Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 5743568bf1 | |||
| 9fd8c11670 | |||
| be0f9d1afe | |||
| 1742d0b575 | |||
| c6772e3d27 | |||
| 9501e4ac12 | |||
| dd952c0e46 |
@@ -63,6 +63,16 @@ jobs:
|
|||||||
cp vendor/el-runtime/v1.0.0-20260501/el_runtime.h /opt/el/runtime/el_runtime.h
|
cp vendor/el-runtime/v1.0.0-20260501/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||||
echo "El runtime PINNED to v1.0.0-20260501: $(ls /opt/el/runtime/)"
|
echo "El runtime PINNED to v1.0.0-20260501: $(ls /opt/el/runtime/)"
|
||||||
|
|
||||||
|
# neuron#133: CI compiles dist/soul.c, NOT the .el sources. On 2026-08-07 a
|
||||||
|
# build off main would have shipped an engine with none of five merged fixes,
|
||||||
|
# including a P0 safety fix, while main's source read as correct. The runner
|
||||||
|
# cannot regenerate the amalgam (elc needs 24GB+ virtual memory), but it can
|
||||||
|
# refuse to compile a stale one. Fails loudly with the recipe in the message.
|
||||||
|
- name: Verify dist/soul.c matches the sources
|
||||||
|
run: |
|
||||||
|
chmod +x tools/soulc-stamp.sh
|
||||||
|
./tools/soulc-stamp.sh --check
|
||||||
|
|
||||||
- name: Build neuron soul binary
|
- name: Build neuron soul binary
|
||||||
run: |
|
run: |
|
||||||
RUNTIME=/opt/el/runtime
|
RUNTIME=/opt/el/runtime
|
||||||
|
|||||||
@@ -889,10 +889,29 @@ fn awareness_run() -> Void {
|
|||||||
state_set("soul.last_beat_ts", int_to_str(now_ts))
|
state_set("soul.last_beat_ts", int_to_str(now_ts))
|
||||||
// Persist in-process Engram (sessions, memories, conversation nodes)
|
// Persist in-process Engram (sessions, memories, conversation nodes)
|
||||||
// to local snapshot so they survive restarts.
|
// to local snapshot so they survive restarts.
|
||||||
|
// FILE MODE ONLY: "soul_snapshot_path" is set exclusively in the
|
||||||
|
// genesis+safe_to_seed branch of soul.el, and safe_to_seed is
|
||||||
|
// unconditionally false when ENGRAM_URL is set. In HTTP mode the
|
||||||
|
// owner persists; the soul must not (soul.el:571-573).
|
||||||
let snap_path: String = state_get("soul_snapshot_path")
|
let snap_path: String = state_get("soul_snapshot_path")
|
||||||
if !str_eq(snap_path, "") {
|
if !str_eq(snap_path, "") {
|
||||||
mem_save(snap_path)
|
mem_save(snap_path)
|
||||||
}
|
}
|
||||||
|
// WRITE-THROUGH RETRY (neuron#117). The HTTP-mode counterpart of the
|
||||||
|
// save above: hand anything still spooled to the persistence owner.
|
||||||
|
//
|
||||||
|
// This is the retry arm of the whole design. Deltas that could not be
|
||||||
|
// pushed — owner down, owner restarting, transient refusal — stay on
|
||||||
|
// disk and are re-offered here every heartbeat until they land. It is
|
||||||
|
// also the catch-all for writes made by the awareness loop itself,
|
||||||
|
// which never passes through the HTTP handler's flush point.
|
||||||
|
//
|
||||||
|
// No-op with no HTTP call when the spool is empty or ENGRAM_URL is
|
||||||
|
// unset, so an idle soul in file mode pays nothing for this.
|
||||||
|
let wt_pushed: Int = wt_drain()
|
||||||
|
if wt_pushed < 0 {
|
||||||
|
ise_post("{\"event\":\"write_through_backlog\",\"ts\":" + int_to_str(now_ts) + "}")
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Curiosity scan: idle-gated AND wall-clock based. Only fires when the
|
// Curiosity scan: idle-gated AND wall-clock based. Only fires when the
|
||||||
|
|||||||
@@ -1162,7 +1162,7 @@ fn hist_trim_with_bell_guard(hist: String) -> String {
|
|||||||
+ " | evicted_at:" + ts_str
|
+ " | evicted_at:" + ts_str
|
||||||
+ " | message:" + safe_content
|
+ " | message:" + safe_content
|
||||||
let preserve_tags: String = "[\"bell-history\",\"bell:" + bell_level + "\",\"evicted\",\"affective\",\"BellEvent\"]"
|
let preserve_tags: String = "[\"bell-history\",\"bell:" + bell_level + "\",\"evicted\",\"affective\",\"BellEvent\"]"
|
||||||
let discard: String = engram_node_full(
|
let discard: String = wt_node(
|
||||||
preserve_content,
|
preserve_content,
|
||||||
"BellEvent",
|
"BellEvent",
|
||||||
"bell:" + bell_level + ":preserved",
|
"bell:" + bell_level + ":preserved",
|
||||||
@@ -1210,7 +1210,7 @@ fn conv_history_persist(session_id: String, hist: String) -> Void {
|
|||||||
if !str_contains(hist, "]") { return "" }
|
if !str_contains(hist, "]") { return "" }
|
||||||
let tags: String = "[\"conv-history\",\"persistent\"]"
|
let tags: String = "[\"conv-history\",\"persistent\"]"
|
||||||
// FIX B: one label rule, shared with the agentic path. See conv_hist_label.
|
// FIX B: one label rule, shared with the agentic path. See conv_hist_label.
|
||||||
let node_id: String = engram_node_full(
|
let node_id: String = wt_node(
|
||||||
hist, "Conversation", conv_hist_label(session_id),
|
hist, "Conversation", conv_hist_label(session_id),
|
||||||
el_from_float(0.7), el_from_float(0.8), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.8), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -3461,7 +3461,7 @@ fn handle_dharma_room_turn(body: String) -> String {
|
|||||||
// engram_node(content, "episodic", ...) which wrongly put a TIER into the node_type
|
// engram_node(content, "episodic", ...) which wrongly put a TIER into the node_type
|
||||||
// slot — that's why nodes showed node_type="episodic". Use the full, correct contract.)
|
// slot — that's why nodes showed node_type="episodic". Use the full, correct contract.)
|
||||||
let utterance_tags: String = "[\"soul-utterance\",\"episodic\"]"
|
let utterance_tags: String = "[\"soul-utterance\",\"episodic\"]"
|
||||||
let discard_id: String = engram_node_full(
|
let discard_id: String = wt_node(
|
||||||
clean_response, "Conversation", "soul:utterance",
|
clean_response, "Conversation", "soul:utterance",
|
||||||
el_from_float(0.6), el_from_float(0.6), el_from_float(0.8),
|
el_from_float(0.6), el_from_float(0.6), el_from_float(0.8),
|
||||||
"Episodic", utterance_tags
|
"Episodic", utterance_tags
|
||||||
@@ -3552,7 +3552,7 @@ fn session_summary_write(summary_text: String) -> String {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
let tags: String = "[\"SessionSummary\",\"session-summary\",\"previous-session\",\"consolidate\"]"
|
let tags: String = "[\"SessionSummary\",\"session-summary\",\"previous-session\",\"consolidate\"]"
|
||||||
let node_id: String = engram_node_full(
|
let node_id: String = wt_node(
|
||||||
content, "SessionSummary", "session:summary",
|
content, "SessionSummary", "session:summary",
|
||||||
el_from_float(0.85), el_from_float(0.85), el_from_float(1.0),
|
el_from_float(0.85), el_from_float(0.85), el_from_float(1.0),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -3578,7 +3578,7 @@ fn session_summary_write_dated(summary_text: String, label: String) -> String {
|
|||||||
let ts_str: String = int_to_str(ts)
|
let ts_str: String = int_to_str(ts)
|
||||||
let content: String = "[session-summary] " + trimmed + " | ts:" + ts_str
|
let content: String = "[session-summary] " + trimmed + " | ts:" + ts_str
|
||||||
let tags: String = "[\"SessionSummary\",\"session-summary\",\"previous-session\",\"consolidate\"]"
|
let tags: String = "[\"SessionSummary\",\"session-summary\",\"previous-session\",\"consolidate\"]"
|
||||||
let node_id: String = engram_node_full(
|
let node_id: String = wt_node(
|
||||||
content, "SessionSummary", label,
|
content, "SessionSummary", label,
|
||||||
el_from_float(0.9), el_from_float(0.8), el_from_float(1.0),
|
el_from_float(0.9), el_from_float(0.8), el_from_float(1.0),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -3654,7 +3654,7 @@ fn auto_persist(req: String, resp: String) -> Void {
|
|||||||
+ ",\"bell\":\"" + bell_level + "\""
|
+ ",\"bell\":\"" + bell_level + "\""
|
||||||
+ ",\"label\":\"chat:" + ts_str + "\"}"
|
+ ",\"label\":\"chat:" + ts_str + "\"}"
|
||||||
|
|
||||||
let conv_node_id: String = engram_node_full(
|
let conv_node_id: String = wt_node(
|
||||||
content,
|
content,
|
||||||
"Conversation",
|
"Conversation",
|
||||||
"chat:" + ts_str,
|
"chat:" + ts_str,
|
||||||
@@ -3692,7 +3692,7 @@ fn auto_persist(req: String, resp: String) -> Void {
|
|||||||
let bell_tags: String = "[\"safety\",\"bell\",\"bell:" + bell_level + "\",\"affective\",\"BellEvent\"]"
|
let bell_tags: String = "[\"safety\",\"bell\",\"bell:" + bell_level + "\",\"affective\",\"BellEvent\"]"
|
||||||
let bell_ts_str: String = int_to_str(time_now())
|
let bell_ts_str: String = int_to_str(time_now())
|
||||||
let bell_label: String = "bell:" + bell_level + ":" + bell_ts_str
|
let bell_label: String = "bell:" + bell_level + ":" + bell_ts_str
|
||||||
let bell_node_id: String = engram_node_full(
|
let bell_node_id: String = wt_node(
|
||||||
bell_content,
|
bell_content,
|
||||||
"BellEvent",
|
"BellEvent",
|
||||||
bell_label,
|
bell_label,
|
||||||
@@ -3751,7 +3751,7 @@ fn auto_persist(req: String, resp: String) -> Void {
|
|||||||
let pos_tags: String = "[\"joy\",\"positive\",\"joy:" + positive_level + "\",\"affective\",\"PositiveEvent\"]"
|
let pos_tags: String = "[\"joy\",\"positive\",\"joy:" + positive_level + "\",\"affective\",\"PositiveEvent\"]"
|
||||||
let pos_ts_label: String = int_to_str(time_now())
|
let pos_ts_label: String = int_to_str(time_now())
|
||||||
let pos_label: String = "joy:" + positive_level + ":" + pos_ts_label
|
let pos_label: String = "joy:" + positive_level + ":" + pos_ts_label
|
||||||
let pos_node_id: String = engram_node_full(
|
let pos_node_id: String = wt_node(
|
||||||
pos_content, "PositiveEvent", pos_label,
|
pos_content, "PositiveEvent", pos_label,
|
||||||
pos_sal_a, pos_sal_b, pos_sal_c, "Episodic", pos_tags
|
pos_sal_a, pos_sal_b, pos_sal_c, "Episodic", pos_tags
|
||||||
)
|
)
|
||||||
|
|||||||
+1384
-664
File diff suppressed because one or more lines are too long
+18
@@ -0,0 +1,18 @@
|
|||||||
|
# soul.c.stamp — fingerprint of the .el sources dist/soul.c was generated from.
|
||||||
|
# Written by tools/soulc-stamp.sh --write. Do not hand-edit.
|
||||||
|
# generated_amalgam_sha256 e31f760de5f6629cd37bcfd26172f92be3ca5d6ff36480f6adafa1d4a1de5a66
|
||||||
|
# generated_amalgam_bytes 1179122
|
||||||
|
f8597e10546654bce3fbbe40461b2da59d0e06dbf1b038d1d362d24f949e3911 awareness.el
|
||||||
|
b6f3d14ca0c26017a2d617399a6d3754dabb0905e4d5f52eb75d25c4ad18d3c5 chat.el
|
||||||
|
42288c212cbf72fb1e8ecbd4d9900e4e9ee1cfa475b7974295c7637f1bf2939f elp-input.el
|
||||||
|
b3f77f49d6086932c38bd17fe7a5eaf8bce25685f6fc3e1750f05729c6b49b9e imprint.el
|
||||||
|
fba8ffdb9ba72bca5b09ca1c93a520edc52f3f4d8aec2c7585fe9b17e06420b2 manifest.el
|
||||||
|
550a72e234ae8cec1f33e02108fd365353f45edd88513da90b792e79b6c0e5f0 memory.el
|
||||||
|
77640783df5c38066149dcd11a11aea7e36f66e40e3df6aedf6723be8b9e0e1e neuron-api.el
|
||||||
|
03c47c451e0e87f2c252cadb4b765867943962a804f548dd53adeef0520912c8 persist.el
|
||||||
|
541b9309c59c33ee619d393714871b820ec4151b721d8b2aebcfdb7ce8eb2ffa routes.el
|
||||||
|
c28e36952ec56525963a0bdf29455ab097d3b0c5653d19c25fbb005e1069a1f7 safety.el
|
||||||
|
fd3ab91d0ae0ea26639e21bef2f8f94054dc4b02eae68b19e3fe689d2769aad4 sessions.el
|
||||||
|
0f1cf43904a98a5a646cce5a07e0e96162ced662692fbc13357d9b67d9a8ac3d soul.el
|
||||||
|
30337940905171a9645b0929f0a412ce6b3dccb1246495070c553bca0bbae6cd stewardship.el
|
||||||
|
e105dc5990e6adbf39db9dc0462cd8bcf6e6c3dfd03709059227ecfad2bbab29 studio.el
|
||||||
@@ -1,9 +1,91 @@
|
|||||||
|
import "persist.el"
|
||||||
|
|
||||||
fn tier_working() -> String { return "Working" }
|
fn tier_working() -> String { return "Working" }
|
||||||
fn tier_episodic() -> String { return "Episodic" }
|
fn tier_episodic() -> String { return "Episodic" }
|
||||||
fn tier_canonical() -> String { return "Canonical" }
|
fn tier_canonical() -> String { return "Canonical" }
|
||||||
|
|
||||||
|
// ── Association on write ──────────────────────────────────────────────────────
|
||||||
|
// DESIGN: "promotion integrates candidate nodes by linking them to existing nodes
|
||||||
|
// using typed semantic edges RATHER THAN APPENDING AS UNLINKED CONTENT" (CCR
|
||||||
|
// claim 29). Unlinked append is the explicitly rejected behaviour — and it is the
|
||||||
|
// only behaviour this system had. Measured 2026-08-09 on Tim's graph: 14,214 edges
|
||||||
|
// across 80,936 nodes, 5% of nodes connected to anything, and NO edge created by
|
||||||
|
// any write since 2026-07-19 while 27,000+ nodes were added. A memory that forms
|
||||||
|
// no connections cannot be reached by spreading activation, so retrieval silently
|
||||||
|
// degrades to literal matching.
|
||||||
|
//
|
||||||
|
// BOUNDS, each one bought with a specific failure:
|
||||||
|
// * max 3 edges per memory — link_memories.py's cap, precision over spray
|
||||||
|
// * never link to identity (self/*, Value): the existing policy is explicit that
|
||||||
|
// "memories must not pollute the self traversal by similarity; only an explicit
|
||||||
|
// citation may touch identity". Similarity is not citation.
|
||||||
|
// * never link telemetry (state-event, soul-response, boot_count, loop-outcome):
|
||||||
|
// these are ~97% of daily write volume (1,020 vs 31 real memories on 08-08).
|
||||||
|
// Linking them would add ~3,000 noise edges a day and re-flatten the graph in
|
||||||
|
// the name of connecting it.
|
||||||
|
// * fail-soft: a failed association never fails the write.
|
||||||
|
// Edges go through wt_edge so they reach the owner and survive restart.
|
||||||
|
fn mem_assoc_skip_label(label: String) -> Bool {
|
||||||
|
if str_contains(label, "state-event") { return true }
|
||||||
|
if str_contains(label, "soul-response") { return true }
|
||||||
|
if str_contains(label, "soul-outbox") { return true }
|
||||||
|
if str_contains(label, "boot_count") { return true }
|
||||||
|
if str_contains(label, "loop-outcome") { return true }
|
||||||
|
if str_contains(label, "search-result") { return true }
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
// A candidate is linkable only if it is a real, distinct, non-identity node.
|
||||||
|
fn mem_assoc_ok(cand_id: String, cand_label: String, self_id: String) -> Bool {
|
||||||
|
if str_eq(cand_id, "") { return false }
|
||||||
|
if str_eq(cand_id, self_id) { return false }
|
||||||
|
// CASE MATTERS — measured 2026-08-09. A lowercase-only check let a memory link
|
||||||
|
// to "Self — Values (grounded)", i.e. it polluted the self traversal, which is
|
||||||
|
// the one thing this policy exists to prevent. My verification had the same
|
||||||
|
// blind spot and printed PASS. Check every casing the graph actually uses, and
|
||||||
|
// exclude identity node TYPES as well as labels.
|
||||||
|
let lab: String = str_lower(cand_label)
|
||||||
|
if str_starts_with(lab, "self") { return false }
|
||||||
|
if str_starts_with(lab, "value") { return false }
|
||||||
|
if str_contains(lab, "values") { return false }
|
||||||
|
if str_contains(lab, "identity") { return false }
|
||||||
|
if mem_assoc_skip_label(cand_label) { return false }
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
// One slot of the association. Manual unroll rather than a loop: EL's codegen
|
||||||
|
// mis-emits accumulating while-loops (documented at soul.el:212, which unrolled
|
||||||
|
// three affective slots for the same reason).
|
||||||
|
fn mem_assoc_slot(results: String, idx: Int, new_id: String) -> Void {
|
||||||
|
if idx >= json_array_len(results) { return }
|
||||||
|
let cand: String = json_array_get(results, idx)
|
||||||
|
let cid: String = json_get(cand, "id")
|
||||||
|
let clabel: String = json_get(cand, "label")
|
||||||
|
let ctype: String = json_get(cand, "node_type")
|
||||||
|
if str_eq(ctype, "Value") { return }
|
||||||
|
if str_eq(ctype, "DharmaSelf") { return }
|
||||||
|
if str_eq(ctype, "Safety") { return }
|
||||||
|
if mem_assoc_ok(cid, clabel, new_id) {
|
||||||
|
wt_edge(new_id, cid, el_from_float(0.5), "related")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// mem_associate — connect a freshly written memory to what it is about.
|
||||||
|
fn mem_associate(new_id: String, content: String, label: String) -> Void {
|
||||||
|
if str_eq(new_id, "") { return }
|
||||||
|
if mem_assoc_skip_label(label) { return }
|
||||||
|
// Ask the graph what this memory resembles. Now that the store carries
|
||||||
|
// meaning-vectors this is semantic, not merely lexical.
|
||||||
|
let probe: String = str_slice(content, 0, 400)
|
||||||
|
let results: String = engram_recall_json(probe, 4)
|
||||||
|
if str_eq(results, "") { return }
|
||||||
|
mem_assoc_slot(results, 0, new_id)
|
||||||
|
mem_assoc_slot(results, 1, new_id)
|
||||||
|
mem_assoc_slot(results, 2, new_id)
|
||||||
|
}
|
||||||
|
|
||||||
fn mem_store(content: String, label: String, tags: String) -> String {
|
fn mem_store(content: String, label: String, tags: String) -> String {
|
||||||
let id: String = engram_node_full(
|
let id: String = wt_node(
|
||||||
content,
|
content,
|
||||||
"Memory",
|
"Memory",
|
||||||
label,
|
label,
|
||||||
@@ -17,13 +99,26 @@ fn mem_store(content: String, label: String, tags: String) -> String {
|
|||||||
println("[memory] write rejected by engram (empty id): label=" + label)
|
println("[memory] write rejected by engram (empty id): label=" + label)
|
||||||
return ""
|
return ""
|
||||||
}
|
}
|
||||||
// Read back to verify the node actually persisted — guards against silent write failures.
|
// wt_node has already read the node back locally and returns "" if it did
|
||||||
let readback: String = engram_get_node_json(id)
|
// not land, so the old duplicate read-back here is gone.
|
||||||
if str_eq(readback, "") || str_eq(readback, "{}") {
|
//
|
||||||
println("[memory] WRITE VERIFY FAILED: label=" + label + " id=" + id + " — node absent after write")
|
// HONESTY (neuron#117): the receipt now says WHERE the write is.
|
||||||
return ""
|
// The old unconditional "write verified" line asserted against the soul's
|
||||||
|
// own RAM — true in memory, false on disk — and printed ~115,000 times on
|
||||||
|
// Tim's machine while the canonical snapshot sat frozen for three days.
|
||||||
|
// wt_commit flushes the spool and then asks the OWNER. When it says false
|
||||||
|
// the node is real and recallable but not yet durable, and the log says so
|
||||||
|
// rather than claiming a save that did not happen. The id is still returned:
|
||||||
|
// the local write DID succeed, and the queued delta will be retried.
|
||||||
|
let durable: Bool = wt_commit(id)
|
||||||
|
// Associate AFTER the node is durable: an edge to a node that did not persist
|
||||||
|
// is a dangling edge, which is the defect the 2026-08-09 cleanup removed 830 of.
|
||||||
|
mem_associate(id, content, label)
|
||||||
|
if durable {
|
||||||
|
println("[memory] write persisted at owner: " + id + " label=" + label)
|
||||||
|
} else {
|
||||||
|
println("[memory] write IN MEMORY ONLY (queued for owner, not yet durable): " + id + " label=" + label)
|
||||||
}
|
}
|
||||||
println("[memory] write verified: " + id + " ok")
|
|
||||||
return id
|
return id
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -51,12 +146,12 @@ fn mem_strengthen(node_id: String) -> Void {
|
|||||||
// memory.el (imported first) so awareness.el and neuron-api.el can both call it.
|
// memory.el (imported first) so awareness.el and neuron-api.el can both call it.
|
||||||
fn mem_tombstone(node_id: String) -> String {
|
fn mem_tombstone(node_id: String) -> String {
|
||||||
let tags: String = "[\"Tombstone\",\"status:deleted\"]"
|
let tags: String = "[\"Tombstone\",\"status:deleted\"]"
|
||||||
let marker: String = engram_node_full(
|
let marker: String = wt_node(
|
||||||
node_id, "Tombstone", "tombstone:" + node_id,
|
node_id, "Tombstone", "tombstone:" + node_id,
|
||||||
el_from_float(0.01), el_from_float(0.01), el_from_float(1.0),
|
el_from_float(0.01), el_from_float(0.01), el_from_float(1.0),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !str_eq(marker, "") {
|
if !str_eq(marker, "") {
|
||||||
engram_connect(marker, node_id, el_from_float(1.0), "tombstones")
|
wt_edge(marker, node_id, el_from_float(1.0), "tombstones")
|
||||||
}
|
}
|
||||||
return marker
|
return marker
|
||||||
}
|
}
|
||||||
|
|||||||
+69
-28
@@ -195,15 +195,24 @@ fn api_compact_activated(raw: String, max_items: Int, snip: Int) -> String {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// api_persisted — read-back-after-write guard against hallucinated saves.
|
// api_persisted — read-back-after-write guard against hallucinated saves.
|
||||||
// After a write builtin returns an id, confirm the node is actually queryable
|
//
|
||||||
// via engram_get_node_json(id) (returns "" or "null" when missing). Returns
|
// WIDENED FOR neuron#117. This function is the single gate every MCP write
|
||||||
// true only when the node is genuinely persisted.
|
// handler passes through before it reports success (10 call sites), which makes
|
||||||
|
// it the right place to close the honesty gap rather than editing ten receipts.
|
||||||
|
//
|
||||||
|
// It used to read back from engram_get_node_json — the SOUL'S OWN in-process
|
||||||
|
// graph. In HTTP-engram mode that asserts the wrong thing: the soul is not the
|
||||||
|
// persistence owner, so a node present in its RAM and absent from the owner read
|
||||||
|
// as "persisted" and then vanished on the next restart. The guard was doing
|
||||||
|
// exactly what its comment promised and still certifying writes that did not
|
||||||
|
// survive. It now flushes the write-through spool and asks the OWNER.
|
||||||
|
//
|
||||||
|
// In file mode (no ENGRAM_URL) the soul IS the owner and wt_commit collapses to
|
||||||
|
// the original local read-back — unchanged behaviour, which is what keeps this
|
||||||
|
// reversible.
|
||||||
fn api_persisted(id: String) -> Bool {
|
fn api_persisted(id: String) -> Bool {
|
||||||
if str_eq(id, "") { return false }
|
if str_eq(id, "") { return false }
|
||||||
let node: String = engram_get_node_json(id)
|
return wt_commit(id)
|
||||||
// engram_get_node_json returns "{}" (empty object) when node is not found — not "" or "null".
|
|
||||||
// Check all three to guard against any runtime variation.
|
|
||||||
return !str_eq(node, "") && !str_eq(node, "null") && !str_eq(node, "{}")
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// api_not_persisted — standard error for a write that did not read back.
|
// api_not_persisted — standard error for a write that did not read back.
|
||||||
@@ -295,10 +304,35 @@ fn handle_api_begin_session(body: String) -> String {
|
|||||||
let state_events: String = api_compact_node_array(state_events_raw, 5, 500)
|
let state_events: String = api_compact_node_array(state_events_raw, 5, 500)
|
||||||
let recent_raw: String = engram_scan_nodes_json(10, 0)
|
let recent_raw: String = engram_scan_nodes_json(10, 0)
|
||||||
let recent: String = api_compact_node_array(recent_raw, 10, 240)
|
let recent: String = api_compact_node_array(recent_raw, 10, 240)
|
||||||
|
// SELF-SEEDED SLICE (2026-08-09). The design is explicit: "Every compilation
|
||||||
|
// query begins at the self-model node and traverses outward... structural
|
||||||
|
// reachability from the self-model node is a precondition for any node to
|
||||||
|
// appear in compiled context" (will-anderson patents/drafts/engram-claims.md,
|
||||||
|
// Self-Seeded Activation; DRAFT, not a filed provisional — cite it as such).
|
||||||
|
//
|
||||||
|
// Measured 2026-08-09 before this change: compiled context contained 0-1
|
||||||
|
// identity records out of 10, because compilation seeds from a hardcoded
|
||||||
|
// TEXT STRING, never from the self. Even an explicit "my values identity who
|
||||||
|
// I am" query returned a boot counter and state-events.
|
||||||
|
//
|
||||||
|
// This restores the designed behaviour WITHOUT repeating the failure that got
|
||||||
|
// self_neighbors set to [] in the first place: that was an UNBOUNDED ~90KB
|
||||||
|
// neighbour dump which closed the socket on every call. Same bound as every
|
||||||
|
// other list here — cap 8, 240-char snippets. The self root has 34 direct
|
||||||
|
// neighbours of which 23 are identity records, so depth 1 is dense enough to
|
||||||
|
// be worth seeding and small enough to stay cheap.
|
||||||
|
let self_raw: String = engram_neighbors_json("kn-efeb4a5b-5aff-4759-8a97-7233099be6ee", 1, "both")
|
||||||
|
// Cap 24, not 8: measured 2026-08-09, the self root's first 8 neighbours are
|
||||||
|
// TAG nodes ("neuron", "tier:note", "disposition:experimental", "imprint",
|
||||||
|
// "traversal") which crowd out the substantive identity records behind them.
|
||||||
|
// The root has 34 neighbours of which 23 are identity; 24 captures them while
|
||||||
|
// staying bounded. Cost measured at ~+4KB on a ~12KB response, nowhere near
|
||||||
|
// the ~90KB unbounded dump that closed sockets and got this set to [].
|
||||||
|
let self_slice: String = api_compact_node_array(self_raw, 24, 240)
|
||||||
return "{\"stats\":" + stats
|
return "{\"stats\":" + stats
|
||||||
+ ",\"recent\":" + recent
|
+ ",\"recent\":" + recent
|
||||||
+ ",\"activated\":" + activated
|
+ ",\"activated\":" + activated
|
||||||
+ ",\"self_neighbors\":[]"
|
+ ",\"self_neighbors\":" + self_slice
|
||||||
+ ",\"recent_state_events\":" + state_events + "}"
|
+ ",\"recent_state_events\":" + state_events + "}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -342,10 +376,17 @@ fn handle_api_remember(body: String) -> String {
|
|||||||
let inner: String = str_slice(base_tags, 1, str_len(base_tags) - 1)
|
let inner: String = str_slice(base_tags, 1, str_len(base_tags) - 1)
|
||||||
"[" + inner + ",\"project:" + project + "\"]"
|
"[" + inner + ",\"project:" + project + "\"]"
|
||||||
}
|
}
|
||||||
let id: String = engram_node_full(content, "Memory", "memory:remembered",
|
let id: String = wt_node(content, "Memory", "memory:remembered",
|
||||||
sal, sal, el_from_float(0.9),
|
sal, sal, el_from_float(0.9),
|
||||||
"Episodic", final_tags)
|
"Episodic", final_tags)
|
||||||
if !api_persisted(id) { return api_not_persisted(id) }
|
if !api_persisted(id) { return api_not_persisted(id) }
|
||||||
|
// Associate on write (2026-08-09). THIS CALL MUST BE HERE, not only in mem_store.
|
||||||
|
// The HTTP memory route writes via wt_node directly; mem_store serves only the
|
||||||
|
// awareness paths (soul-response, search-result, activation-result) which are
|
||||||
|
// exactly the telemetry we refuse to link. Hooking mem_store alone produced
|
||||||
|
// ZERO edges across four real writes — measured, not assumed, which is the only
|
||||||
|
// reason it was caught before shipping.
|
||||||
|
mem_associate(id, content, "memory:remembered")
|
||||||
return "{\"id\":\"" + id + "\",\"ok\":true}"
|
return "{\"id\":\"" + id + "\",\"ok\":true}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -369,7 +410,7 @@ fn handle_api_node_create(body: String) -> String {
|
|||||||
if str_eq(importance, "low") { 0.25 } else { 0.5 }
|
if str_eq(importance, "low") { 0.25 } else { 0.5 }
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
let id: String = engram_node_full(content, node_type, label,
|
let id: String = wt_node(content, node_type, label,
|
||||||
sal, sal, el_from_float(0.9),
|
sal, sal, el_from_float(0.9),
|
||||||
tier, tags)
|
tier, tags)
|
||||||
if !api_persisted(id) { return api_not_persisted(id) }
|
if !api_persisted(id) { return api_not_persisted(id) }
|
||||||
@@ -422,11 +463,11 @@ fn handle_api_node_update(body: String) -> String {
|
|||||||
}
|
}
|
||||||
let body_tags: String = json_get(body, "tags")
|
let body_tags: String = json_get(body, "tags")
|
||||||
let tags: String = if str_eq(body_tags, "") { "[\"" + node_type + "\"]" } else { body_tags }
|
let tags: String = if str_eq(body_tags, "") { "[\"" + node_type + "\"]" } else { body_tags }
|
||||||
let new_id: String = engram_node_full(content, node_type, label,
|
let new_id: String = wt_node(content, node_type, label,
|
||||||
el_from_float(0.5), el_from_float(0.5), el_from_float(0.8),
|
el_from_float(0.5), el_from_float(0.5), el_from_float(0.8),
|
||||||
tier, tags)
|
tier, tags)
|
||||||
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
||||||
engram_connect(new_id, id, el_from_float(0.9), "supersedes")
|
wt_edge(new_id, id, el_from_float(0.9), "supersedes")
|
||||||
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + id + "\",\"ok\":true}"
|
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + id + "\",\"ok\":true}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -503,7 +544,7 @@ fn handle_api_capture_knowledge(body: String) -> String {
|
|||||||
let full: String = if str_eq(title, "") { content } else { title + ": " + content }
|
let full: String = if str_eq(title, "") { content } else { title + ": " + content }
|
||||||
let lbl: String = str_slice(title, 0, 80)
|
let lbl: String = str_slice(title, 0, 80)
|
||||||
let tags: String = "[\"Knowledge\",\"captured\"]"
|
let tags: String = "[\"Knowledge\",\"captured\"]"
|
||||||
let id: String = engram_node_full(full, "Knowledge", lbl,
|
let id: String = wt_node(full, "Knowledge", lbl,
|
||||||
el_from_float(0.85), el_from_float(0.8), el_from_float(0.9),
|
el_from_float(0.85), el_from_float(0.8), el_from_float(0.9),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !api_persisted(id) { return api_not_persisted(id) }
|
if !api_persisted(id) { return api_not_persisted(id) }
|
||||||
@@ -518,12 +559,12 @@ fn handle_api_evolve_knowledge(body: String) -> String {
|
|||||||
if !str_eq(prior_id, "") && is_protected_node(prior_id) { return api_err_protected(prior_id) }
|
if !str_eq(prior_id, "") && is_protected_node(prior_id) { return api_err_protected(prior_id) }
|
||||||
let tags: String = "[\"Knowledge\",\"evolved\"]"
|
let tags: String = "[\"Knowledge\",\"evolved\"]"
|
||||||
// Empty label → engram_node_full derives content[:60] (LABEL FIX 2026-07-23).
|
// Empty label → engram_node_full derives content[:60] (LABEL FIX 2026-07-23).
|
||||||
let new_id: String = engram_node_full(content, "Knowledge", "",
|
let new_id: String = wt_node(content, "Knowledge", "",
|
||||||
el_from_float(0.75), el_from_float(0.75), el_from_float(0.9),
|
el_from_float(0.75), el_from_float(0.75), el_from_float(0.9),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
||||||
if !str_eq(prior_id, "") {
|
if !str_eq(prior_id, "") {
|
||||||
engram_connect(new_id, prior_id, el_from_float(0.9), "supersedes")
|
wt_edge(new_id, prior_id, el_from_float(0.9), "supersedes")
|
||||||
}
|
}
|
||||||
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true}"
|
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true}"
|
||||||
}
|
}
|
||||||
@@ -540,11 +581,11 @@ fn handle_api_promote_knowledge(body: String) -> String {
|
|||||||
"[\"Knowledge\",\"tier:canonical\",\"disposition:stable\"]"
|
"[\"Knowledge\",\"tier:canonical\",\"disposition:stable\"]"
|
||||||
} else { tags_raw }
|
} else { tags_raw }
|
||||||
// Empty label → engram_node_full derives content[:60] (LABEL FIX 2026-07-23).
|
// Empty label → engram_node_full derives content[:60] (LABEL FIX 2026-07-23).
|
||||||
let new_id: String = engram_node_full(content, "Knowledge", "",
|
let new_id: String = wt_node(content, "Knowledge", "",
|
||||||
el_from_float(0.9), el_from_float(0.9), el_from_float(1.0),
|
el_from_float(0.9), el_from_float(0.9), el_from_float(1.0),
|
||||||
"Canonical", tags)
|
"Canonical", tags)
|
||||||
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
if !api_persisted(new_id) { return api_not_persisted(new_id) }
|
||||||
engram_connect(new_id, prior_id, el_from_float(0.95), "supersedes")
|
wt_edge(new_id, prior_id, el_from_float(0.95), "supersedes")
|
||||||
return "{\"ok\":true,\"new_id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\"}"
|
return "{\"ok\":true,\"new_id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\"}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -567,7 +608,7 @@ fn handle_api_define_process(body: String) -> String {
|
|||||||
if str_eq(content, "") { return api_err("content is required") }
|
if str_eq(content, "") { return api_err("content is required") }
|
||||||
let label: String = if str_eq(name, "") { "process:unnamed" } else { "process:" + name }
|
let label: String = if str_eq(name, "") { "process:unnamed" } else { "process:" + name }
|
||||||
let tags: String = "[\"Process\"]"
|
let tags: String = "[\"Process\"]"
|
||||||
let id: String = engram_node_full(content, "Process", label,
|
let id: String = wt_node(content, "Process", label,
|
||||||
el_from_float(0.8), el_from_float(0.8), el_from_float(0.9),
|
el_from_float(0.8), el_from_float(0.8), el_from_float(0.9),
|
||||||
"Canonical", tags)
|
"Canonical", tags)
|
||||||
if !api_persisted(id) { return api_not_persisted(id) }
|
if !api_persisted(id) { return api_not_persisted(id) }
|
||||||
@@ -652,7 +693,7 @@ fn handle_api_tune_config(body: String) -> String {
|
|||||||
if str_eq(key, "") { return api_err("key is required") }
|
if str_eq(key, "") { return api_err("key is required") }
|
||||||
let content: String = "config:" + key + "=" + value
|
let content: String = "config:" + key + "=" + value
|
||||||
let tags: String = "[\"ConfigEntry\",\"config\"]"
|
let tags: String = "[\"ConfigEntry\",\"config\"]"
|
||||||
let id: String = engram_node_full(content, "ConfigEntry", key,
|
let id: String = wt_node(content, "ConfigEntry", key,
|
||||||
el_from_float(0.85), el_from_float(0.85), el_from_float(0.9),
|
el_from_float(0.85), el_from_float(0.85), el_from_float(0.9),
|
||||||
"Canonical", tags)
|
"Canonical", tags)
|
||||||
if !api_persisted(id) { return api_not_persisted(id) }
|
if !api_persisted(id) { return api_not_persisted(id) }
|
||||||
@@ -699,7 +740,7 @@ fn handle_api_link_entities(body: String) -> String {
|
|||||||
if is_protected_node(to_id) { return api_err_protected(to_id) }
|
if is_protected_node(to_id) { return api_err_protected(to_id) }
|
||||||
let relation: String = json_get(body, "relation")
|
let relation: String = json_get(body, "relation")
|
||||||
let eff_relation: String = if str_eq(relation, "") { "associates" } else { relation }
|
let eff_relation: String = if str_eq(relation, "") { "associates" } else { relation }
|
||||||
engram_connect(from_id, to_id, el_from_float(0.5), eff_relation)
|
wt_edge(from_id, to_id, el_from_float(0.5), eff_relation)
|
||||||
return "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + eff_relation + "\"}"
|
return "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + eff_relation + "\"}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -732,11 +773,11 @@ fn handle_api_evolve_memory(body: String) -> String {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
let tags: String = "[\"Memory\",\"evolved\"]"
|
let tags: String = "[\"Memory\",\"evolved\"]"
|
||||||
let new_id: String = engram_node_full(content, "Memory", "memory:evolved",
|
let new_id: String = wt_node(content, "Memory", "memory:evolved",
|
||||||
sal, sal, el_from_float(0.9),
|
sal, sal, el_from_float(0.9),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
||||||
engram_connect(new_id, prior_id, el_from_float(0.9), "supersedes")
|
wt_edge(new_id, prior_id, el_from_float(0.9), "supersedes")
|
||||||
}
|
}
|
||||||
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true}"
|
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true}"
|
||||||
}
|
}
|
||||||
@@ -794,11 +835,11 @@ fn handle_api_cultivate(body: String) -> String {
|
|||||||
let content: String = json_get(body, "content")
|
let content: String = json_get(body, "content")
|
||||||
if str_eq(content, "") { return api_err("content is required") }
|
if str_eq(content, "") { return api_err("content is required") }
|
||||||
let tags: String = "[\"Knowledge\",\"evolved\",\"cultivated\"]"
|
let tags: String = "[\"Knowledge\",\"evolved\",\"cultivated\"]"
|
||||||
let new_id: String = engram_node_full(content, "Knowledge", "knowledge:cultivated",
|
let new_id: String = wt_node(content, "Knowledge", "knowledge:cultivated",
|
||||||
el_from_float(0.75), el_from_float(0.75), el_from_float(0.9),
|
el_from_float(0.75), el_from_float(0.75), el_from_float(0.9),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
||||||
engram_connect(new_id, prior_id, el_from_float(0.9), "supersedes")
|
wt_edge(new_id, prior_id, el_from_float(0.9), "supersedes")
|
||||||
}
|
}
|
||||||
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true,\"cultivated\":true}"
|
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true,\"cultivated\":true}"
|
||||||
}
|
}
|
||||||
@@ -814,11 +855,11 @@ fn handle_api_cultivate(body: String) -> String {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
let tags: String = "[\"Memory\",\"evolved\",\"cultivated\"]"
|
let tags: String = "[\"Memory\",\"evolved\",\"cultivated\"]"
|
||||||
let new_id: String = engram_node_full(content, "Memory", "memory:cultivated",
|
let new_id: String = wt_node(content, "Memory", "memory:cultivated",
|
||||||
sal, sal, el_from_float(0.9),
|
sal, sal, el_from_float(0.9),
|
||||||
"Episodic", tags)
|
"Episodic", tags)
|
||||||
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
if !str_eq(prior_id, "") && !str_eq(new_id, "") {
|
||||||
engram_connect(new_id, prior_id, el_from_float(0.9), "supersedes")
|
wt_edge(new_id, prior_id, el_from_float(0.9), "supersedes")
|
||||||
}
|
}
|
||||||
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true,\"cultivated\":true}"
|
return "{\"id\":\"" + new_id + "\",\"supersedes\":\"" + prior_id + "\",\"ok\":true,\"cultivated\":true}"
|
||||||
}
|
}
|
||||||
@@ -838,7 +879,7 @@ fn handle_api_cultivate(body: String) -> String {
|
|||||||
if str_eq(to_id, "") { return api_err("to_id is required") }
|
if str_eq(to_id, "") { return api_err("to_id is required") }
|
||||||
let relation: String = json_get(body, "relation")
|
let relation: String = json_get(body, "relation")
|
||||||
let eff_relation: String = if str_eq(relation, "") { "associates" } else { relation }
|
let eff_relation: String = if str_eq(relation, "") { "associates" } else { relation }
|
||||||
engram_connect(from_id, to_id, el_from_float(0.5), eff_relation)
|
wt_edge(from_id, to_id, el_from_float(0.5), eff_relation)
|
||||||
return "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + eff_relation + "\",\"cultivated\":true}"
|
return "{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + eff_relation + "\",\"cultivated\":true}"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -873,7 +914,7 @@ fn handle_api_consolidate(body: String) -> String {
|
|||||||
if !str_eq(summary, "") {
|
if !str_eq(summary, "") {
|
||||||
let safe_summary: String = str_replace(summary, "\"", "'")
|
let safe_summary: String = str_replace(summary, "\"", "'")
|
||||||
let tags: String = "[\"SessionSummary\",\"consolidate\"]"
|
let tags: String = "[\"SessionSummary\",\"consolidate\"]"
|
||||||
let summary_id: String = engram_node_full(
|
let summary_id: String = wt_node(
|
||||||
"[session-summary] " + safe_summary,
|
"[session-summary] " + safe_summary,
|
||||||
"SessionSummary", "session:summary",
|
"SessionSummary", "session:summary",
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
|
|||||||
+426
@@ -0,0 +1,426 @@
|
|||||||
|
// persist.el — the soul→engram WRITE-THROUGH boundary (neuron#117).
|
||||||
|
//
|
||||||
|
// WHY THIS FILE EXISTS
|
||||||
|
// soul.el:571-573 states the ownership rule: "when ENGRAM_URL is set the HTTP
|
||||||
|
// Engram owns persistence — the soul must NEVER write to the local snapshot
|
||||||
|
// (not the persistence owner)." The soul obeys the NEGATIVE half. The POSITIVE
|
||||||
|
// half — how a write made inside the soul actually REACHES the owner — was
|
||||||
|
// never built. Sync is pull-only (awareness.el `/api/sync` -> engram_load_merge),
|
||||||
|
// so every node the soul creates lives in its process RAM and is shed on
|
||||||
|
// restart. Measured live 2026-08-07: soul node_count=102184, engram
|
||||||
|
// node_count=79197 — ~23k nodes existing nowhere but RAM.
|
||||||
|
//
|
||||||
|
// SCOPE NOTE ON THE PATENT (corrects an earlier internal reading)
|
||||||
|
// Engram provisional claims 15-18 describe a delta-sync protocol "with peer
|
||||||
|
// Engram instances"; claim 17's pull-then-push sequence is PEER-ENGRAM to
|
||||||
|
// PEER-ENGRAM. The soul is NOT a peer Engram — it is a CALLER of the database
|
||||||
|
// system API (cf. claim 27, "invoked explicitly by a caller of the database
|
||||||
|
// system API"). So claim 17 does not specify a soul↔engram contract and is not
|
||||||
|
// cited as authority here. This design is derived from the ownership rule
|
||||||
|
// alone: the owner owns the writes, therefore the soul must HAND writes to the
|
||||||
|
// owner and must never write the owner's file itself.
|
||||||
|
//
|
||||||
|
// THE MECHANISM, AND WHY NOT `POST /api/nodes`
|
||||||
|
// The obvious route is the one the persona/boot-counter write-backs already
|
||||||
|
// use, POST /api/nodes. It is the wrong instrument here, verified against the
|
||||||
|
// live engram binary in a sandbox:
|
||||||
|
// - it mints a NEW server-side id (engram_node), so the soul's id and the
|
||||||
|
// owner's id diverge — the next /api/sync pull re-imports the node as a
|
||||||
|
// DUPLICATE, and any edge referencing the soul's id never resolves;
|
||||||
|
// - it accepts only {content, node_type, salience} and drops label, tier,
|
||||||
|
// tags, importance, confidence, metadata. A probe posted with tier
|
||||||
|
// "Canonical" came back tier "Working", importance 0.5.
|
||||||
|
// POST /api/load-merge (Will's own route, el `dc39a61`) is the right one:
|
||||||
|
// - engram_load_merge PRESERVES the id and every field;
|
||||||
|
// - it dedups nodes by id and edges by (from_id,to_id,relation), so a
|
||||||
|
// re-submitted delta is a NO-OP — retry safety is free, and it is the same
|
||||||
|
// local-wins semantics the graph already uses;
|
||||||
|
// - it calls persist_canonical() — THE OWNER writes its own canonical file.
|
||||||
|
// The soul never touches it. The ownership rule is honoured in its
|
||||||
|
// strongest form rather than worked around;
|
||||||
|
// - it returns real counts {ok, nodes_added, edges_added, node_count},
|
||||||
|
// so a receipt can be a MEASUREMENT instead of a fixed success shape.
|
||||||
|
//
|
||||||
|
// SPOOL-AND-DRAIN, AND WHY IT IS NOT JUST A DIRECT POST
|
||||||
|
// Measured in a sandbox against a 79k-node / 176MB graph (live scale): one
|
||||||
|
// load-merge costs ~0.38s, essentially all of it the owner's persist_canonical.
|
||||||
|
// A chat turn writes 5-7 nodes; pushing each separately would add ~2.7s per
|
||||||
|
// turn. So writes are STAGED and pushed in one coalesced batch.
|
||||||
|
// The staging buffer is the FILESYSTEM, not process state, because the soul
|
||||||
|
// serves each HTTP connection on its own pthread (el_runtime http_serve_async)
|
||||||
|
// and a shared in-process buffer would lose entries to a read-modify-write
|
||||||
|
// race — silently, which is the one failure mode this file exists to end.
|
||||||
|
// One file per write, named with uuid_v4, is race-free by construction and
|
||||||
|
// buys a property a memory buffer cannot: writes that could not be pushed
|
||||||
|
// SURVIVE A SOUL CRASH and are drained on the next boot.
|
||||||
|
//
|
||||||
|
// WHAT IS DELIBERATELY NOT PUSHED
|
||||||
|
// - InternalStateEvent / heartbeat telemetry. Will's own carve-out, stated in
|
||||||
|
// engram server.el 8f8ccc9: "48h-pruned, loss-tolerant, ~2/min; snapshotting
|
||||||
|
// 28MB per heartbeat is waste."
|
||||||
|
// NOTE (ours, flagged for Will): we do NOT additionally exclude Working-tier
|
||||||
|
// nodes. That exclusion exists in `fb0bb55` to stop the boot counter leaking
|
||||||
|
// through the /api/sync PULL; it is about sync backflow, not durability.
|
||||||
|
// Applying it here would exclude mem_store — which writes tier "Working" — and
|
||||||
|
// mem_store is the single most important durable write path in the soul. Boot
|
||||||
|
// seeding reads the canonical file wholesale, so a pushed Working-tier node
|
||||||
|
// does survive restart. This is the one classification call this file makes
|
||||||
|
// that Will has not ruled on.
|
||||||
|
//
|
||||||
|
// WHAT THIS BOUNDARY CANNOT EXPRESS (by construction, not by omission)
|
||||||
|
// - engram_strengthen (salience/activation drift): load-merge SKIPS ids that
|
||||||
|
// already exist, so it cannot update an existing node. There is no owner-side
|
||||||
|
// update/upsert route. Not pushable through any current route; left as a
|
||||||
|
// follow-up that needs a change in the engram repo.
|
||||||
|
// - engram_forget (hard delete): load-merge is additive and has no delete verb.
|
||||||
|
// Propagating deletes would mean DELETE /api/nodes/<id>, a HARD delete at the
|
||||||
|
// owner — which scripts/verify-soul-contract.sh section B explicitly fails the
|
||||||
|
// build for ("to delete is to supersede/tombstone, never hard-remove"). Local
|
||||||
|
// deletes therefore stay local; the TOMBSTONE NODE and its "tombstones" edge
|
||||||
|
// (mem_tombstone) are pushed, and that is the sanctioned representation of a
|
||||||
|
// deletion in this graph.
|
||||||
|
|
||||||
|
// ── Configuration ─────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
// wt_engram_url — same resolution order as ise_post: env, then the state key
|
||||||
|
// stashed at boot. NO hardcoded localhost fallback: unlike telemetry, inventing
|
||||||
|
// a destination for durable data would risk pushing a user's memories at whatever
|
||||||
|
// happens to be listening on 8742. Empty means "no HTTP owner" -> file mode.
|
||||||
|
fn wt_engram_url() -> String {
|
||||||
|
let env_url: String = env("ENGRAM_URL")
|
||||||
|
if !str_eq(env_url, "") { return env_url }
|
||||||
|
return state_get("soul_engram_url")
|
||||||
|
}
|
||||||
|
|
||||||
|
fn wt_api_key() -> String {
|
||||||
|
let env_key: String = env("ENGRAM_API_KEY")
|
||||||
|
if !str_eq(env_key, "") { return env_key }
|
||||||
|
return state_get("soul_engram_api_key")
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_enabled — true only in HTTP-engram mode. In file mode the soul IS the
|
||||||
|
// persistence owner and every path below is a no-op, so this whole feature is
|
||||||
|
// inert for genesis/local deployments. That is also what makes it reversible.
|
||||||
|
fn wt_enabled() -> Bool {
|
||||||
|
return !str_eq(wt_engram_url(), "")
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_spool_dir — where staged deltas live. MUST be readable by the engram
|
||||||
|
// process: /api/load-merge takes a PATH and the owner opens it itself. Both
|
||||||
|
// processes are same-host by construction (dev-stack LaunchAgents; the GKE
|
||||||
|
// image starts engram and soul in one container per entrypoint.sh).
|
||||||
|
fn wt_spool_dir() -> String {
|
||||||
|
let raw: String = env("SOUL_OUTBOX_DIR")
|
||||||
|
let dir: String = if str_eq(raw, "") { env("HOME") + "/.neuron/soul-outbox" } else { raw }
|
||||||
|
fs_mkdir(dir)
|
||||||
|
return dir
|
||||||
|
}
|
||||||
|
|
||||||
|
// ── Helpers ───────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
// wt_esc — minimal JSON string escape. Deliberately local rather than reusing
|
||||||
|
// chat.el's json_safe: persist.el is imported BY memory.el, which is imported by
|
||||||
|
// chat.el, so depending on chat.el here would be an import cycle.
|
||||||
|
fn wt_esc(s: String) -> String {
|
||||||
|
let s1: String = str_replace(s, "\\", "\\\\")
|
||||||
|
let s2: String = str_replace(s1, "\"", "\\\"")
|
||||||
|
let s3: String = str_replace(s2, "\n", "\\n")
|
||||||
|
let s4: String = str_replace(s3, "\r", "\\r")
|
||||||
|
let s5: String = str_replace(s4, "\t", "\\t")
|
||||||
|
return s5
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_durable_class — Will's telemetry carve-out, by node_type. See header.
|
||||||
|
fn wt_durable_class(node_type: String) -> Bool {
|
||||||
|
if str_eq(node_type, "InternalStateEvent") { return false }
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_inner — strip the surrounding brackets off a JSON array so several arrays
|
||||||
|
// can be concatenated into one. Returns "" for "[]" / "" / anything too short.
|
||||||
|
fn wt_inner(arr: String) -> String {
|
||||||
|
let n: Int = str_len(arr)
|
||||||
|
if n < 3 { return "" }
|
||||||
|
if !str_starts_with(arr, "[") { return "" }
|
||||||
|
return str_slice(arr, 1, n - 1)
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_read — fs_read, plus a MANDATORY reset of the runtime's binary-length hint.
|
||||||
|
//
|
||||||
|
// THIS IS NOT OPTIONAL AND MUST NOT BE "SIMPLIFIED" BACK TO A BARE fs_read.
|
||||||
|
// The pinned runtime (vendor/el-runtime/v1.0.0-20260501) keeps a thread-local
|
||||||
|
// `_tl_fs_read_len` that fs_read SETS to the file's byte count (so binary files
|
||||||
|
// can be served with a correct Content-Length) and that http_send_response
|
||||||
|
// CONSUMES as the Content-Length of the next reply. Nothing else clears it
|
||||||
|
// except json_get_raw. So any fs_read during request handling that is not
|
||||||
|
// followed by a json_get_raw makes the NEXT HTTP response advertise the FILE's
|
||||||
|
// length instead of the body's — and the runtime then sends that many bytes,
|
||||||
|
// appending whatever adjacent heap memory follows the reply.
|
||||||
|
//
|
||||||
|
// Caught here, measured: a /api/neuron/memory reply that should be 86 bytes went
|
||||||
|
// out as 497, with 411 bytes of this module's own spool paths and log strings
|
||||||
|
// trailing the JSON. The drain reads spool files mid-request, so this boundary
|
||||||
|
// is exactly where the landmine gets stepped on.
|
||||||
|
//
|
||||||
|
// Upstream el fixed the class in `43636ae` ("pair fs_read length hint with its
|
||||||
|
// buffer"); that runtime is NOT the one vendored here, and re-pinning the
|
||||||
|
// runtime is deliberately out of scope for this change. Clearing the hint at
|
||||||
|
// our own boundary fixes our exposure without touching the pinned C.
|
||||||
|
// json_get_raw is used as the reset because it is the only builtin in this
|
||||||
|
// runtime that zeroes the hint, and it does so before any early return.
|
||||||
|
fn wt_clear_binlen() -> Void {
|
||||||
|
let discard: String = json_get_raw("{}", "_wt_reset")
|
||||||
|
}
|
||||||
|
|
||||||
|
fn wt_read(path: String) -> String {
|
||||||
|
let data: String = fs_read(path)
|
||||||
|
wt_clear_binlen()
|
||||||
|
return data
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_sweep — best-effort removal of the zero-byte husks left by truncation.
|
||||||
|
// The runtime exposes no unlink builtin, so a drained delta is emptied rather
|
||||||
|
// than deleted; this reclaims the directory entries.
|
||||||
|
//
|
||||||
|
// `-empty` is the safety property, not an optimisation: the command is
|
||||||
|
// STRUCTURALLY INCAPABLE of removing a delta that still has content, so it can
|
||||||
|
// never destroy a pending write even if it runs concurrently with a stage.
|
||||||
|
// Only the directory path is interpolated (never a filename), and it is quoted.
|
||||||
|
// The exit code is ignored — an un-swept husk costs one directory entry.
|
||||||
|
fn wt_sweep(dir: String) -> Void {
|
||||||
|
if str_eq(dir, "") { return }
|
||||||
|
if str_contains(dir, "'") { return }
|
||||||
|
exec_command("find '" + dir + "' -maxdepth 1 -name 'wt*.json' -empty -delete 2>/dev/null")
|
||||||
|
}
|
||||||
|
|
||||||
|
// ── Staging ───────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
// wt_stage — write ONE delta file. uuid_v4 in the name makes concurrent stagers
|
||||||
|
// collision-free without any lock. Returns true if the delta is on disk.
|
||||||
|
fn wt_stage(nodes_json: String, edges_json: String) -> Bool {
|
||||||
|
let dir: String = wt_spool_dir()
|
||||||
|
if str_eq(dir, "") { return false }
|
||||||
|
let payload: String = "{\"nodes\":" + nodes_json + ",\"edges\":" + edges_json + "}"
|
||||||
|
let path: String = dir + "/wt-" + uuid_v4() + ".json"
|
||||||
|
fs_write(path, payload)
|
||||||
|
// Read-back-verify the stage itself. A stage that did not land is a write we
|
||||||
|
// would otherwise believe was queued — exactly the hallucinated-save class.
|
||||||
|
if str_eq(wt_read(path), "") {
|
||||||
|
println("[persist] wt_stage: FAILED to write spool file " + path + " — delta not queued")
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
|
||||||
|
// ── The write boundary ────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
// wt_node — create a node locally AND queue it for the persistence owner.
|
||||||
|
// Same signature and same return contract as engram_node_full ("" on failure),
|
||||||
|
// so converting a call site is a rename and nothing else.
|
||||||
|
fn wt_node(content: String, node_type: String, label: String,
|
||||||
|
salience: Float, importance: Float, confidence: Float,
|
||||||
|
tier: String, tags: String) -> String {
|
||||||
|
let id: String = engram_node_full(content, node_type, label,
|
||||||
|
salience, importance, confidence,
|
||||||
|
tier, tags)
|
||||||
|
if str_eq(id, "") { return "" }
|
||||||
|
// engram_get_node_json emits the SAME record shape engram_save writes (minus
|
||||||
|
// the embedding vector, which the owner backfills lazily), so the read-back
|
||||||
|
// doubles as the delta payload — no second serialization to drift.
|
||||||
|
let rec: String = engram_get_node_json(id)
|
||||||
|
if str_eq(rec, "") || str_eq(rec, "{}") {
|
||||||
|
println("[persist] wt_node: local write did not read back, id=" + id + " label=" + label)
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
if wt_enabled() && wt_durable_class(node_type) {
|
||||||
|
wt_stage("[" + rec + "]", "[]")
|
||||||
|
}
|
||||||
|
return id
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_edge — create an edge locally AND queue it. Mirrors engram_connect.
|
||||||
|
//
|
||||||
|
// The edge id is freshly generated rather than read back: the runtime exposes no
|
||||||
|
// "id of the edge I just created" accessor, and the owner dedups edges by
|
||||||
|
// (from_id,to_id,relation), never by id — so the id is not load-bearing. The
|
||||||
|
// consequence, stated plainly: the soul's copy and the owner's copy of the same
|
||||||
|
// edge carry different edge ids. Nothing in either codebase looks an edge up by
|
||||||
|
// id (neighbors traversal scans from_id/to_id), so this is cosmetic.
|
||||||
|
fn wt_edge(from_id: String, to_id: String, weight: Float, relation: String) -> Void {
|
||||||
|
engram_connect(from_id, to_id, weight, relation)
|
||||||
|
if !wt_enabled() { return }
|
||||||
|
if str_eq(from_id, "") || str_eq(to_id, "") { return }
|
||||||
|
let ts: Int = time_now()
|
||||||
|
let rec: String = "{\"id\":\"" + uuid_v4() + "\""
|
||||||
|
+ ",\"from_id\":\"" + wt_esc(from_id) + "\""
|
||||||
|
+ ",\"to_id\":\"" + wt_esc(to_id) + "\""
|
||||||
|
+ ",\"relation\":\"" + wt_esc(relation) + "\""
|
||||||
|
+ ",\"metadata\":\"{}\""
|
||||||
|
+ ",\"weight\":" + float_to_str(weight)
|
||||||
|
+ ",\"confidence\":1"
|
||||||
|
+ ",\"created_at\":" + int_to_str(ts)
|
||||||
|
+ ",\"updated_at\":" + int_to_str(ts)
|
||||||
|
+ ",\"last_fired\":0,\"inhibitory\":0,\"layer_id\":1}"
|
||||||
|
wt_stage("[]", "[" + rec + "]")
|
||||||
|
}
|
||||||
|
|
||||||
|
// ── The drain ─────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
// wt_drain — coalesce every staged delta into ONE load-merge against the owner.
|
||||||
|
//
|
||||||
|
// Returns: nodes_added on success (>= 0), 0 when there was nothing to do, and
|
||||||
|
// -1 when the push FAILED. -1 is load-bearing: on failure the spool files are
|
||||||
|
// left untouched, so nothing is lost and the next drain retries them. A caller
|
||||||
|
// must never read a non-negative return as "my particular node is durable" —
|
||||||
|
// use wt_durable(id) for that.
|
||||||
|
//
|
||||||
|
// Concurrency: several threads may drain at once. Each builds its own batch file
|
||||||
|
// (uuid-named), and overlapping batches are harmless because load-merge dedups.
|
||||||
|
// Files are truncated ONLY after a confirmed ok:true, so a lost race costs a
|
||||||
|
// redundant push, never a dropped write.
|
||||||
|
fn wt_drain() -> Int {
|
||||||
|
if !wt_enabled() { return 0 }
|
||||||
|
let dir: String = wt_spool_dir()
|
||||||
|
if str_eq(dir, "") { return 0 }
|
||||||
|
|
||||||
|
// el_list_len/el_list_get, NOT json_stringify(fs_list(...)): fs_list builds
|
||||||
|
// a native list via el_list_append, and json_stringify does not serialize
|
||||||
|
// that type — it renders the raw pointer value. (Verified in isolation; the
|
||||||
|
// same latent defect is live in studio.el's /api/tools/file/list route,
|
||||||
|
// which returns e.g. {"entries":4386409744}. Noted, not fixed here.)
|
||||||
|
let listing = fs_list(dir)
|
||||||
|
let count: Int = el_list_len(listing)
|
||||||
|
if count == 0 { return 0 }
|
||||||
|
|
||||||
|
let nodes_acc: String = ""
|
||||||
|
let edges_acc: String = ""
|
||||||
|
let drained: String = ""
|
||||||
|
let found: Int = 0
|
||||||
|
let i: Int = 0
|
||||||
|
// No `continue` / `break`: elc lists them as keywords but not one line of
|
||||||
|
// the shipped soul uses either, so they are unexercised on this build path.
|
||||||
|
// Guard conditions are expressed as nested ifs instead, and every rebind is
|
||||||
|
// at the loop-body top level where `let x = ...` is assignment (the idiom
|
||||||
|
// memory.el's boot-counter loop relies on) — never inside a nested block,
|
||||||
|
// where it would shadow instead.
|
||||||
|
while i < count {
|
||||||
|
let name: String = el_list_get(listing, i)
|
||||||
|
// A delta is only usable when it ends with the closing "]}" that
|
||||||
|
// wt_stage writes last. fs_write is not atomic, so a file being written
|
||||||
|
// right now can be observed half-formed; requiring the terminator means
|
||||||
|
// it is picked up whole on the next drain instead of merged as garbage.
|
||||||
|
// An empty read means "already drained and truncated" — not an error.
|
||||||
|
let p: String = if str_starts_with(name, "wt-") { dir + "/" + name } else { "" }
|
||||||
|
let raw: String = if str_eq(p, "") { "" } else { wt_read(p) }
|
||||||
|
let usable: Bool = !str_eq(raw, "") && str_ends_with(raw, "]}")
|
||||||
|
let nj: String = if usable { wt_inner(json_get_raw(raw, "nodes")) } else { "" }
|
||||||
|
let ej: String = if usable { wt_inner(json_get_raw(raw, "edges")) } else { "" }
|
||||||
|
let nodes_acc = if str_eq(nj, "") { nodes_acc } else if str_eq(nodes_acc, "") { nj } else { nodes_acc + "," + nj }
|
||||||
|
let edges_acc = if str_eq(ej, "") { edges_acc } else if str_eq(edges_acc, "") { ej } else { edges_acc + "," + ej }
|
||||||
|
let drained = if !usable { drained } else if str_eq(drained, "") { p } else { drained + "\n" + p }
|
||||||
|
let found = if usable { found + 1 } else { found }
|
||||||
|
let i = i + 1
|
||||||
|
}
|
||||||
|
|
||||||
|
if found == 0 { return 0 }
|
||||||
|
|
||||||
|
let combined: String = "{\"nodes\":[" + nodes_acc + "],\"edges\":[" + edges_acc + "]}"
|
||||||
|
let batch: String = dir + "/wtb-" + uuid_v4() + ".json"
|
||||||
|
fs_write(batch, combined)
|
||||||
|
if str_eq(wt_read(batch), "") {
|
||||||
|
println("[persist] wt_drain: could not write batch file " + batch + " — " + int_to_str(found) + " deltas stay queued")
|
||||||
|
return -1
|
||||||
|
}
|
||||||
|
|
||||||
|
let url: String = wt_engram_url()
|
||||||
|
let key: String = wt_api_key()
|
||||||
|
let body: String = "{\"path\":\"" + wt_esc(batch) + "\",\"_auth\":\"" + wt_esc(key) + "\"}"
|
||||||
|
let resp: String = http_post_json(url + "/api/load-merge", body)
|
||||||
|
|
||||||
|
// The batch file is pure scratch — the retry is rebuilt from the SPOOL, not
|
||||||
|
// from it. Truncate it unconditionally, before branching on the outcome, so
|
||||||
|
// a persistently unreachable owner cannot accumulate one husk per attempt.
|
||||||
|
fs_write(batch, "")
|
||||||
|
|
||||||
|
// Distinguish the two failures rather than collapsing them: "cannot reach
|
||||||
|
// the owner" and "the owner refused this delta" need different human
|
||||||
|
// responses, and a log line that says the wrong one costs a debugging hour.
|
||||||
|
// curl surfaces transport errors as a JSON body, so an empty response is not
|
||||||
|
// the only unreachable signal.
|
||||||
|
// (str_contains rather than a strict parse on purpose — the engram's HTTP
|
||||||
|
// responses have been observed carrying trailing bytes past the JSON.)
|
||||||
|
let unreachable: Bool = str_eq(resp, "")
|
||||||
|
|| str_contains(resp, "Couldn't connect")
|
||||||
|
|| str_contains(resp, "Failed to connect")
|
||||||
|
|| str_contains(resp, "Could not resolve")
|
||||||
|
|| str_contains(resp, "timed out")
|
||||||
|
if unreachable {
|
||||||
|
wt_sweep(dir)
|
||||||
|
println("[persist] wt_drain: owner UNREACHABLE at " + url + " — " + int_to_str(found)
|
||||||
|
+ " deltas stay queued in " + dir + " (will retry): " + resp)
|
||||||
|
return -1
|
||||||
|
}
|
||||||
|
if !str_contains(resp, "\"ok\":true") {
|
||||||
|
wt_sweep(dir)
|
||||||
|
println("[persist] wt_drain: owner REJECTED the delta — " + int_to_str(found)
|
||||||
|
+ " stay queued in " + dir + ": " + resp)
|
||||||
|
return -1
|
||||||
|
}
|
||||||
|
|
||||||
|
let added: Int = json_get_int(resp, "nodes_added")
|
||||||
|
let added_e: Int = json_get_int(resp, "edges_added")
|
||||||
|
|
||||||
|
// Confirmed. Truncate the drained spool files so they are not re-pushed.
|
||||||
|
// Truncation (not deletion) because the runtime exposes no unlink builtin;
|
||||||
|
// an emptied file is inert to the loop above. The zero-byte husks are then
|
||||||
|
// swept below.
|
||||||
|
let paths = str_split(drained, "\n")
|
||||||
|
let pn: Int = el_list_len(paths)
|
||||||
|
let k: Int = 0
|
||||||
|
while k < pn {
|
||||||
|
let one: String = el_list_get(paths, k)
|
||||||
|
if !str_eq(one, "") { fs_write(one, "") }
|
||||||
|
let k = k + 1
|
||||||
|
}
|
||||||
|
wt_sweep(dir)
|
||||||
|
|
||||||
|
println("[persist] wt_drain: pushed " + int_to_str(found) + " deltas -> owner added "
|
||||||
|
+ int_to_str(added) + " nodes, " + int_to_str(added_e) + " edges")
|
||||||
|
return added
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_durable — is this id present AT THE OWNER? The only honest answer to
|
||||||
|
// "did my write persist" in HTTP mode.
|
||||||
|
//
|
||||||
|
// In file mode the soul IS the owner, so the local read-back is the owner-side
|
||||||
|
// read-back and this collapses to the pre-existing check.
|
||||||
|
//
|
||||||
|
// nodes_added from wt_drain is NOT a substitute: a concurrent drain may have
|
||||||
|
// already pushed this node, making our own added count 0 while the node is
|
||||||
|
// perfectly durable. Presence at the owner is the fact; counts are telemetry.
|
||||||
|
fn wt_durable(id: String) -> Bool {
|
||||||
|
if str_eq(id, "") { return false }
|
||||||
|
if !wt_enabled() {
|
||||||
|
let local: String = engram_get_node_json(id)
|
||||||
|
return !str_eq(local, "") && !str_eq(local, "null") && !str_eq(local, "{}")
|
||||||
|
}
|
||||||
|
let url: String = wt_engram_url()
|
||||||
|
let resp: String = http_get(url + "/api/nodes/" + id)
|
||||||
|
if str_eq(resp, "") { return false }
|
||||||
|
if str_eq(resp, "{}") { return false }
|
||||||
|
return str_contains(resp, "\"id\"")
|
||||||
|
}
|
||||||
|
|
||||||
|
// wt_commit — flush, then assert at the owner. The receipt callers should use.
|
||||||
|
// Deliberately NOT a fixed success shape: it can and does return false while the
|
||||||
|
// local write is perfectly fine in RAM, which is the true state of affairs when
|
||||||
|
// the owner is unreachable.
|
||||||
|
fn wt_commit(id: String) -> Bool {
|
||||||
|
if str_eq(id, "") { return false }
|
||||||
|
if !wt_enabled() {
|
||||||
|
let local: String = engram_get_node_json(id)
|
||||||
|
return !str_eq(local, "") && !str_eq(local, "null") && !str_eq(local, "{}")
|
||||||
|
}
|
||||||
|
let pushed: Int = wt_drain()
|
||||||
|
return wt_durable(id)
|
||||||
|
}
|
||||||
@@ -186,7 +186,7 @@ fn route_imprint_contextual(body: String) -> String {
|
|||||||
return "{\"ok\":false,\"error\":\"empty body\"}"
|
return "{\"ok\":false,\"error\":\"empty body\"}"
|
||||||
}
|
}
|
||||||
let tags: String = "[\"imprint\",\"contextual\"]"
|
let tags: String = "[\"imprint\",\"contextual\"]"
|
||||||
let id: String = engram_node_full(
|
let id: String = wt_node(
|
||||||
body,
|
body,
|
||||||
"Entity",
|
"Entity",
|
||||||
"imprint:contextual",
|
"imprint:contextual",
|
||||||
@@ -208,7 +208,7 @@ fn route_imprint_user(body: String) -> String {
|
|||||||
return "{\"ok\":false,\"error\":\"empty body\"}"
|
return "{\"ok\":false,\"error\":\"empty body\"}"
|
||||||
}
|
}
|
||||||
let tags: String = "[\"imprint\",\"user\"]"
|
let tags: String = "[\"imprint\",\"user\"]"
|
||||||
let id: String = engram_node_full(
|
let id: String = wt_node(
|
||||||
body,
|
body,
|
||||||
"Entity",
|
"Entity",
|
||||||
"imprint:user",
|
"imprint:user",
|
||||||
@@ -239,7 +239,7 @@ fn route_synthesize(body: String) -> String {
|
|||||||
}
|
}
|
||||||
let req: String = "synthesize " + parent_a + " " + parent_b
|
let req: String = "synthesize " + parent_a + " " + parent_b
|
||||||
let tags: String = "[\"soul-inbox-pending\",\"synthesis-request\"]"
|
let tags: String = "[\"soul-inbox-pending\",\"synthesis-request\"]"
|
||||||
engram_node_full(
|
wt_node(
|
||||||
req,
|
req,
|
||||||
"Entity",
|
"Entity",
|
||||||
"synthesis-request",
|
"synthesis-request",
|
||||||
@@ -395,7 +395,28 @@ fn handle_connectors(method: String, clean: String, body: String) -> String {
|
|||||||
return "{\"ok\":false,\"error\":\"unknown connectors route\"}"
|
return "{\"ok\":false,\"error\":\"unknown connectors route\"}"
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// handle_request — the soul's HTTP entry point.
|
||||||
|
//
|
||||||
|
// NOTE ON THE NAME (neuron#117): the el runtime resolves this handler by NAME
|
||||||
|
// via dlsym(RTLD_DEFAULT, "handle_request") — that is why the Linux build must
|
||||||
|
// link -rdynamic. So the dispatcher body moved to route_dispatch and the name
|
||||||
|
// `handle_request` stays put as a thin wrapper. Do not rename it back.
|
||||||
|
//
|
||||||
|
// The wrapper exists to give the write-through boundary a guaranteed flush
|
||||||
|
// point. route_dispatch returns from ~60 places; a per-branch flush would be
|
||||||
|
// forgotten on the 61st. Draining here means EVERY request that staged a write
|
||||||
|
// pushes it before the connection closes, whatever route produced it, including
|
||||||
|
// routes added later that know nothing about persistence.
|
||||||
|
//
|
||||||
|
// wt_drain is a no-op (no HTTP, no cost) when nothing is staged and when the
|
||||||
|
// soul is not in HTTP-engram mode, so this is free on read traffic.
|
||||||
fn handle_request(method: String, path: String, body: String) -> String {
|
fn handle_request(method: String, path: String, body: String) -> String {
|
||||||
|
let resp: String = route_dispatch(method, path, body)
|
||||||
|
let flushed: Int = wt_drain()
|
||||||
|
return resp
|
||||||
|
}
|
||||||
|
|
||||||
|
fn route_dispatch(method: String, path: String, body: String) -> String {
|
||||||
let clean: String = strip_query(path)
|
let clean: String = strip_query(path)
|
||||||
|
|
||||||
// ACTIVITY STAMP (2026-07-30 self-review): every inbound HTTP request —
|
// ACTIVITY STAMP (2026-07-30 self-review): every inbound HTTP request —
|
||||||
@@ -432,10 +453,27 @@ fn handle_request(method: String, path: String, body: String) -> String {
|
|||||||
return engram_scan_nodes_json(9999, 0)
|
return engram_scan_nodes_json(9999, 0)
|
||||||
}
|
}
|
||||||
if str_eq(clean, "/api/graph/edges") {
|
if str_eq(clean, "/api/graph/edges") {
|
||||||
// TODO(reliability #8): engram_save races with awareness loop mem_save().
|
// FIXED (neuron#117): this GET used to engram_save() straight over
|
||||||
// Both now use atomic write-to-temp+rename (el_runtime.c). Serialised
|
// ~/.neuron/engram/snapshot.json — a READ route, in a process that is
|
||||||
// by engram_global_mu. Future: add engram_edges_json() builtin.
|
// NOT the persistence owner, overwriting the owner's canonical file
|
||||||
let snap_path: String = env("HOME") + "/.neuron/engram/snapshot.json"
|
// on every call. It broke soul.el:571-573 ("the soul must NEVER write
|
||||||
|
// to the local snapshot") and it is the same defect class Will removed
|
||||||
|
// from the engram itself in el `dc39a61` ("stop read routes clobbering
|
||||||
|
// canonical snapshot"), where route_scan_edges/route_sync were moved
|
||||||
|
// to scratch paths for exactly this reason. It was also the race the
|
||||||
|
// old TODO(reliability #8) admitted to.
|
||||||
|
//
|
||||||
|
// Export to a scratch path instead. Same response, no canonical write.
|
||||||
|
// The soul's own snapshot writes are otherwise already gated behind
|
||||||
|
// state key "soul_snapshot_path", which is set ONLY in the genesis
|
||||||
|
// file-mode branch (soul.el: is_genesis && safe_to_seed, and
|
||||||
|
// safe_to_seed is unconditionally false when ENGRAM_URL is set) — so
|
||||||
|
// after this change the soul writes nothing at all in HTTP mode.
|
||||||
|
// Future: add an engram_edges_json() builtin and drop the file round
|
||||||
|
// trip entirely.
|
||||||
|
let scratch_dir: String = env("TMPDIR")
|
||||||
|
let scratch_base: String = if str_eq(scratch_dir, "") { "/tmp" } else { scratch_dir }
|
||||||
|
let snap_path: String = scratch_base + "/soul-edges-export-" + state_get("soul_cgi_id") + ".json"
|
||||||
engram_save(snap_path)
|
engram_save(snap_path)
|
||||||
let snap: String = fs_read(snap_path)
|
let snap: String = fs_read(snap_path)
|
||||||
let edges_raw: String = json_get_raw(snap, "edges")
|
let edges_raw: String = json_get_raw(snap, "edges")
|
||||||
|
|||||||
@@ -204,7 +204,7 @@ fn safety_log_bell(level: String, reason: String, input_summary: String) -> Stri
|
|||||||
// Emit a fallback println so the bell event leaves at least a log trace even
|
// Emit a fallback println so the bell event leaves at least a log trace even
|
||||||
// when engram is degraded. This does not replace engram persistence -- it is a
|
// when engram is degraded. This does not replace engram persistence -- it is a
|
||||||
// last-resort audit trail when the primary write cannot be confirmed.
|
// last-resort audit trail when the primary write cannot be confirmed.
|
||||||
let node_id: String = engram_node_full(
|
let node_id: String = wt_node(
|
||||||
content,
|
content,
|
||||||
"BellEvent",
|
"BellEvent",
|
||||||
"bell:" + level,
|
"bell:" + level,
|
||||||
|
|||||||
+7
-7
@@ -87,7 +87,7 @@ fn session_create(body: String) -> String {
|
|||||||
let folder: String = json_get(body, "folder")
|
let folder: String = json_get(body, "folder")
|
||||||
let content: String = session_make_content(id, title, ts, ts, folder)
|
let content: String = session_make_content(id, title, ts, ts, folder)
|
||||||
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
||||||
let node_id: String = engram_node_full(
|
let node_id: String = wt_node(
|
||||||
content, "Conversation", "session:meta",
|
content, "Conversation", "session:meta",
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -358,7 +358,7 @@ fn session_update_patch(session_id: String, body: String) -> String {
|
|||||||
let created_int: Int = str_to_int(old_created)
|
let created_int: Int = str_to_int(old_created)
|
||||||
let new_content: String = session_make_content(session_id, eff_title, created_int, ts, eff_folder)
|
let new_content: String = session_make_content(session_id, eff_title, created_int, ts, eff_folder)
|
||||||
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
||||||
let new_node_id: String = engram_node_full(
|
let new_node_id: String = wt_node(
|
||||||
new_content, "Conversation", "session:meta",
|
new_content, "Conversation", "session:meta",
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -456,7 +456,7 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
|
|||||||
// TODO(reliability #7): delete-then-insert is not atomic — concurrent saves for the
|
// TODO(reliability #7): delete-then-insert is not atomic — concurrent saves for the
|
||||||
// same session can produce orphan history nodes. State is primary truth; engram fallback.
|
// same session can produce orphan history nodes. State is primary truth; engram fallback.
|
||||||
let tags: String = "[\"session\",\"session-history\",\"Conversation\"]"
|
let tags: String = "[\"session\",\"session-history\",\"Conversation\"]"
|
||||||
let discard: String = engram_node_full(
|
let discard: String = wt_node(
|
||||||
hist, "Conversation", "session:messages:" + session_id,
|
hist, "Conversation", "session:messages:" + session_id,
|
||||||
el_from_float(0.6), el_from_float(0.6), el_from_float(0.9),
|
el_from_float(0.6), el_from_float(0.6), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -488,7 +488,7 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
|
|||||||
+ " | ts:" + int_to_str(ts_now)
|
+ " | ts:" + int_to_str(ts_now)
|
||||||
let summary_tags: String = "[\"session-emotional-summary\",\"affective\",\"bell:" + eff_level + "\",\"BellEvent\"]"
|
let summary_tags: String = "[\"session-emotional-summary\",\"affective\",\"bell:" + eff_level + "\",\"BellEvent\"]"
|
||||||
let summary_sal: String = if str_eq(eff_level, "hard") { el_from_float(0.95) } else { el_from_float(0.85) }
|
let summary_sal: String = if str_eq(eff_level, "hard") { el_from_float(0.95) } else { el_from_float(0.85) }
|
||||||
let sum_discard: String = engram_node_full(
|
let sum_discard: String = wt_node(
|
||||||
summary_content,
|
summary_content,
|
||||||
"BellEvent",
|
"BellEvent",
|
||||||
"session:emotional-summary",
|
"session:emotional-summary",
|
||||||
@@ -529,7 +529,7 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
|
|||||||
if !str_eq(ot_id, "") { engram_forget(ot_id) }
|
if !str_eq(ot_id, "") { engram_forget(ot_id) }
|
||||||
let oti = oti + 1
|
let oti = oti + 1
|
||||||
}
|
}
|
||||||
let discard_topic: String = engram_node_full(
|
let discard_topic: String = wt_node(
|
||||||
topic_content, "Conversation", topic_label,
|
topic_content, "Conversation", topic_label,
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
"Episodic", topic_tags
|
"Episodic", topic_tags
|
||||||
@@ -582,7 +582,7 @@ fn session_update_meta_timestamp(session_id: String) -> Void {
|
|||||||
let created_int: Int = str_to_int(old_created)
|
let created_int: Int = str_to_int(old_created)
|
||||||
let new_content: String = session_make_content(session_id, old_title, created_int, ts, old_folder)
|
let new_content: String = session_make_content(session_id, old_title, created_int, ts, old_folder)
|
||||||
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
||||||
let new_id: String = engram_node_full(
|
let new_id: String = wt_node(
|
||||||
new_content, "Conversation", "session:meta",
|
new_content, "Conversation", "session:meta",
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
@@ -629,7 +629,7 @@ fn session_auto_title(session_id: String, first_message: String) -> Void {
|
|||||||
let created_int: Int = str_to_int(old_created)
|
let created_int: Int = str_to_int(old_created)
|
||||||
let new_content: String = session_make_content(session_id, new_title, created_int, ts, old_folder)
|
let new_content: String = session_make_content(session_id, new_title, created_int, ts, old_folder)
|
||||||
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
let tags: String = "[\"session\",\"session:meta\",\"Conversation\"]"
|
||||||
let new_id: String = engram_node_full(
|
let new_id: String = wt_node(
|
||||||
new_content, "Conversation", "session:meta",
|
new_content, "Conversation", "session:meta",
|
||||||
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
|
||||||
"Episodic", tags
|
"Episodic", tags
|
||||||
|
|||||||
@@ -657,6 +657,23 @@ if is_genesis && safe_to_seed {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// CRASH RECOVERY (neuron#117). Deltas the previous process staged but could not
|
||||||
|
// hand to the owner are still on disk — the spool is a filesystem queue, not a
|
||||||
|
// memory buffer, precisely so that a soul that died mid-flight does not take its
|
||||||
|
// unpushed writes with it. Drain them before serving, so recovered memories are
|
||||||
|
// durable and recallable from the owner from the first request onward.
|
||||||
|
//
|
||||||
|
// Safe on a clean boot: an empty spool means no HTTP call at all. Safe in file
|
||||||
|
// mode: wt_drain returns immediately when ENGRAM_URL is unset.
|
||||||
|
let wt_recovered: Int = wt_drain()
|
||||||
|
if wt_recovered > 0 {
|
||||||
|
println("[soul] write-through: recovered " + int_to_str(wt_recovered)
|
||||||
|
+ " nodes from a previous process's spool -> persistence owner")
|
||||||
|
}
|
||||||
|
if wt_recovered < 0 {
|
||||||
|
println("[soul] write-through: spool present but the persistence owner is unreachable — queued, will retry on heartbeat")
|
||||||
|
}
|
||||||
|
|
||||||
println("[soul] serving on port " + int_to_str(port))
|
println("[soul] serving on port " + int_to_str(port))
|
||||||
http_serve_async(port, "handle_request")
|
http_serve_async(port, "handle_request")
|
||||||
println("[soul] awareness loop starting")
|
println("[soul] awareness loop starting")
|
||||||
|
|||||||
+2
-2
@@ -11,7 +11,7 @@ import "memory.el"
|
|||||||
fn steward_log_event(kind: String, detail: String) -> Void {
|
fn steward_log_event(kind: String, detail: String) -> Void {
|
||||||
let content: String = "STEWARD:" + kind + " | " + detail
|
let content: String = "STEWARD:" + kind + " | " + detail
|
||||||
let tags: String = "[\"stewardship\",\"steward:" + kind + "\"]"
|
let tags: String = "[\"stewardship\",\"steward:" + kind + "\"]"
|
||||||
let discard: String = engram_node_full(
|
let discard: String = wt_node(
|
||||||
content,
|
content,
|
||||||
"StewardshipEvent",
|
"StewardshipEvent",
|
||||||
"steward:" + kind,
|
"steward:" + kind,
|
||||||
@@ -221,7 +221,7 @@ fn steward_fingerprint_session(input: String, session_id: String) -> String {
|
|||||||
+ " formality=" + fs_str
|
+ " formality=" + fs_str
|
||||||
+ " time=" + tb_str
|
+ " time=" + tb_str
|
||||||
let sample_tags: String = "[\"behavior\",\"BehaviorSample\",\"stewardship\"]"
|
let sample_tags: String = "[\"behavior\",\"BehaviorSample\",\"stewardship\"]"
|
||||||
let discard: String = engram_node_full(
|
let discard: String = wt_node(
|
||||||
sample_content,
|
sample_content,
|
||||||
"BehaviorSample",
|
"BehaviorSample",
|
||||||
"behavior:" + session_id,
|
"behavior:" + session_id,
|
||||||
|
|||||||
Executable
+59
@@ -0,0 +1,59 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# build-soul-from-dist.sh — build a deployable soul from the SAME input CI compiles.
|
||||||
|
#
|
||||||
|
# THE PROBLEM THIS CLOSES: until now, deploys were built by build-soul.sh, which
|
||||||
|
# compiles a scratch amalgam and never touches dist/soul.c. CI compiles dist/soul.c.
|
||||||
|
# Two lineages. On 2026-08-09 the committed input fell 2,761 bytes behind the sources
|
||||||
|
# while three binaries built the other way were installed on the operator machine —
|
||||||
|
# so "what runs" and "what the repo says builds" were different artifacts again,
|
||||||
|
# which is the whole of #133 and #111 wearing new clothes.
|
||||||
|
#
|
||||||
|
# This builds from dist/soul.c with CI's own flags, after asserting that dist/soul.c
|
||||||
|
# actually matches the .el sources, and writes a provenance sidecar so a deployer can
|
||||||
|
# refuse anything of unknown origin.
|
||||||
|
#
|
||||||
|
# -rdynamic and -DHAVE_CURL are copied from .gitea/workflows/ci.yaml deliberately.
|
||||||
|
# The CI comment explains -rdynamic: without it the runtime cannot resolve its HTTP
|
||||||
|
# handler by name via dlsym and the binary serves nothing on every route.
|
||||||
|
#
|
||||||
|
# usage: build-soul-from-dist.sh <out-binary>
|
||||||
|
set -u
|
||||||
|
OUT="${1:?usage: build-soul-from-dist.sh <out-binary>}"
|
||||||
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
RUNTIME="$ROOT/vendor/el-runtime/v1.0.0-20260501"
|
||||||
|
|
||||||
|
cd "$ROOT" || exit 2
|
||||||
|
|
||||||
|
echo "[build-from-dist] GATE: does dist/soul.c match the sources?"
|
||||||
|
if ! ./tools/soulc-stamp.sh --check; then
|
||||||
|
echo "[build-from-dist] REFUSING — the build input is stale. Regenerate and stamp first." >&2
|
||||||
|
exit 9
|
||||||
|
fi
|
||||||
|
|
||||||
|
[ -f "$RUNTIME/el_runtime.c" ] || { echo "pinned runtime missing at $RUNTIME" >&2; exit 2; }
|
||||||
|
|
||||||
|
echo "[build-from-dist] compiling dist/soul.c with CI's flags"
|
||||||
|
cc -O2 -DHAVE_CURL -rdynamic \
|
||||||
|
-I"$RUNTIME" \
|
||||||
|
dist/soul.c \
|
||||||
|
"$RUNTIME/el_runtime.c" \
|
||||||
|
-lcurl -lpthread -lm \
|
||||||
|
-o "$OUT" || { echo "[build-from-dist] COMPILE FAILED" >&2; exit 3; }
|
||||||
|
|
||||||
|
# Provenance sidecar: what a deployer checks before installing anything.
|
||||||
|
SRC_SHA="$(shasum -a 256 dist/soul.c | awk '{print $1}')"
|
||||||
|
STAMP_SHA="$(shasum -a 256 dist/soul.c.stamp | awk '{print $1}')"
|
||||||
|
COMMIT="$(git rev-parse HEAD 2>/dev/null || echo unknown)"
|
||||||
|
DIRTY="clean"; [ -n "$(git status --porcelain -- '*.el' dist/soul.c 2>/dev/null)" ] && DIRTY="DIRTY"
|
||||||
|
cat > "$OUT.provenance" <<EOF
|
||||||
|
{"built_from":"dist/soul.c",
|
||||||
|
"dist_soul_c_sha256":"$SRC_SHA",
|
||||||
|
"stamp_sha256":"$STAMP_SHA",
|
||||||
|
"git_commit":"$COMMIT",
|
||||||
|
"worktree":"$DIRTY",
|
||||||
|
"runtime":"vendor/el-runtime/v1.0.0-20260501",
|
||||||
|
"flags":"-O2 -DHAVE_CURL -rdynamic"}
|
||||||
|
EOF
|
||||||
|
|
||||||
|
echo "[build-from-dist] OK -> $OUT ($(wc -c < "$OUT" | tr -d ' ') bytes)"
|
||||||
|
echo "[build-from-dist] provenance -> $OUT.provenance (commit ${COMMIT:0:8}, worktree $DIRTY)"
|
||||||
Executable
+83
@@ -0,0 +1,83 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# soulc-stamp.sh — make it impossible for dist/soul.c to drift from the sources
|
||||||
|
# in silence.
|
||||||
|
#
|
||||||
|
# THE PROBLEM (neuron#133, and its own words): "Nothing in the tree regenerates
|
||||||
|
# this file. Only a human running the recipe. It lags in batches, never
|
||||||
|
# per-change, and it will drift again."
|
||||||
|
#
|
||||||
|
# It drifted. On 2026-08-07 a CI or GKE build off main would have shipped an
|
||||||
|
# engine with NONE of five merged fixes — including a P0 safety fix — while
|
||||||
|
# main's source read as correct. CI compiles dist/soul.c, not the .el files, so
|
||||||
|
# the source being right is not the same as the build being right.
|
||||||
|
#
|
||||||
|
# WHY A STAMP AND NOT AUTO-REGENERATION: the CI workflow says elc cannot run on
|
||||||
|
# the runner ("elb on Linux would OOM the runner (elc uses 24GB+ virtual memory
|
||||||
|
# on a 16GB host)"). So the build cannot regenerate the file itself. What it CAN
|
||||||
|
# do, for free and with no compiler, is refuse to compile a stale one.
|
||||||
|
#
|
||||||
|
# The stamp records a fingerprint of every .el source that feeds the amalgam at
|
||||||
|
# the moment it was generated. --check recomputes and compares. Divergence is a
|
||||||
|
# build failure with the recipe in the message, not a silent ship.
|
||||||
|
#
|
||||||
|
# soulc-stamp.sh --write after regenerating dist/soul.c (records the fingerprint)
|
||||||
|
# soulc-stamp.sh --check in CI, before the compile (fails on drift)
|
||||||
|
set -u
|
||||||
|
MODE="${1:---check}"
|
||||||
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||||
|
STAMP="$ROOT/dist/soul.c.stamp"
|
||||||
|
AMALGAM="$ROOT/dist/soul.c"
|
||||||
|
|
||||||
|
# Every .el at the repo root is an input to the amalgam. Sorted so the hash is
|
||||||
|
# order-independent; content-only so timestamps and checkouts do not perturb it.
|
||||||
|
fingerprint() {
|
||||||
|
(
|
||||||
|
cd "$ROOT" || exit 1
|
||||||
|
for f in $(ls -1 *.el 2>/dev/null | sort); do
|
||||||
|
printf '%s %s\n' "$(shasum -a 256 "$f" | awk '{print $1}')" "$f"
|
||||||
|
done
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
case "$MODE" in
|
||||||
|
--write)
|
||||||
|
[ -f "$AMALGAM" ] || { echo "no dist/soul.c to stamp — regenerate it first" >&2; exit 2; }
|
||||||
|
{
|
||||||
|
echo "# soul.c.stamp — fingerprint of the .el sources dist/soul.c was generated from."
|
||||||
|
echo "# Written by tools/soulc-stamp.sh --write. Do not hand-edit."
|
||||||
|
echo "# generated_amalgam_sha256 $(shasum -a 256 "$AMALGAM" | awk '{print $1}')"
|
||||||
|
echo "# generated_amalgam_bytes $(wc -c < "$AMALGAM" | tr -d ' ')"
|
||||||
|
fingerprint
|
||||||
|
} > "$STAMP"
|
||||||
|
echo "stamped $(fingerprint | wc -l | tr -d ' ') sources -> dist/soul.c.stamp"
|
||||||
|
;;
|
||||||
|
|
||||||
|
--check)
|
||||||
|
if [ ! -f "$STAMP" ]; then
|
||||||
|
echo "FAIL: dist/soul.c.stamp is missing — the build input is unverifiable." >&2
|
||||||
|
echo " Regenerate the amalgam, then: tools/soulc-stamp.sh --write" >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
RECORDED="$(grep -v '^#' "$STAMP")"
|
||||||
|
CURRENT="$(fingerprint)"
|
||||||
|
if [ "$RECORDED" = "$CURRENT" ]; then
|
||||||
|
echo "soulc-stamp: OK — dist/soul.c matches the .el sources"
|
||||||
|
exit 0
|
||||||
|
fi
|
||||||
|
echo "FAIL: dist/soul.c is STALE. It does not match the current .el sources." >&2
|
||||||
|
echo "" >&2
|
||||||
|
echo "CI compiles dist/soul.c, not the .el files. Shipping this means shipping" >&2
|
||||||
|
echo "an engine that does not contain the merged source. That is neuron#133," >&2
|
||||||
|
echo "which once hid five merged fixes including a P0 safety fix." >&2
|
||||||
|
echo "" >&2
|
||||||
|
echo "Sources that changed since the amalgam was generated:" >&2
|
||||||
|
diff <(printf '%s\n' "$RECORDED") <(printf '%s\n' "$CURRENT") \
|
||||||
|
| grep -E '^[<>]' | awk '{print " " $1 " " $3}' | sort -u >&2
|
||||||
|
echo "" >&2
|
||||||
|
echo "Fix: regenerate the amalgam, then tools/soulc-stamp.sh --write" >&2
|
||||||
|
exit 1
|
||||||
|
;;
|
||||||
|
|
||||||
|
*)
|
||||||
|
echo "usage: soulc-stamp.sh [--check|--write]" >&2; exit 2 ;;
|
||||||
|
esac
|
||||||
Reference in New Issue
Block a user