feat(agent): Ed25519-signed checkpoints

Makes the README's "cryptographically verifiable memory" true.

With HDF5Memory::set_signing_key(key), every checkpoint stores a signed
manifest of the store: a SHA-256 per memory record (text, embedding as
stored, channel, timestamp, session, tags, deleted flag, activation) in
a Merkle tree, plus hashes of the settings (and WAL mark), sessions and
knowledge graph. The signature, public key and manifest hashes go in
/meta; the per-record hashes in /integrity/record_hashes, so
HDF5Memory::verify(path, &public_key) can say which records changed, not
just that something did. A forged manifest fails the signature.

Decisions, as agreed:
- the key is set on the open store and never persisted;
- a signed store refuses to checkpoint without its key
  (MemoryError::SigningKeyRequired); remove_signature() is the
  deliberate way back to unsigned;
- checkpoints only: saves still in the WAL are not covered, and verify
  reports how many there are.

The hashes cover exactly what the file persists, in the form the loader
returns it (strings lose trailing NULs; an empty WAL mark is not
written), so untouched stores verify across any number of reopen and
checkpoint cycles. MemoryError becomes #[non_exhaustive] (it already
gains variants in this unreleased version).

CLI: keygen (owner-only key file), --signing-key / CLAWHDF5_SIGNING_KEY
on writing commands (create signs immediately), verify --public-key
(JSON; exit 2 if not valid), `signed` in create/stats output.

Tests: reopen/checkpoint cycles with awkward strings (f16 and f32),
refusal without the key, wrong and rotated keys, eight kinds of edit
each detected and located, a forged manifest, unsigned stores, NULs in
text, and an edit made in place with h5py that verify pinpoints.

Cost on tank (search_harness --signing-study --full, 3 runs): ~20% of a
checkpoint (+9 ms at 10K, +89-112 ms at 100K), verify 18.6 ms / 247 ms,
32 bytes per record in the file. New deps ed25519-dalek, sha2,
rand_core: pure Rust, the no-C check passes.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-cli/src/main.rs

@@ -1,15 +1,22 @@
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 
 use clap::{Parser, Subcommand};
+use clawhdf5_agent::signing::{self, SigningKey, VerifyingKey};
 use clawhdf5_agent::{AgentMemory, HDF5Memory, MemoryConfig, MemoryEntry};
 
 /// ClawhDF5 — HDF5-backed cognitive memory for AI agents
 #[derive(Parser)]
 #[command(name = "clawhdf5", version, about)]
 struct Cli {
-    /// Path to the .h5 memory file
+    /// Path to the .h5 memory file (not needed for `keygen`)
     #[arg(short, long, env = "CLAWHDF5_PATH")]
-    path: PathBuf,
+    path: Option<PathBuf>,
+
+    /// File holding an Ed25519 signing key (64 hex characters, from
+    /// `keygen`). Every checkpoint this command makes is then signed; a
+    /// signed store refuses to checkpoint without it.
+    #[arg(long, env = "CLAWHDF5_SIGNING_KEY", global = true)]
+    signing_key: Option<PathBuf>,
 
     #[command(subcommand)]
     command: Commands,
@@ -91,6 +98,38 @@ enum Commands {
         /// Destination path
         dest: PathBuf,
     },
+    /// Generate an Ed25519 signing key for signed checkpoints
+    Keygen {
+        /// Where to write the secret key (created new, owner-only on Unix)
+        #[arg(long)]
+        out: PathBuf,
+    },
+    /// Verify a signed store against a public key; exit status 2 if not valid
+    Verify {
+        /// The trusted public key: 64 hex characters, or a file holding them
+        #[arg(long)]
+        public_key: String,
+    },
+}
+
+fn read_signing_key(path: &Path) -> Result<SigningKey, Box<dyn std::error::Error>> {
+    let text = std::fs::read_to_string(path)
+        .map_err(|e| format!("cannot read signing key {}: {e}", path.display()))?;
+    let bytes = signing::from_hex::<32>(&text)
+        .ok_or_else(|| format!("{} is not a 64-hex-character key", path.display()))?;
+    Ok(SigningKey::from_bytes(&bytes))
+}
+
+/// Open for writing, with the signing key applied if one was given.
+fn open_writable(
+    path: &Path,
+    key: &Option<SigningKey>,
+) -> Result<HDF5Memory, Box<dyn std::error::Error>> {
+    let mut mem = HDF5Memory::open(path)?;
+    if let Some(k) = key {
+        mem.set_signing_key(k.clone());
+    }
+    Ok(mem)
 }
 
 fn main() {
@@ -103,6 +142,37 @@ fn main() {
 }
 
 fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
+    if let Commands::Keygen { out } = &cli.command {
+        let key = signing::generate_key();
+        let mut opts = std::fs::OpenOptions::new();
+        opts.write(true).create_new(true);
+        #[cfg(unix)]
+        {
+            use std::os::unix::fs::OpenOptionsExt;
+            opts.mode(0o600);
+        }
+        use std::io::Write;
+        let mut f = opts
+            .open(out)
+            .map_err(|e| format!("cannot create {}: {e}", out.display()))?;
+        writeln!(f, "{}", signing::to_hex(&key.to_bytes()))?;
+        let j = serde_json::json!({
+            "status": "generated",
+            "secret_key_file": out.display().to_string(),
+            "public_key": signing::to_hex(&key.verifying_key().to_bytes()),
+        });
+        println!("{}", serde_json::to_string_pretty(&j)?);
+        return Ok(());
+    }
+    let path = cli
+        .path
+        .clone()
+        .ok_or("--path (or CLAWHDF5_PATH) is required")?;
+    let key = cli
+        .signing_key
+        .as_deref()
+        .map(read_signing_key)
+        .transpose()?;
     match cli.command {
         Commands::Create {
             agent_id,
@@ -113,7 +183,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
             f32,
             float16: _,
         } => {
-            let mut config = MemoryConfig::new(cli.path.clone(), &agent_id, dim);
+            let mut config = MemoryConfig::new(path.clone(), &agent_id, dim);
             config.wal_enabled = wal;
             // As with --f32-index: only ever switch the library default off.
             if f32 {
@@ -127,15 +197,21 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
                 config.quantized_index = false;
             }
             let config_quantized = config.quantized_index;
-            let mem = HDF5Memory::create(config)?;
+            let mut mem = HDF5Memory::create(config)?;
+            // Sign straight away, so the store is never on disk unsigned.
+            if let Some(k) = &key {
+                mem.set_signing_key(k.clone());
+                mem.flush_wal()?;
+            }
             let j = serde_json::json!({
                 "status": "created",
-                "path": cli.path.display().to_string(),
+                "path": path.display().to_string(),
                 "agent_id": agent_id,
                 "embedding_dim": dim,
                 "wal_enabled": wal,
                 "quantized_index": config_quantized,
                 "float16": config_float16,
+                "signed": mem.is_signed(),
                 "count": mem.count(),
             });
             println!("{}", serde_json::to_string_pretty(&j)?);
@@ -152,7 +228,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
                 }
             };
             let entry: MemoryEntry = serde_json::from_str(&input)?;
-            let mut mem = HDF5Memory::open(&cli.path)?;
+            let mut mem = open_writable(&path, &key)?;
             let idx = mem.save(entry)?;
             let j = serde_json::json!({ "status": "saved", "index": idx, "count": mem.count() });
             println!("{}", serde_json::to_string(&j)?);
@@ -166,7 +242,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
             keyword_weight,
         } => {
             let emb: Vec<f32> = serde_json::from_str(&embedding)?;
-            let mut mem = HDF5Memory::open(&cli.path)?;
+            let mut mem = open_writable(&path, &key)?;
             let results = mem.hybrid_search(&emb, &query, vector_weight, keyword_weight, top_k);
             let j: Vec<serde_json::Value> = results
                 .iter()
@@ -184,7 +260,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
         }
 
         Commands::Recall { index } => {
-            let mem = HDF5Memory::open_read_only(&cli.path)?;
+            let mem = HDF5Memory::open_read_only(&path)?;
             match mem.get_chunk(index) {
                 Some(content) => {
                     let j = serde_json::json!({ "index": index, "chunk": content });
@@ -198,22 +274,23 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
         }
 
         Commands::Stats => {
-            let mem = HDF5Memory::open_read_only(&cli.path)?;
+            let mem = HDF5Memory::open_read_only(&path)?;
             let cfg = mem.config();
             let j = serde_json::json!({
-                "path": cli.path.display().to_string(),
+                "path": path.display().to_string(),
                 "agent_id": cfg.agent_id,
                 "embedding_dim": cfg.embedding_dim,
                 "count": mem.count(),
                 "active": mem.count_active(),
                 "wal_enabled": cfg.wal_enabled,
                 "wal_pending": mem.wal_pending_count(),
+                "signed": mem.is_signed(),
             });
             println!("{}", serde_json::to_string_pretty(&j)?);
         }
 
         Commands::FlushWal => {
-            let mut mem = HDF5Memory::open(&cli.path)?;
+            let mut mem = open_writable(&path, &key)?;
             let before = mem.wal_pending_count();
             mem.flush_wal()?;
             let j = serde_json::json!({
@@ -225,7 +302,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
         }
 
         Commands::AgentsMd { output } => {
-            let mem = HDF5Memory::open_read_only(&cli.path)?;
+            let mem = HDF5Memory::open_read_only(&path)?;
             let md = mem.generate_agents_md();
             match output {
                 Some(p) => {
@@ -237,7 +314,7 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
         }
 
         Commands::Export => {
-            let mem = HDF5Memory::open_read_only(&cli.path)?;
+            let mem = HDF5Memory::open_read_only(&path)?;
             for i in 0..mem.count() {
                 if let Some(chunk) = mem.get_chunk(i) {
                     let j = serde_json::json!({ "index": i, "chunk": chunk });
@@ -246,11 +323,44 @@ fn run(cli: Cli) -> Result<(), Box<dyn std::error::Error>> {
             }
         }
 
+        Commands::Keygen { .. } => unreachable!("handled before opening a store"),
+
+        Commands::Verify { public_key } => {
+            let text = if Path::new(&public_key).is_file() {
+                std::fs::read_to_string(&public_key)?
+            } else {
+                public_key
+            };
+            let bytes = signing::from_hex::<32>(&text)
+                .ok_or("--public-key must be 64 hex characters or a file holding them")?;
+            let trusted = VerifyingKey::from_bytes(&bytes)?;
+            let r = HDF5Memory::verify(&path, &trusted)?;
+            let j = serde_json::json!({
+                "valid": r.is_valid(),
+                "signed": r.signed,
+                "key_matches": r.key_matches,
+                "signature_valid": r.signature_valid,
+                "records_match": r.records_match,
+                "settings_match": r.settings_match,
+                "sessions_match": r.sessions_match,
+                "graph_match": r.graph_match,
+                "changed_records": r.changed_records,
+                "record_count": r.record_count,
+                "signed_record_count": r.signed_record_count,
+                "signed_by": r.public_key.map(|k| signing::to_hex(&k)),
+                "wal_entries_unsigned": r.wal_entries_unsigned,
+            });
+            println!("{}", serde_json::to_string_pretty(&j)?);
+            if !r.is_valid() {
+                std::process::exit(2);
+            }
+        }
+
         Commands::Snapshot { dest } => {
-            let _result = clawhdf5_agent::storage::snapshot_file(&cli.path, &dest)?;
+            let _result = clawhdf5_agent::storage::snapshot_file(&path, &dest)?;
             let j = serde_json::json!({
                 "status": "snapshot_created",
-                "source": cli.path.display().to_string(),
+                "source": path.display().to_string(),
                 "dest": dest.display().to_string(),
             });
             println!("{}", serde_json::to_string(&j)?);