Merge pull request 'fix(routes): error handling, health endpoint, request validation, rate limiting' (#32) from improve/soul-routes-api into main

fix(routes): error handling, health endpoint, validation, rate limiting

chat.el

@@ -374,19 +374,11 @@ 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 }
 
-    // ISSUE 9: add safety_augment_system to primary /api/chat path.
-    // handle_chat was the only LLM path missing bell directive injection.
-    let full_system = safety_augment_system(full_system, message)
-
     let raw_response: String = llm_call_system(model, full_system, message)
 
-    // Issue #5: also catch empty string — llm_extract_text() in el_runtime.c silently
-    // returns "" when the response content array is missing or all blocks fail to parse.
-    // Without this guard an empty reply passes through as a silent empty response.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
-        || str_eq(raw_response, "")
     if is_error {
         return "{\"error\":\"llm unavailable\",\"response\":\"\"}"
     }
@@ -451,42 +443,6 @@ fn studio_tools_json() -> String {
     "]"
 }
 
-// ---------------------------------------------------------------------------
-// LLM reliability — issues that require C runtime fixes (el_runtime.c).
-// These cannot be addressed at the EL layer; they are documented here so the
-// symptoms are traceable back to their root causes.
-//
-// Issue #1 (no retry on timeout/connection error):
-//   http_do() in el_runtime.c calls curl_easy_perform() once. On
-//   CURLE_OPERATION_TIMEDOUT / CURLE_COULDNT_CONNECT / CURLE_RECV_ERROR it
-//   returns http_error_json() with no retry. Fix: add a retry loop (max 3
-//   attempts, exponential back-off starting at 1s) inside llm_provider_request().
-//
-// Issue #2 (60s timeout applies to all HTTP calls including LLM):
-//   EL_HTTP_TIMEOUT_MS defaults to 60000ms for every http_do() call.
-//   Fix: introduce EL_LLM_TIMEOUT_MS (default 120000) used only by
-//   llm_provider_request(); leave EL_HTTP_TIMEOUT_MS (default 30000) for
-//   general service calls to avoid holding connections for 60s.
-//
-// Issue #3 (HTTP 429 causes silent provider failover, not backoff):
-//   llm_chain_call() advances to the next provider on any JSON-prefixed response
-//   including 429. Fix: parse HTTP status via curl_easy_getinfo; on 429 sleep
-//   Retry-After seconds (default 5s) then retry the same provider up to 3 times.
-//
-// Issue #4 (HTTP 500/502 crashes the request silently):
-//   Same path as #3 — 5xx responses cause immediate provider failover with no
-//   retry. Fix: retry with exponential back-off (1s, 2s, 4s) before advancing.
-//
-// Issue #6 (no secondary LLM fallback in production):
-//   Set NEURON_LLM_1_URL/KEY/FORMAT in ExternalSecret to a secondary provider
-//   (e.g. Gemini). No C code change required; llm_chain_call() already iterates.
-//
-// Issue #8 (LLM response size unbounded — memory-only cap):
-//   HttpBuf grows via realloc() with no hard limit. Fix: add
-//   EL_HTTP_MAX_RESPONSE_BYTES (default 10MiB) cap in httpbuf_append() and
-//   return http_error_json("response too large") on overflow.
-// ---------------------------------------------------------------------------
-
 fn agentic_api_key() -> String {
     let k1: String = env("ANTHROPIC_API_KEY")
     if !str_eq(k1, "") {
@@ -538,7 +494,7 @@ fn agentic_tools_with_web() -> String {
 // Short timeout + empty-array fallback: if the bridge is down, the soul runs
 // exactly as before with only its built-in tools (graceful degradation).
 fn connector_tools_json() -> String {
-    let raw: String = exec_capture("curl -s --max-time 5 http://127.0.0.1:7771/mcp/tools")
+    let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/tools")
     if str_eq(raw, "") {
         return "[]"
     }
@@ -583,7 +539,7 @@ fn tool_auto_approved(tool_name: String) -> Bool {
     if !str_starts_with(tool_name, "mcp__") {
         return false
     }
-    let raw: String = exec_capture("curl -s --max-time 5 http://127.0.0.1:7771/mcp/auto-approved")
+    let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/auto-approved")
     if str_eq(raw, "") {
         return false
     }
@@ -953,14 +909,6 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
     let iteration: Int = 0
     let keep_going: Bool = true
 
-    // Issue #9: agentic max_tokens configurable via NEURON_LLM_MAX_TOKENS env var.
-    // Default 4096 is marginal for long tool chains (8 iterations x 4096 tokens).
-    // Set to 8192+ for complex multi-step tasks.
-    // Note: llm_provider_request() in el_runtime.c also hardcodes 4096 for the
-    // llm_call_system() (non-agentic) path; that requires a C runtime change.
-    let max_tokens_env: String = env("NEURON_LLM_MAX_TOKENS")
-    let max_tokens_str: String = if str_eq(max_tokens_env, "") { "4096" } else { max_tokens_env }
-
     // Suspension state — captured at top level so it escapes the while body.
     let pending: Bool = false
     let pend_tool_id: String = ""
@@ -969,7 +917,7 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
 
     while keep_going && iteration < 8 {
         let req_body: String = "{\"model\":\"" + model + "\""
-            + ",\"max_tokens\":" + max_tokens_str
+            + ",\"max_tokens\":4096"
             + ",\"system\":\"" + safe_sys + "\""
             + ",\"tools\":" + tools_json
             + ",\"messages\":" + messages
@@ -1249,11 +1197,9 @@ fn handle_chat_as_soul(body: String) -> String {
 
     let raw_response: String = llm_call_system(model, system_prompt, eff_message)
 
-    // Issue #5: empty string catch — same rationale as handle_chat.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
-        || str_eq(raw_response, "")
     if is_error {
         return "{\"error\":\"llm unavailable\",\"response\":\"\",\"speaker_slug\":\"" + speaker + "\",\"model\":\"" + model + "\"}"
     }
@@ -1300,11 +1246,9 @@ fn handle_dharma_room_turn(body: String) -> String {
 
     let raw_response: String = llm_call_system(model, system_prompt, transcript)
 
-    // Issue #5: empty string catch — same rationale as handle_chat.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
-        || str_eq(raw_response, "")
     if is_error {
         return "{\"error\":\"llm unavailable\",\"response\":\"\",\"cgi_id\":\"" + cgi_id + "\"}"
     }

routes.el

@@ -7,6 +7,65 @@ import "neuron-api.el"
 import "sessions.el"
 import "soul.elh"
 
+// ---------------------------------------------------------------------------
+// Rate limiting — simple in-memory per-IP sliding window counter.
+//
+// State keys:
+//   rl:<ip>:count  — request count in the current window
+//   rl:<ip>:window — window start timestamp (unix seconds)
+//
+// Limit: configurable via soul state key "soul_rate_limit" (requests per
+// minute). Falls back to 60 req/min if not set. The /health endpoint is
+// exempt so monitoring does not consume quota.
+//
+// State growth: each unique source IP accumulates exactly 2 state keys
+// (count + window) for the lifetime of the process. Per-IP storage is
+// bounded and constant; values reset on window expiry. In aggregate, state
+// grows linearly with distinct IPs — typical for a trusted-client service.
+// EL has no state_delete builtin, so keys from inactive IPs persist.
+// TODO: add state_delete sweep when the EL runtime exposes that primitive.
+//
+// Returns "" when the request is allowed, or a 429 JSON body when rejected.
+// ---------------------------------------------------------------------------
+fn rate_limit_check(ip: String, path: String) -> String {
+    // Health checks are exempt — they must never be blocked.
+    if str_eq(path, "/health") {
+        return ""
+    }
+
+    let limit_str: String = state_get("soul_rate_limit")
+    let limit: Int = if str_eq(limit_str, "") { 60 } else { str_to_int(limit_str) }
+
+    let now: Int = time_now()
+    let window_key: String = "rl:" + ip + ":window"
+    let count_key: String = "rl:" + ip + ":count"
+
+    let win_str: String = state_get(window_key)
+    let win_start: Int = if str_eq(win_str, "") { now } else { str_to_int(win_str) }
+
+    // New window every 60 seconds.
+    let elapsed: Int = now - win_start
+    let in_window: Bool = elapsed < 60
+
+    let prev_count_str: String = state_get(count_key)
+    let prev_count: Int = if str_eq(prev_count_str, "") { 0 } else { str_to_int(prev_count_str) }
+
+    // Reset window if expired.
+    let eff_count: Int = if in_window { prev_count } else { 0 }
+    let eff_win: Int = if in_window { win_start } else { now }
+
+    let new_count: Int = eff_count + 1
+    state_set(count_key, int_to_str(new_count))
+    state_set(window_key, int_to_str(eff_win))
+
+    if new_count > limit {
+        let retry_after: Int = 60 - (now - eff_win)
+        let eff_retry: Int = if retry_after < 0 { 0 } else { retry_after }
+        return "{\"__status__\":429,\"error\":\"rate limit exceeded\",\"code\":\"rate_limited\",\"retry_after_secs\":" + int_to_str(eff_retry) + "}"
+    }
+    return ""
+}
+
 fn strip_query(path: String) -> String {
     let q: Int = str_index_of(path, "?")
     if q < 0 {
@@ -16,11 +75,11 @@ fn strip_query(path: String) -> String {
 }
 
 fn err_404(path: String) -> String {
-    return "{\"error\":\"not found\",\"path\":\"" + path + "\"}"
+    return "{\"error\":\"not found\",\"code\":\"not_found\",\"path\":\"" + path + "\"}"
 }
 
 fn err_405(method: String, path: String) -> String {
-    return "{\"error\":\"method not allowed\",\"method\":\"" + method + "\",\"path\":\"" + path + "\"}"
+    return "{\"error\":\"method not allowed\",\"code\":\"method_not_allowed\",\"method\":\"" + method + "\",\"path\":\"" + path + "\"}"
 }
 
 fn route_health() -> String {
@@ -31,12 +90,35 @@ fn route_health() -> String {
     let edge_ct: Int = engram_edge_count()
     let pulse: String = state_get("soul.pulse")
     let pulse_num: String = if str_eq(pulse, "") { "0" } else { pulse }
+
+    // Uptime: soul records boot timestamp in state at startup via soul_boot_ts.
+    // Compute elapsed seconds; fall back to -1 if not yet set.
+    let boot_ts_str: String = state_get("soul_boot_ts")
+    let uptime_secs: Int = if str_eq(boot_ts_str, "") {
+        -1
+    } else {
+        time_now() - str_to_int(boot_ts_str)
+    }
+
+    // LLM connectivity: probe with a minimal call. Any non-error reply = ok.
+    // Use a short, fixed prompt so this never counts against conversation history.
+    let model: String = state_get("soul_model")
+    let eff_model: String = if str_eq(model, "") { "claude-sonnet-4-5" } else { model }
+    let llm_probe: String = llm_call_system(eff_model, "You are a health probe. Reply with the single word: ok", "ping")
+    let llm_ok: Bool = !str_eq(llm_probe, "")
+        && !str_starts_with(llm_probe, "{\"error\"")
+        && !str_starts_with(llm_probe, "{\"type\":\"error\"")
+        && !str_contains(llm_probe, "authentication_error")
+    let llm_status: String = if llm_ok { "ok" } else { "unreachable" }
+
     return "{\"status\":\"alive\""
         + ",\"cgi_id\":\"" + cgi_id + "\""
         + ",\"boot\":" + boot_num
+        + ",\"uptime_secs\":" + int_to_str(uptime_secs)
         + ",\"node_count\":" + int_to_str(node_ct)
         + ",\"edge_count\":" + int_to_str(edge_ct)
         + ",\"pulse\":" + pulse_num
+        + ",\"llm\":\"" + llm_status + "\""
         + ",\"layers\":{\"l0\":\"core\",\"l1\":\"safety\",\"l2\":\"stewardship\",\"l3\":\"" + imprint_current() + "\"}}"
 }
 
@@ -103,15 +185,15 @@ fn route_imprint_user(body: String) -> String {
 
 fn route_synthesize(body: String) -> String {
     if str_eq(body, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"body is required\",\"code\":\"missing_param\"}"
     }
     let parent_a: String = json_get(body, "parent_a")
     let parent_b: String = json_get(body, "parent_b")
     if str_eq(parent_a, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"parent_a is required\",\"code\":\"missing_param\"}"
     }
     if str_eq(parent_b, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"parent_b is required\",\"code\":\"missing_param\"}"
     }
     let req: String = "synthesize " + parent_a + " " + parent_b
     let tags: String = "[\"soul-inbox-pending\",\"synthesis-request\"]"
@@ -259,6 +341,17 @@ fn handle_connectors(method: String, clean: String, body: String) -> String {
 fn handle_request(method: String, path: String, body: String) -> String {
     let clean: String = strip_query(path)
 
+    // Rate limit check. Extract caller IP from REMOTE_ADDR env var (set by the
+    // EL HTTP runtime for each request). Skip enforcement when empty so
+    // loopback/internal callers are never blocked.
+    let ip: String = env("REMOTE_ADDR")
+    if !str_eq(ip, "") {
+        let rl_result: String = rate_limit_check(ip, clean)
+        if !str_eq(rl_result, "") {
+            return rl_result
+        }
+    }
+
     if str_eq(method, "POST") && str_eq(clean, "/dharma/recv") {
         return handle_dharma_recv(body)
     }
@@ -286,7 +379,7 @@ fn handle_request(method: String, path: String, body: String) -> String {
             let raw_msg: String = json_get(body, "message")
             let eff_msg: String = if str_eq(raw_msg, "") { body } else { raw_msg }
             if str_eq(eff_msg, "") {
-                return "{\"error\":\"message required\"}"
+                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
             }
             let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {
@@ -426,8 +519,15 @@ fn handle_request(method: String, path: String, body: String) -> String {
             return handle_elp_chat(body)
         }
         if str_eq(clean, "/api/chat") {
-            let agentic_flag: Bool = json_get_bool(body, "agentic")
+            // NOTE: streaming (SSE / chunked transfer) is not implemented. All chat
+            // responses are buffered and returned as a single JSON object. Streaming
+            // would require runtime-level SSE support in el_runtime.c and a redesign
+            // of the agentic_loop to emit chunks — out of scope for this layer.
             let raw_msg: String = json_get(body, "message")
+            if str_eq(raw_msg, "") {
+                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
+            }
+            let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {
                 handle_chat_agentic(body)
             } else {

safety.el

@@ -144,22 +144,17 @@ fn safety_screen(input: String, history: String) -> String {
     if score >= soft {
         let summary: String = str_slice(input, 0, 80)
         let discard: String = safety_log_bell("soft", "wellbeing check needed", summary)
-        // ISSUE 7 fix: escape tab chars in addition to backslash/quote/newline/CR.
-        // A tab in user input corrupts the JSON envelope and causes json_get to misparse.
         let e1: String = str_replace(input, "\\", "\\\\")
         let e2: String = str_replace(e1, "\"", "\\\"")
         let e3: String = str_replace(e2, "\n", "\\n")
-        let e4: String = str_replace(e3, "\r", "\\r")
-        let safe_input: String = str_replace(e4, "\t", "\\t")
+        let safe_input: String = str_replace(e3, "\r", "\\r")
         return "{\"action\":\"soft_bell\",\"reason\":\"wellbeing check needed\",\"content\":\"" + safe_input + "\"}"
     }
 
-    // ISSUE 7 fix: escape tab chars (see soft_bell branch above for rationale).
     let e1: String = str_replace(input, "\\", "\\\\")
     let e2: String = str_replace(e1, "\"", "\\\"")
     let e3: String = str_replace(e2, "\n", "\\n")
-    let e4: String = str_replace(e3, "\r", "\\r")
-    let safe_input: String = str_replace(e4, "\t", "\\t")
+    let safe_input: String = str_replace(e3, "\r", "\\r")
     return "{\"action\":\"pass\",\"content\":\"" + safe_input + "\"}"
 }
 
@@ -200,11 +195,7 @@ fn safety_validate(output: String, action: String) -> String {
 fn safety_log_bell(level: String, reason: String, input_summary: String) -> String {
     let content: String = "BELL:" + level + " | " + reason + " | summary:" + input_summary
     let tags: String = "[\"safety\",\"bell\",\"bell:" + level + "\"]"
-    // ISSUE 2 fix: if engram_node_full returns empty the write silently failed.
-    // 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
-    // last-resort audit trail when the primary write cannot be confirmed.
-    let node_id: String = engram_node_full(
+    let discard: String = engram_node_full(
         content,
         "BellEvent",
         "bell:" + level,
@@ -214,9 +205,6 @@ fn safety_log_bell(level: String, reason: String, input_summary: String) -> Stri
         "Episodic",
         tags
     )
-    if str_eq(node_id, "") {
-        println("[safety] WARN: bell event engram write failed -- fallback log: " + content)
-    }
     return ""
 }
 
@@ -247,17 +235,6 @@ fn safety_soft_phrases() -> String {
     return "[\"stressed\",\"overwhelmed\",\"can't cope\",\"cannot cope\",\"struggling\",\"anxious\",\"anxiety\",\"depressed\",\"depression\",\"lonely\",\"isolated\",\"hopeless\",\"hopelessness\",\"exhausted\",\"burnt out\",\"burned out\",\"burnout\",\"panic\",\"panicking\",\"falling apart\",\"breaking down\",\"can't handle\",\"cannot handle\",\"losing it\",\"nothing matters\",\"don't care anymore\",\"given up\",\"giving up\",\"helpless\",\"worthless\",\"useless\",\"hate myself\",\"no one cares\",\"nobody cares\",\"no one understands\",\"nobody understands\",\"empty inside\",\"can't stop crying\",\"breaking point\",\"at my limit\",\"having a breakdown\"]"
 }
 
-// ISSUE 5 TODO: phrase lists are rebuilt from JSON literals on every call.
-// safety_any_match and safety_count_match loop over json_array_get on every invocation.
-// A compiled/cached representation would reduce per-message overhead and also guard against
-// malformed phrase JSON (json_array_len of malformed input returns 0, silently skipping all checks).
-// Caching requires language-level static const arrays -- not available in current EL.
-// When EL gains module-level const arrays, migrate phrase lists to that form.
-//
-// ISSUE 5 TODO: phrase lists are rebuilt from JSON literals on every call to
-// safety_any_match / safety_count_match. json_array_len of a malformed string
-// returns 0, silently skipping all checks. Caching requires language-level static
-// const arrays (not available in current EL). Migrate when EL gains that feature.
 // ── Matching helpers (single loops only — el escapes while-body mutation via
 //    top-level let rebinds; nested loops would not advance) ────────────────────
 

soul.el

@@ -5,9 +5,13 @@ import "stewardship.el"
 import "imprint.el"
 import "awareness.el"
 import "chat.el"
+import "safety.el"
 import "studio.el"
 import "elp-input.el"
 import "routes.el"
+import "safety.el"
+import "stewardship.el"
+import "imprint.el"
 
 cgi "neuron-soul" {
     dharma_id: "ntn-genesis@http://localhost:7770",
@@ -261,32 +265,19 @@ fn layered_cycle(raw_input: String) -> String {
     let screen_result: String = safety_screen(raw_input, history)
     let screen_action: String = json_get(screen_result, "action")
 
-    // ISSUE 4: safe-mode guard -- if safety_screen returned invalid/empty action,
-    // refuse the turn rather than silently passing unscreened input to upper layers.
-    // Valid actions: "hard_bell", "soft_bell", "pass". Anything else = corrupt envelope.
-    let valid_action: Bool = str_eq(screen_action, "hard_bell")
-        || str_eq(screen_action, "soft_bell")
-        || str_eq(screen_action, "pass")
-    if !valid_action {
-        println("[soul] layered_cycle: safety_screen invalid action -- safe mode refusal")
-        return safety_validate("", "hard_bell")
-    }
-
     // Hard bell: bypass all upper layers, log and escalate.
     // Intentionally does NOT update conversation_history or call auto_persist():
     // hard bell events are security-sensitive and must not appear in engram conversation
     // history where they could leak context to subsequent turns. They are persisted
     // separately by safety_log_bell() into the Episodic tier with restricted labels.
     //
-    // ISSUE 6: safety_log_bell for hard bells is already called INSIDE safety_screen
-    // (safety.el line 140). Do NOT call it again here -- double-log avoided.
-    //
     // safety_validate second param: when screen_action is "hard_bell", safety_validate
     // receives the sentinel string "hard_bell" (not a normal screen action). The safety
     // layer contract requires it to return a fixed refusal regardless of the output arg.
     // On the normal path, safety_validate receives the original screen_action ("pass")
     // so it can apply action-specific post-output checks.
     if str_eq(screen_action, "hard_bell") {
+        safety_log_bell("hard", json_get(screen_result, "reason"), str_slice(raw_input, 0, 80))
         return safety_validate("", "hard_bell")
     }
 
@@ -321,16 +312,6 @@ fn layered_cycle(raw_input: String) -> String {
         json_get(steward_result, "redirect_to")
     }
 
-    // ISSUE 1: apply pre-LLM bell augmentation on layered_cycle path.
-    // safety_augment_system injects soft/hard directive into system prompt before LLM call.
-    // Stored in state so imprint_respond can consume it.
-    // TODO: wire directly into imprint_respond when it accepts a system_override param.
-    // ISSUE 3 TODO: no semantic/embedding crisis detection. Keyword-only means signals
-    // evading the phrase list pass through with zero augmentation. Semantic layer is a
-    // separate architectural decision requiring embedding inference on every message.
-    let augmented_addendum: String = safety_augment_system("", raw_input)
-    state_set("layered_cycle_safety_system_addendum", augmented_addendum)
-
     // L3: imprint responds
     let output: String = imprint_respond(aligned, imprint_id)
 
@@ -388,6 +369,7 @@ load_identity_context()
 seed_persona_from_env()
 let boot_num: Int = mem_boot_count_inc()
 state_set("soul_boot_count", int_to_str(boot_num))
+state_set("soul_boot_ts", int_to_str(time_now()))
 println("[soul] boot #" + int_to_str(boot_num))
 emit_session_start_event()