Compare commits

..

1 Commits

Author SHA1 Message Date
will.anderson edcec3bdf4 engram: add /api/nodes/reseed so a node body can be repaired at its own id
El SDK Release / build-and-release (pull_request) Failing after 11m24s
Two write paths could put a node in the graph and neither could put a body
on an id that already exists. POST /api/nodes mints a fresh id via
engram_node_full; POST /api/load-merge honors a declared id but skips
anything already present. That is right for the additive case and leaves a
hole: a node resident with a truncated body cannot be repaired.

Forge's genesis seed sits in that hole. Two of Neuron's identity nodes
carry only their own label as content -- 30 and 22 bytes against 4263 and
2590 declared. Their ids are load-bearing (is_protected_node keys on them
and 214 declared edges reference them), so recreating them under a new id
is not a repair, it is a second break.

Engram has no in-place node update, so a replace is forget-then-merge, and
engram_forget also drops every incident edge -- 85 and 93 on those two
nodes, nearly all tag edges and accumulated hebbian associations the seed
does not declare and could not restore. preserve_edges (default true)
therefore snapshots before the forget and re-merges after: the replaced
node is back by then so it is skipped, and every dropped edge returns
through the (from_id,to_id,relation) dedup. The same re-merge is the
failure path -- if the seed merge does not produce the node, the backup
puts the original back. Rollback, not data loss.

With no replace list the route is exactly /api/load-merge.

Verified on a sandbox engram seeded to mirror the live graph's state for
this seed (15 resident nodes, 694 incident edges): 87 nodes created at
their declared ids, 2 replaced in place, 214/214 edges laid, 682/682
non-seed incident edges preserved, and a second run reports 0 added.
2026-08-10 16:44:17 -05:00
+89
View File
@@ -272,6 +272,89 @@ fn route_load_merge(method: String, path: String, body: String) -> String {
"{\"ok\":true,\"nodes_added\":" + int_to_str(added_n) + ",\"edges_added\":" + int_to_str(added_e) + ",\"node_count\":" + int_to_str(engram_node_count()) + "}"
}
// route_reseed_nodes POST /api/nodes/reseed
// {"path": "<snapshot-format file>", "replace": ["<id>", ...],
// "preserve_edges": true, "_auth": "<key>"}
//
// ID-PRESERVING install/repair for declarative seed graphs.
//
// WHY THIS EXISTS (2026-08-10). Two write paths could put a node into the
// graph and neither can put a BODY onto an id that already exists:
// POST /api/nodes mints a fresh id via engram_node_full, and
// POST /api/load-merge honors the declared id but SKIPS anything already
// present. That is exactly right for the additive case and leaves one hole:
// a node that exists with a truncated body. Forge's genesis seed hit it
// two identity nodes (Voice, Voice Craft) sat in the graph carrying only
// their own label as content, 30 and 22 bytes against 4263 and 2590 in the
// seed. Their ids are load-bearing (is_protected_node keys on them and 214
// declared edges reference them), so "delete and recreate with a new id" is
// not a repair, it is a second break.
//
// Mechanism: engram has no in-place node update, so a replace is
// forget-then-merge. engram_forget also drops every INCIDENT EDGE for
// those two nodes that is 85 and 93 edges, almost all of them tag edges and
// accumulated hebbian associations that the seed does not declare and could
// not restore. preserve_edges (default true) therefore snapshots the graph
// before the forget and re-merges that snapshot afterwards: the replaced
// node is back by then so it is skipped, and every dropped incident edge
// returns through load_merge's (from_id,to_id,relation) dedup. The same
// re-merge is the failure path if the seed merge does not produce the
// node, the backup puts the original back. Rollback, not data loss.
//
// preserve_edges=false skips the two snapshot round-trips (cheap, lossy);
// use it only on a graph whose edges are fully declared by the seed.
// With no "replace" list this route is exactly /api/load-merge.
fn route_reseed_nodes(method: String, path: String, body: String) -> String {
let p: String = json_get_string(body, "path")
if str_eq(p, "") { return err_json("path is required") }
if str_eq(fs_read(p), "") { return err_json("file missing or empty") }
let dir_raw: String = env("ENGRAM_DATA_DIR")
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
let backup: String = dir + "/.reseed-backup.json"
let replace_raw: String = json_get_raw(body, "replace")
let n_replace: Int = json_array_len(replace_raw)
// Presence-aware: absent key means "preserve", only an explicit false opts out.
let pe_raw: String = json_get_raw(body, "preserve_edges")
let preserve: Bool = !str_eq(pe_raw, "false")
let before_n: Int = engram_node_count()
let before_e: Int = engram_edge_count()
let replaced: Int = 0
if n_replace > 0 {
if preserve { engram_save(backup) }
let i: Int = 0
while i < n_replace {
let rid: String = json_array_get_string(replace_raw, i)
if !str_eq(rid, "") {
// engram_get_node_json returns "{}" for a miss only forget
// ids that are actually resident, so a typo in the replace
// list is a no-op rather than a silent partial run.
let existing: String = engram_get_node_json(rid)
if !str_eq(existing, "{}") {
engram_forget(rid)
let replaced = replaced + 1
}
}
let i = i + 1
}
}
engram_load_merge(p)
if replaced > 0 {
if preserve { engram_load_merge(backup) }
}
let saved: Int = persist_canonical()
"{\"ok\":true,\"replaced\":" + int_to_str(replaced) +
",\"nodes_added\":" + int_to_str(engram_node_count() - before_n) +
",\"edges_added\":" + int_to_str(engram_edge_count() - before_e) +
",\"node_count\":" + int_to_str(engram_node_count()) +
",\"edge_count\":" + int_to_str(engram_edge_count()) + "}"
}
// route_emit_ise write an InternalStateEvent node from the soul daemon.
//
// Endpoint: POST /api/neuron/state-events
@@ -419,6 +502,12 @@ fn handle_request(method: String, path: String, body: String) -> String {
}
// Nodes
// Reseed must be tested before the exact "/api/nodes" match below reads
// as the general create path order is not load-bearing (the match is
// exact) but keeping them adjacent keeps them from drifting apart.
if str_eq(method, "POST") && (str_eq(clean, "/api/nodes/reseed") || str_eq(clean, "/nodes/reseed")) {
return route_reseed_nodes(method, path, body)
}
if str_eq(method, "POST") && (str_eq(clean, "/api/nodes") || str_eq(clean, "/nodes")) {
return route_create_node(method, path, body)
}