memory-search: chunk context output for hook delivery

Claude Code's hook output limit (~10K chars) was truncating the full
context load. Split output into chunks at section boundaries, deliver
first chunk on UserPromptSubmit, save remaining chunks to disk for
drip-feeding on subsequent PostToolUse calls.

Two-pass algorithm: split at "--- KEY (group) ---" boundaries, then
merge adjacent small sections up to 9K per chunk. Separates session_id
guard (needed for chunk state) from prompt guard (needed only for
search), so PostToolUse events without a prompt can still pop chunks.

poc-memory/src/bin/memory-search.rs

@@ -45,6 +45,8 @@ struct Args {
 }
 
 const STASH_PATH: &str = "/tmp/claude-memory-search/last-input.json";
+/// Max bytes per context chunk (hook output limit is ~10K chars)
+const CHUNK_SIZE: usize = 9000;
 
 fn main() {
     // Daemon agent calls set POC_AGENT=1 — skip memory search.
@@ -84,7 +86,7 @@ fn main() {
     let prompt = json["prompt"].as_str().unwrap_or("");
     let session_id = json["session_id"].as_str().unwrap_or("");
 
-    if prompt.is_empty() || session_id.is_empty() {
+    if session_id.is_empty() {
         return;
     }
 
@@ -123,12 +125,12 @@ fn main() {
 
         if debug { println!("[memory-search] loading full context"); }
 
-        // Load full memory context and pre-populate seen set with injected keys
+        // Load full memory context, chunk it, print first chunk, save rest
         if let Ok(output) = Command::new("poc-memory").args(["load-context"]).output() {
             if output.status.success() {
-                let ctx = String::from_utf8_lossy(&output.stdout);
+                let ctx = String::from_utf8_lossy(&output.stdout).to_string();
                 if !ctx.trim().is_empty() {
-                    // Extract keys from "--- KEY (group) ---" lines
+                    // Extract keys from all chunks for seen set
                     for line in ctx.lines() {
                         if line.starts_with("--- ") && line.ends_with(" ---") {
                             let inner = &line[4..line.len() - 4];
@@ -138,15 +140,42 @@ fn main() {
                             }
                         }
                     }
-                    if debug { println!("[memory-search] context loaded: {} bytes", ctx.len()); }
+
-                    if args.hook {
+                    let chunks = chunk_context(&ctx, CHUNK_SIZE);
-                        print!("{}", ctx);
+                    if debug {
+                        println!("[memory-search] context: {} bytes, {} chunks",
+                            ctx.len(), chunks.len());
                     }
+
+                    // Print first chunk
+                    if let Some(first) = chunks.first() {
+                        if args.hook {
+                            print!("{}", first);
+                        }
+                    }
+
+                    // Save remaining chunks for drip-feeding
+                    save_pending_chunks(&state_dir, session_id, &chunks[1..]);
                 }
             }
         }
 
         let _ = cookie;
+    } else {
+        // Not first call: drip-feed next pending chunk
+        if let Some(chunk) = pop_pending_chunk(&state_dir, session_id) {
+            if debug {
+                println!("[memory-search] drip-feeding pending chunk: {} bytes", chunk.len());
+            }
+            if args.hook {
+                print!("{}", chunk);
+            }
+        }
+    }
+
+    // Search requires a prompt (PostToolUse events don't have one)
+    if prompt.is_empty() {
+        return;
     }
 
     // Skip system/AFK prompts
@@ -288,6 +317,82 @@ fn main() {
 }
 
 
+/// Split context output into chunks of approximately `max_bytes`, breaking
+/// at section boundaries ("--- KEY (group) ---" lines).
+fn chunk_context(ctx: &str, max_bytes: usize) -> Vec<String> {
+    // Split into sections at group boundaries, then merge small adjacent
+    // sections into chunks up to max_bytes.
+    let mut sections: Vec<String> = Vec::new();
+    let mut current = String::new();
+
+    for line in ctx.lines() {
+        // Group headers start new sections
+        if line.starts_with("--- ") && line.ends_with(" ---") && !current.is_empty() {
+            sections.push(std::mem::take(&mut current));
+        }
+        if !current.is_empty() {
+            current.push('\n');
+        }
+        current.push_str(line);
+    }
+    if !current.is_empty() {
+        sections.push(current);
+    }
+
+    // Merge small sections into chunks, respecting max_bytes
+    let mut chunks: Vec<String> = Vec::new();
+    let mut chunk = String::new();
+    for section in sections {
+        if !chunk.is_empty() && chunk.len() + section.len() + 1 > max_bytes {
+            chunks.push(std::mem::take(&mut chunk));
+        }
+        if !chunk.is_empty() {
+            chunk.push('\n');
+        }
+        chunk.push_str(&section);
+    }
+    if !chunk.is_empty() {
+        chunks.push(chunk);
+    }
+    chunks
+}
+
+/// Save remaining chunks to disk for drip-feeding on subsequent hook calls.
+fn save_pending_chunks(dir: &Path, session_id: &str, chunks: &[String]) {
+    let chunks_dir = dir.join(format!("chunks-{}", session_id));
+    // Clear any old chunks
+    let _ = fs::remove_dir_all(&chunks_dir);
+    if chunks.is_empty() { return; }
+    fs::create_dir_all(&chunks_dir).ok();
+    for (i, chunk) in chunks.iter().enumerate() {
+        let path = chunks_dir.join(format!("{:04}", i));
+        fs::write(path, chunk).ok();
+    }
+}
+
+/// Pop the next pending chunk (lowest numbered file). Returns None if no chunks remain.
+fn pop_pending_chunk(dir: &Path, session_id: &str) -> Option<String> {
+    let chunks_dir = dir.join(format!("chunks-{}", session_id));
+    if !chunks_dir.exists() { return None; }
+
+    let mut entries: Vec<_> = fs::read_dir(&chunks_dir).ok()?
+        .flatten()
+        .filter(|e| e.file_type().map(|t| t.is_file()).unwrap_or(false))
+        .collect();
+    entries.sort_by_key(|e| e.file_name());
+
+    let first = entries.first()?;
+    let content = fs::read_to_string(first.path()).ok()?;
+    fs::remove_file(first.path()).ok();
+
+    // Clean up directory if empty
+    if fs::read_dir(&chunks_dir).ok().map(|mut d| d.next().is_none()).unwrap_or(true) {
+        fs::remove_dir(&chunks_dir).ok();
+    }
+
+    Some(content)
+}
+
 /// Reverse-scan the transcript JSONL, extracting text from user/assistant
 /// messages until we accumulate `max_tokens` tokens of text content.
 /// Then search for all node keys as substrings, weighted by position.