|
|
|
@@ -94,39 +94,18 @@ fn hist_append(hist: String, role: String, content: String) -> String {
|
|
|
|
|
return "[" + inner + "," + entry + "]"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// hist_trim — drop the oldest two entries from a history JSON array.
|
|
|
|
|
//
|
|
|
|
|
// Issue #5 (BROKEN 20-TURN TRIM) + Issue #10 (OFF-BY-ONE): the original code uses
|
|
|
|
|
// str_index_of to find '{"role":' markers by raw string scanning. If any message content
|
|
|
|
|
// contains the literal string '{"role":' (e.g. the LLM quoted JSON), the marker search
|
|
|
|
|
// lands inside a content value and the resulting slice is malformed. Additionally, the
|
|
|
|
|
// function had no minimum-retained-count guard.
|
|
|
|
|
//
|
|
|
|
|
// Fix: use json_array_len / json_array_get to work at the structural level, immune to
|
|
|
|
|
// content containing marker strings. Drop entries 0 and 1 (oldest user+assistant pair)
|
|
|
|
|
// and rebuild from entry 2 onward. Minimum retained count: 2 entries (never over-trim).
|
|
|
|
|
fn hist_trim(hist: String) -> String {
|
|
|
|
|
let total: Int = json_array_len(hist)
|
|
|
|
|
// Safety: never trim below 2 entries. If already at or below the minimum, return unchanged.
|
|
|
|
|
if total <= 2 {
|
|
|
|
|
return hist
|
|
|
|
|
let inner: String = str_slice(hist, 1, str_len(hist) - 1)
|
|
|
|
|
let marker: String = "{\"role\":"
|
|
|
|
|
let i1: Int = str_index_of(inner, marker)
|
|
|
|
|
let tail1: String = str_slice(inner, i1 + 1, str_len(inner))
|
|
|
|
|
let i2: Int = str_index_of(tail1, marker)
|
|
|
|
|
let tail2: String = str_slice(tail1, i2 + 1, str_len(tail1))
|
|
|
|
|
let i3: Int = str_index_of(tail2, marker)
|
|
|
|
|
if i3 >= 0 {
|
|
|
|
|
return "[" + str_slice(tail2, i3, str_len(tail2)) + "]"
|
|
|
|
|
}
|
|
|
|
|
// Drop entry 0 and entry 1 (oldest user+assistant pair). Rebuild from entry 2 onward.
|
|
|
|
|
let result: String = ""
|
|
|
|
|
let i: Int = 2
|
|
|
|
|
while i < total {
|
|
|
|
|
let entry: String = json_array_get(hist, i)
|
|
|
|
|
let result = if str_eq(result, "") {
|
|
|
|
|
entry
|
|
|
|
|
} else {
|
|
|
|
|
result + "," + entry
|
|
|
|
|
}
|
|
|
|
|
let i = i + 1
|
|
|
|
|
}
|
|
|
|
|
if str_eq(result, "") {
|
|
|
|
|
return hist
|
|
|
|
|
}
|
|
|
|
|
return "[" + result + "]"
|
|
|
|
|
return hist
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// clean_llm_response — strips GPT-2 BPE byte-to-unicode artifacts that vLLM
|
|
|
|
@@ -145,72 +124,32 @@ fn clean_llm_response(s: String) -> String {
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// conv_history_persist — save conversation history to engram for cross-restart continuity.
|
|
|
|
|
// Stores as a Conversation node with label "conv:history".
|
|
|
|
|
//
|
|
|
|
|
// Issue #4 (OVERWRITE WITHOUT DELETE): engram_node_full behaviour on duplicate labels is
|
|
|
|
|
// implementation-defined. If it appends rather than upserts, stale older nodes accumulate.
|
|
|
|
|
// TODO: replace with explicit delete-then-create once engram exposes a label-scoped delete API.
|
|
|
|
|
//
|
|
|
|
|
// Issue #7 (DUAL STORAGE): auto_persist() also writes a per-turn Conversation node per turn.
|
|
|
|
|
// Both run every turn for different purposes (rolling array vs. Q&A snapshot). Documented here.
|
|
|
|
|
// Stores as a Conversation node. Overwrites by using consistent label "conv:history".
|
|
|
|
|
fn conv_history_persist(hist: String) -> Void {
|
|
|
|
|
if str_eq(hist, "") { return "" }
|
|
|
|
|
if str_eq(hist, "[]") { return "" }
|
|
|
|
|
// Issue #6 (PARTIAL-WRITE GUARD): refuse to persist a blob that is not a complete JSON
|
|
|
|
|
// array. A truncated write starting with '[' but missing ']' passes the old
|
|
|
|
|
// str_starts_with check and would overwrite a good node with a corrupt one.
|
|
|
|
|
if !str_starts_with(hist, "[") { return "" }
|
|
|
|
|
if !str_contains(hist, "]") { return "" }
|
|
|
|
|
let ts: Int = time_now()
|
|
|
|
|
let tags: String = "[\"conv-history\",\"persistent\"]"
|
|
|
|
|
let node_id: String = engram_node_full(
|
|
|
|
|
hist, "Conversation", "conv:history",
|
|
|
|
|
el_from_float(0.7), el_from_float(0.8), el_from_float(0.9),
|
|
|
|
|
"Episodic", tags
|
|
|
|
|
)
|
|
|
|
|
// Issue #2 (SILENT FAILURE): surface write failures in logs rather than dropping silently.
|
|
|
|
|
if str_eq(node_id, "") {
|
|
|
|
|
println("[chat] conv_history_persist: engram_node_full returned empty — history node may be lost")
|
|
|
|
|
println("[chat] conv_history_persist: engram_node_full returned empty — history node lost")
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// conv_history_load — restore conversation history from engram on first access.
|
|
|
|
|
//
|
|
|
|
|
// Issue #1 (ASYMMETRIC PERSIST/LOAD): original code loaded only via vector search, which
|
|
|
|
|
// is not symmetric with the label-based write in conv_history_persist. A cold or corrupt
|
|
|
|
|
// vector index returns [] even when the node exists on disk. Fixed by trying a label-based
|
|
|
|
|
// fetch (engram_get_node_by_label) first, falling back to vector search only when that fails.
|
|
|
|
|
//
|
|
|
|
|
// Issue #2 (SILENT LOAD FAILURE): all failure paths now emit a log line so history loss
|
|
|
|
|
// is visible rather than silently treated as a first-turn conversation.
|
|
|
|
|
//
|
|
|
|
|
// Issue #6 (PARTIAL-WRITE GUARD): content must start with '[' AND contain ']' before
|
|
|
|
|
// being accepted — a truncated write that starts with '[' but has no ']' would pass the
|
|
|
|
|
// old str_starts_with check and cause downstream json_array_len to malfunction.
|
|
|
|
|
// Returns the most recent "conv:history" node content, or "" if none found.
|
|
|
|
|
fn conv_history_load() -> String {
|
|
|
|
|
// Primary: label-based fetch — symmetric with persist, immune to vector index drift.
|
|
|
|
|
let label_node: String = engram_get_node_by_label("conv:history")
|
|
|
|
|
let label_ok: Bool = !str_eq(label_node, "") && !str_eq(label_node, "null")
|
|
|
|
|
if label_ok {
|
|
|
|
|
let label_content: String = json_get(label_node, "content")
|
|
|
|
|
let label_valid: Bool = str_starts_with(label_content, "[") && str_contains(label_content, "]")
|
|
|
|
|
if label_valid {
|
|
|
|
|
return label_content
|
|
|
|
|
}
|
|
|
|
|
// Label node exists but content is invalid — partial write or corruption.
|
|
|
|
|
println("[chat] conv_history_load: label node found but content invalid — falling back to vector search")
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Fallback: vector search — covers nodes indexed before this fix, or on cold index.
|
|
|
|
|
let results: String = engram_search_json("conv:history", 3)
|
|
|
|
|
if str_eq(results, "") { return "" }
|
|
|
|
|
if str_eq(results, "[]") { return "" }
|
|
|
|
|
let node: String = json_array_get(results, 0)
|
|
|
|
|
let content: String = json_get(node, "content")
|
|
|
|
|
// Issue #6: full partial-write guard — require both '[' prefix AND ']' presence.
|
|
|
|
|
if !str_starts_with(content, "[") || !str_contains(content, "]") {
|
|
|
|
|
println("[chat] conv_history_load: vector search result content invalid — treating as first turn")
|
|
|
|
|
return ""
|
|
|
|
|
}
|
|
|
|
|
// Validate it looks like a JSON array
|
|
|
|
|
if !str_starts_with(content, "[") { return "" }
|
|
|
|
|
return content
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
@@ -221,13 +160,6 @@ fn handle_chat(body: String) -> String {
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Load history BEFORE compiling context so we can anchor activation to the thread.
|
|
|
|
|
// Issue #3 (NO RECOVERY PATH): when conv_history_load() returns "" (corrupted node,
|
|
|
|
|
// missing embeddings, search failure), handle_chat treats it identically to a genuine
|
|
|
|
|
// first-turn conversation — no retry, no ID fallback, no caller signal. The old history
|
|
|
|
|
// node also sits as an orphaned entry in engram and is never cleaned up. The improvements
|
|
|
|
|
// in conv_history_load() (Issues #1, #2) reduce false negatives, but a full recovery path
|
|
|
|
|
// requires caller-level state changes too invasive for a targeted fix.
|
|
|
|
|
// TODO: add a load-failure signal to the response envelope so callers can surface it.
|
|
|
|
|
let state_hist: String = state_get("conv_history")
|
|
|
|
|
let stored_hist: String = if str_eq(state_hist, "") { conv_history_load() } else { state_hist }
|
|
|
|
|
let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
|
|
|
|
@@ -257,13 +189,6 @@ fn handle_chat(body: String) -> String {
|
|
|
|
|
let req_model: String = json_get(body, "model")
|
|
|
|
|
let model: String = if str_eq(req_model, "") { chat_default_model() } else { req_model }
|
|
|
|
|
|
|
|
|
|
// Safety augmentation on the main chat path. Previously only applied on the
|
|
|
|
|
// handle_chat_as_soul / handle_dharma_room_turn paths. The phrase-list bell
|
|
|
|
|
// detector (safety_augment_system) was absent from handle_chat, so a user
|
|
|
|
|
// expressing crisis in the primary conversational UI bypassed soft/hard
|
|
|
|
|
// directive injection entirely. Applying it here before every llm_call_system.
|
|
|
|
|
let full_system = safety_augment_system(full_system, message)
|
|
|
|
|
|
|
|
|
|
let raw_response: String = llm_call_system(model, full_system, message)
|
|
|
|
|
|
|
|
|
|
let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
|
|
|
|
@@ -278,11 +203,6 @@ fn handle_chat(body: String) -> String {
|
|
|
|
|
|
|
|
|
|
let updated_hist: String = hist_append(stored_hist, "user", message)
|
|
|
|
|
let updated_hist2: String = hist_append(updated_hist, "assistant", raw_response)
|
|
|
|
|
// Issue #8 (NO MAX SIZE GUARD): the 20-turn count limit bounds entry count, but individual
|
|
|
|
|
// messages can be arbitrarily large (up to max_tokens = 4096 tokens each). At 20 turns the
|
|
|
|
|
// history blob can reach ~80KB before trim fires. engram_node_full has no apparent size cap.
|
|
|
|
|
// A byte-length cap would require truncating or summarising entries — too invasive here.
|
|
|
|
|
// TODO: add a byte-length cap (e.g. 32KB) that drops oldest entries until under limit.
|
|
|
|
|
let final_hist: String = if json_array_len(updated_hist2) > 20 {
|
|
|
|
|
hist_trim(updated_hist2)
|
|
|
|
|
} else {
|
|
|
|
@@ -592,17 +512,12 @@ fn dispatch_tool(tool_name: String, tool_input: String) -> String {
|
|
|
|
|
let path: String = json_get(tool_input, "path")
|
|
|
|
|
let old_text: String = json_get(tool_input, "old_text")
|
|
|
|
|
let new_text: String = json_get(tool_input, "new_text")
|
|
|
|
|
let root: String = agent_workspace_root()
|
|
|
|
|
if !path_within_root(path, root) {
|
|
|
|
|
return json_safe("denied: path is outside the agent workspace root")
|
|
|
|
|
}
|
|
|
|
|
let resolved: String = resolve_in_root(path, root)
|
|
|
|
|
let content: String = fs_read(resolved)
|
|
|
|
|
let content: String = fs_read(path)
|
|
|
|
|
if str_eq(content, "") {
|
|
|
|
|
return json_safe("{\"error\":\"file not found\"}")
|
|
|
|
|
}
|
|
|
|
|
let updated: String = str_replace(content, old_text, new_text)
|
|
|
|
|
fs_write(resolved, updated)
|
|
|
|
|
fs_write(path, updated)
|
|
|
|
|
return json_safe("{\"ok\":true}")
|
|
|
|
|
}
|
|
|
|
|
if str_eq(tool_name, "remember") {
|
|
|
|
@@ -725,6 +640,21 @@ fn handle_chat_agentic(body: String) -> String {
|
|
|
|
|
// Thread-aware activation: same logic as handle_chat.
|
|
|
|
|
// Use the session's or global history to anchor short messages to the thread.
|
|
|
|
|
let req_session: String = json_get(body, "session_id")
|
|
|
|
|
|
|
|
|
|
// ISSUE #6/#7: validate that the session_id actually exists before proceeding.
|
|
|
|
|
// Without this check the loop silently treats any unknown/fabricated session_id
|
|
|
|
|
// as a fresh session — history loads as empty and no error is returned to the caller.
|
|
|
|
|
// Only validate when a session_id is explicitly provided; anonymous calls
|
|
|
|
|
// (no session_id) continue to work for backward compatibility.
|
|
|
|
|
let session_valid: Bool = if str_eq(req_session, "") {
|
|
|
|
|
true
|
|
|
|
|
} else {
|
|
|
|
|
!str_contains(session_get(req_session), "\"error\"")
|
|
|
|
|
}
|
|
|
|
|
if !session_valid {
|
|
|
|
|
return "{\"error\":\"session not found\",\"session_id\":\"" + req_session + "\",\"reply\":\"\"}"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
let hist_key: String = if str_eq(req_session, "") { "conv_history" } else { "session_hist_" + req_session }
|
|
|
|
|
let agentic_hist: String = state_get(hist_key)
|
|
|
|
|
let agentic_hist_len: Int = if str_eq(agentic_hist, "") { 0 } else { json_array_len(agentic_hist) }
|
|
|
|
@@ -763,23 +693,12 @@ fn handle_chat_agentic(body: String) -> String {
|
|
|
|
|
|
|
|
|
|
// Persist the exchange to session/global history for thread continuity on next turn.
|
|
|
|
|
// Only save when the loop completed (reply present), not when tool_pending.
|
|
|
|
|
//
|
|
|
|
|
// Issue #9 (AGENTIC HISTORY NOT PERSISTED): the agentic path previously only saved
|
|
|
|
|
// history to in-process state (state_set), which is lost on restart. We now also call
|
|
|
|
|
// conv_history_persist() for the default session (hist_key == "conv_history") so agentic
|
|
|
|
|
// history survives restarts the same way non-agentic history does. Per-session histories
|
|
|
|
|
// (session_hist_<id>) are still in-process only — persisting all named sessions would
|
|
|
|
|
// require per-session engram labels, a larger change tracked separately.
|
|
|
|
|
let reply_text: String = json_get(result, "reply")
|
|
|
|
|
let discard_hist: Bool = if !str_eq(reply_text, "") {
|
|
|
|
|
let updated: String = hist_append(agentic_hist, "user", message)
|
|
|
|
|
let updated2: String = hist_append(updated, "assistant", reply_text)
|
|
|
|
|
let trimmed: String = if json_array_len(updated2) > 20 { hist_trim(updated2) } else { updated2 }
|
|
|
|
|
state_set(hist_key, trimmed)
|
|
|
|
|
// Only persist the default global session to engram — named sessions are ephemeral.
|
|
|
|
|
if str_eq(hist_key, "conv_history") {
|
|
|
|
|
conv_history_persist(trimmed)
|
|
|
|
|
}
|
|
|
|
|
true
|
|
|
|
|
} else { false }
|
|
|
|
|
|
|
|
|
@@ -1247,7 +1166,7 @@ fn auto_persist(req: String, resp: String) -> Void {
|
|
|
|
|
+ ",\"label\":\"chat:" + ts_str + "\"}"
|
|
|
|
|
|
|
|
|
|
let tags: String = "[\"Conversation\",\"chat\",\"timestamped\"]"
|
|
|
|
|
engram_node_full(
|
|
|
|
|
let persist_id: String = engram_node_full(
|
|
|
|
|
content,
|
|
|
|
|
"Conversation",
|
|
|
|
|
"chat:" + ts_str,
|
|
|
|
@@ -1257,6 +1176,9 @@ fn auto_persist(req: String, resp: String) -> Void {
|
|
|
|
|
"Episodic",
|
|
|
|
|
tags
|
|
|
|
|
)
|
|
|
|
|
if str_eq(persist_id, "") {
|
|
|
|
|
println("[chat] auto_persist: engram_node_full returned empty — conversation node lost (ts=" + ts_str + ")")
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// strengthen_chat_nodes — strengthen the engram nodes that were activated during a chat.
|
|
|
|
|
will.anderson