|
|
|
@@ -1202,86 +1202,6 @@ fn agentic_api_key() -> String {
|
|
|
|
|
return env("NEURON_LLM_0_KEY")
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// ── OpenAI-compatible providers (Ollama / OpenAI / Grok / Gemini) ──────────────────────────────
|
|
|
|
|
// The brain speaks Anthropic's Messages format by default. When the active provider uses the
|
|
|
|
|
// OpenAI-compatible wire format (NEURON_LLM_0_FORMAT=openai) with a configured base URL
|
|
|
|
|
// (NEURON_LLM_0_URL, e.g. http://localhost:11434/v1 for local Ollama), basic chat turns are served
|
|
|
|
|
// here instead of the Anthropic agentic loop.
|
|
|
|
|
// v1 SCOPE: plain chat completion only — NO tools / agentic loop yet (that is a follow-up port).
|
|
|
|
|
// This block is ADDITIVE: the Anthropic path is untouched and stays the default.
|
|
|
|
|
|
|
|
|
|
fn llm_base_url() -> String {
|
|
|
|
|
return env("NEURON_LLM_0_URL")
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn llm_wire_format() -> String {
|
|
|
|
|
let f: String = env("NEURON_LLM_0_FORMAT")
|
|
|
|
|
if str_eq(f, "") {
|
|
|
|
|
return "anthropic"
|
|
|
|
|
}
|
|
|
|
|
return f
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Escape a decoded string so it can be embedded back into a JSON string literal.
|
|
|
|
|
fn json_escape(s: String) -> String {
|
|
|
|
|
let a: String = str_replace(s, "\\", "\\\\")
|
|
|
|
|
let b: String = str_replace(a, "\"", "\\\"")
|
|
|
|
|
let c: String = str_replace(b, "\n", "\\n")
|
|
|
|
|
let d: String = str_replace(c, "\r", "\\r")
|
|
|
|
|
return d
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Basic (non-agentic) chat completion against an OpenAI-compatible endpoint.
|
|
|
|
|
// [safe_sys] is already JSON-escaped; [messages_json] is the same JSON array the Anthropic path
|
|
|
|
|
// builds (e.g. [{"role":"user","content":"..."}]). Returns the soul's standard {"reply":"..."}.
|
|
|
|
|
fn openai_chat_complete(model: String, base_url: String, api_key: String, safe_sys: String, messages_json: String) -> String {
|
|
|
|
|
// Prepend the system prompt as an OpenAI "system" message, then the existing turn array.
|
|
|
|
|
let inner: String = if json_array_len(messages_json) > 0 {
|
|
|
|
|
str_slice(messages_json, 1, str_len(messages_json) - 1)
|
|
|
|
|
} else {
|
|
|
|
|
""
|
|
|
|
|
}
|
|
|
|
|
let msgs: String = if str_eq(inner, "") {
|
|
|
|
|
"[{\"role\":\"system\",\"content\":\"" + safe_sys + "\"}]"
|
|
|
|
|
} else {
|
|
|
|
|
"[{\"role\":\"system\",\"content\":\"" + safe_sys + "\"}," + inner + "]"
|
|
|
|
|
}
|
|
|
|
|
let req_body: String = "{\"model\":\"" + model + "\""
|
|
|
|
|
+ ",\"max_tokens\":4096"
|
|
|
|
|
+ ",\"messages\":" + msgs
|
|
|
|
|
+ "}"
|
|
|
|
|
|
|
|
|
|
let h: Map = {}
|
|
|
|
|
map_set(h, "content-type", "application/json")
|
|
|
|
|
// Ollama needs no key; OpenAI / Grok / Gemini use a Bearer token.
|
|
|
|
|
if !str_eq(api_key, "") {
|
|
|
|
|
map_set(h, "Authorization", "Bearer " + api_key)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
let url: String = base_url + "/chat/completions"
|
|
|
|
|
let raw_resp: String = http_post_with_headers(url, req_body, h)
|
|
|
|
|
|
|
|
|
|
let is_error: Bool = str_starts_with(raw_resp, "{\"error\"") || str_contains(raw_resp, "\"error\":")
|
|
|
|
|
if is_error {
|
|
|
|
|
return "{\"error\":\"llm unavailable\",\"reply\":\"\"}"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Parse OpenAI response shape: choices[0].message.content
|
|
|
|
|
let choices: String = json_get_raw(raw_resp, "choices")
|
|
|
|
|
let eff_choices: String = if str_eq(choices, "") {
|
|
|
|
|
"[]"
|
|
|
|
|
} else {
|
|
|
|
|
choices
|
|
|
|
|
}
|
|
|
|
|
if json_array_len(eff_choices) < 1 {
|
|
|
|
|
return "{\"error\":\"empty response\",\"reply\":\"\"}"
|
|
|
|
|
}
|
|
|
|
|
let first: String = json_array_get(eff_choices, 0)
|
|
|
|
|
let message: String = json_get_raw(first, "message")
|
|
|
|
|
let content: String = json_get(message, "content")
|
|
|
|
|
return "{\"reply\":\"" + json_escape(content) + "\",\"tools_used\":[]}"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn agentic_tools_literal() -> String {
|
|
|
|
|
return "[" +
|
|
|
|
|
"{\"name\":\"read_file\",\"description\":\"Read contents of a file from disk.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\",\"description\":\"Absolute file path\"}},\"required\":[\"path\"]}}," +
|
|
|
|
@@ -1768,12 +1688,25 @@ fn handle_chat_agentic(body: String) -> String {
|
|
|
|
|
let safe_msg: String = json_safe(message)
|
|
|
|
|
let safe_sys: String = json_safe(system)
|
|
|
|
|
|
|
|
|
|
// Vision in the agentic brain (2026-06-27): when the client attaches an image
|
|
|
|
|
// (base64 in body "image", mime in "image_media_type"), send it as a real Anthropic
|
|
|
|
|
// image content block on THIS user turn — so the model sees raw pixels WITH memory,
|
|
|
|
|
// history, and tools (parity with the CLI). img_b64 == "" => byte-identical to before.
|
|
|
|
|
let img_b64: String = json_get(body, "image")
|
|
|
|
|
let img_mt_raw: String = json_get(body, "image_media_type")
|
|
|
|
|
let img_mt: String = if str_eq(img_mt_raw, "") { "image/png" } else { img_mt_raw }
|
|
|
|
|
let cur_user_content: String = if str_eq(img_b64, "") {
|
|
|
|
|
"\"" + safe_msg + "\""
|
|
|
|
|
} else {
|
|
|
|
|
"[{\"type\":\"text\",\"text\":\"" + safe_msg + "\"},{\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":\"" + img_mt + "\",\"data\":\"" + img_b64 + "\"}}]"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Seed the messages array with recent history if available, so the LLM sees the thread.
|
|
|
|
|
let prior_messages: String = if agentic_hist_len > 0 {
|
|
|
|
|
let inner: String = str_slice(agentic_hist, 1, str_len(agentic_hist) - 1)
|
|
|
|
|
"[" + inner + ",{\"role\":\"user\",\"content\":\"" + safe_msg + "\"}]"
|
|
|
|
|
"[" + inner + ",{\"role\":\"user\",\"content\":" + cur_user_content + "}]"
|
|
|
|
|
} else {
|
|
|
|
|
"[{\"role\":\"user\",\"content\":\"" + safe_msg + "\"}]"
|
|
|
|
|
"[{\"role\":\"user\",\"content\":" + cur_user_content + "}]"
|
|
|
|
|
}
|
|
|
|
|
let messages: String = prior_messages
|
|
|
|
|
let api_url: String = "https://api.anthropic.com/v1/messages"
|
|
|
|
@@ -1784,14 +1717,7 @@ fn handle_chat_agentic(body: String) -> String {
|
|
|
|
|
|
|
|
|
|
// Use caller-supplied session_id if provided, otherwise generate a bridge id.
|
|
|
|
|
let session_id: String = if str_eq(req_session, "") { next_bridge_id() } else { req_session }
|
|
|
|
|
// Provider fork: OpenAI-compatible providers (Ollama/OpenAI/Grok/Gemini) take the plain-completion
|
|
|
|
|
// path (v1, no tools); everything else stays on the Anthropic agentic loop (the default).
|
|
|
|
|
let use_openai: Bool = !str_eq(llm_base_url(), "") && str_eq(llm_wire_format(), "openai")
|
|
|
|
|
let result: String = if use_openai {
|
|
|
|
|
openai_chat_complete(model, llm_base_url(), agentic_api_key(), safe_sys, messages)
|
|
|
|
|
} else {
|
|
|
|
|
agentic_loop(session_id, model, safe_sys, tools_json, messages, h, "")
|
|
|
|
|
}
|
|
|
|
|
let result: String = agentic_loop(session_id, model, safe_sys, tools_json, messages, h, "")
|
|
|
|
|
|
|
|
|
|
// 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.
|
|
|
|
|
will.anderson
Tim Lingo