **No output necessary if skipping.**",
+    "skip_guidance": "WHEN TO SKIP\n------------\nSkip routine operations:\n- Empty status checks\n- Package installations with no errors\n- Simple file listings with no follow-on finding\n- Repetitive operations you've already documented\n- File related research that comes back empty or not found\n\nIf skipping, return an empty response only. Do not explain the skip in prose.",
     "type_guidance": "**type**: MUST be EXACTLY one of these 6 options (no other values allowed):\n      - bugfix: something was broken, now fixed\n      - feature: new capability or functionality added\n      - refactor: code restructured, behavior unchanged\n      - change: generic modification (docs, config, misc)\n      - discovery: learning about existing system\n      - decision: architectural/design choice with rationale",
     "concept_guidance": "**concepts**: 2-5 knowledge-type categories. MUST use ONLY these exact keywords:\n      - how-it-works: understanding mechanisms\n      - why-it-exists: purpose or rationale\n      - what-changed: modifications made\n      - problem-solution: issues and their fixes\n      - gotcha: traps or edge cases\n      - pattern: reusable approach\n      - trade-off: pros/cons of a decision\n\n    IMPORTANT: Do NOT include the observation type (change/discovery/decision) as a concept.\n    Types and concepts are separate dimensions.",
     "field_guidance": "**facts**: Concise, self-contained statements\nEach fact is ONE piece of information\n      No pronouns - each fact must stand alone\n      Include specific details: filenames, functions, values\n\n**files**: All files touched (full paths from project root)",

src/sdk/prompts.ts

@@ -116,7 +116,11 @@ export function buildObservationPrompt(obs: Observation): string {
   <occurred_at>${new Date(obs.created_at_epoch).toISOString()}</occurred_at>${obs.cwd ? `\n  <working_directory>${obs.cwd}</working_directory>` : ''}
   <parameters>${JSON.stringify(toolInput, null, 2)}</parameters>
   <outcome>${JSON.stringify(toolOutput, null, 2)}</outcome>
-</observed_from_primary_session>`;
+</observed_from_primary_session>
+
+Return either one or more <observation>...</observation> blocks, or an empty response if this tool use should be skipped.
+Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection count as durable discoveries and should be recorded.
+Never reply with prose such as "Skipping", "No substantive tool executions", or any explanation outside XML. Non-XML text is discarded.`;
 }
 
 /**

src/services/worker/agents/ResponseProcessor.ts

@@ -68,6 +68,19 @@ export async function processAgentResponse(
   const observations = parseObservations(text, session.contentSessionId);
   const summary = parseSummary(text, session.sessionDbId);
 
+  if (
+    text.trim() &&
+    observations.length === 0 &&
+    !summary &&
+    !/<observation>|<summary>|<skip_summary\b/.test(text)
+  ) {
+    const preview = text.length > 200 ? `${text.slice(0, 200)}...` : text;
+    logger.warn('PARSER', `${agentName} returned non-XML response; observation content was discarded`, {
+      sessionId: session.sessionDbId,
+      preview
+    });
+  }
+
   // Convert nullable fields to empty strings for storeSummary (if summary exists)
   const summaryForStore = normalizeSummaryForStorage(summary);
 

tests/sdk/prompts.test.ts

@@ -0,0 +1,20 @@
+import { describe, expect, it } from 'bun:test';
+
+import { buildObservationPrompt } from '../../src/sdk/prompts.js';
+
+describe('buildObservationPrompt', () => {
+  it('instructs the observer to avoid prose skip responses', () => {
+    const prompt = buildObservationPrompt({
+      id: 1,
+      tool_name: 'exec_command',
+      tool_input: JSON.stringify({ cmd: 'pwd' }),
+      tool_output: JSON.stringify({ output: '/repo' }),
+      created_at_epoch: Date.now(),
+      cwd: '/repo',
+    });
+
+    expect(prompt).toContain('Return either one or more <observation>...</observation> blocks, or an empty response');
+    expect(prompt).toContain('Concrete debugging findings from logs, queue state, database rows, session routing, or code-path inspection');
+    expect(prompt).toContain('Never reply with prose such as "Skipping", "No substantive tool executions"');
+  });
+});

tests/worker/agents/response-processor.test.ts

@@ -212,6 +212,36 @@ describe('ResponseProcessor', () => {
     });
   });
 
+  describe('non-XML observer responses', () => {
+    it('warns when the observer returns prose that will be discarded', async () => {
+      const session = createMockSession();
+      const responseText = 'Skipping — repeated log scan with no new findings.';
+
+      await processAgentResponse(
+        responseText,
+        session,
+        mockDbManager,
+        mockSessionManager,
+        mockWorker,
+        100,
+        null,
+        'TestAgent'
+      );
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        'PARSER',
+        'TestAgent returned non-XML response; observation content was discarded',
+        expect.objectContaining({
+          sessionId: 1,
+          preview: responseText
+        })
+      );
+      const [, , observations, summary] = mockStoreObservations.mock.calls[0];
+      expect(observations).toHaveLength(0);
+      expect(summary).toBeNull();
+    });
+  });
+
   describe('parsing summary from XML response', () => {
     it('should parse summary from response', async () => {
       const session = createMockSession();