gramps/jarvisChat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: resolve all critical runtime errors and bugs from audit

Browse Source 
- Add COMPLETIONS_API_KEY to config.py (env var + auto-generated fallback)
- Fix perplexity auto-search: upstream sends logprobs=true, parse_llama_stream_chunk
  extracts per-token logprobs, all_logprobs populated during streaming
- Fix all /api/models endpoints to target LLAMA_SERVER_BASE (port 8081) not OLLAMA_BASE
- Fix RAG embedding endpoint URL from port 11434 (Ollama) to 8081 (llama-server)
- Correct misleading error messages: 'inference server' not 'Ollama'
- Remove raw_results leak from SSE event stream in /api/search
- Fix weather query extractor: pattern-match instead of unconditional suffix append
- Escape FTS5 operator keywords (AND/OR/NOT/NEAR) in memory search
- Move auth.py BODY_LIMIT_DEFAULT_BYTES imports to module level
- Change RAG injection log level from warning to info
- Fix all 8 test files after modular refactor (rewire imports from correct modules)
- Update AGENTS.md and README.md to reflect v1.8.0 changes
This commit is contained in:
gramps
2026-06-27 15:12:18 -07:00
parent 41a8708c0d
commit cc1efa7a21
20 changed files with 457 additions and 896 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
routers/chat.py
View File

@@ -26,7 +26,7 @@ def parse_llama_stream_chunk(line: str) -> tuple:
if line.startswith("data: "):
line = line[6:]
if line.strip() == "[DONE]":
return None, True, {}
return None, True, {}, []
try:
chunk = json.loads(line)
choices = chunk.get("choices", [])
@@ -35,10 +35,17 @@ def parse_llama_stream_chunk(line: str) -> tuple:
token = delta.get("content")
finish = choices[0].get("finish_reason")
stats = {}
logprobs_list = []
logprobs_info = choices[0].get("logprobs")
if logprobs_info:
content_logprobs = logprobs_info.get("content", [])
for entry in content_logprobs:
if "logprob" in entry:
logprobs_list.append({"logprob": entry["logprob"]})
if finish == "stop":
usage = chunk.get("usage", {})
stats["tokens_per_sec"] = usage.get("tokens_per_second", 0.0)
return token, finish == "stop", stats
return token, finish == "stop", stats, logprobs_list
if "message" in chunk and "content" in chunk["message"]:
token = chunk["message"]["content"]
done = chunk.get("done", False)
@@ -47,10 +54,10 @@ def parse_llama_stream_chunk(line: str) -> tuple:
eval_count = chunk.get("eval_count", 0)
eval_duration = chunk.get("eval_duration", 0)
stats["tokens_per_sec"] = (eval_count / (eval_duration / 1e9)) if eval_duration > 0 else 0
return token, done, stats
return token, done, stats, []
except json.JSONDecodeError:
pass
return None, False, {}
return None, False, {}, []
@router.post("/api/chat")
@@ -97,7 +104,7 @@ async def chat(request: Request):
for row in history_rows:
messages.append({"role": row["role"], "content": row["content"]})
ollama_payload = {"model": model, "messages": messages, "stream": True}
upstream_payload = {"model": model, "messages": messages, "stream": True, "logprobs": True}
async def stream_response():
full_response = []
@@ -111,12 +118,14 @@ async def chat(request: Request):
try:
async with client.stream(
"POST", f"{LLAMA_SERVER_BASE}/v1/chat/completions",
json=ollama_payload,
json=upstream_payload,
timeout=httpx.Timeout(300.0, connect=10.0),
) as resp:
async for line in resp.aiter_lines():
if line.strip():
token, done, stats = parse_llama_stream_chunk(line)
token, done, stats, chunk_logprobs = parse_llama_stream_chunk(line)
if chunk_logprobs:
all_logprobs.extend(chunk_logprobs)
if token:
full_response.append(token)
yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
@@ -153,7 +162,7 @@ async def chat(request: Request):
) as resp2:
async for line in resp2.aiter_lines():
if line.strip():
token2, done2, _ = parse_llama_stream_chunk(line)
token2, done2, _, _ = parse_llama_stream_chunk(line)
if token2:
augmented_response.append(token2)
if done2:
@@ -194,9 +203,9 @@ async def chat(request: Request):
except httpx.RemoteProtocolError:
pass
except httpx.ConnectError:
yield f"data: {json.dumps({'error': 'Cannot connect to Ollama. Is it running?'})}\n\n"
yield f"data: {json.dumps({'error': 'Cannot connect to inference server. Is it running?'})}\n\n"
except Exception as e:
incident_key = log_incident("chat_stream", message="Ollama stream failure during chat response",
incident_key = log_incident("chat_stream", message="Inference stream failure during chat response",
request=request, exc=e)
yield f"data: {json.dumps({'error': 'Chat response generation failed before completion. Use the incident key for support lookup.', 'error_key': incident_key})}\n\n"

4
routers/completions.py
View File

@@ -178,7 +178,7 @@ async def _stream_chat(payload: dict, model: str, conv_id: str, request: Request
async for line in resp.aiter_lines():
if not line.strip():
continue
token, done, _ = parse_llama_stream_chunk(line)
token, done, _, _ = parse_llama_stream_chunk(line)
if token:
full_response.append(token)
yield _build_openai_chunk(token, model, conv_id)
@@ -222,7 +222,7 @@ async def _blocking_chat(payload: dict, model: str, conv_id: str, request: Reque
async for line in resp.aiter_lines():
if not line.strip():
continue
token, done, _ = parse_llama_stream_chunk(line)
token, done, _, _ = parse_llama_stream_chunk(line)
if token:
full_response.append(token)
if done:

15
routers/models.py
View File

@@ -8,7 +8,7 @@ import httpx
import psutil
from fastapi import APIRouter, HTTPException, Request
from config import OLLAMA_BASE
from config import LLAMA_SERVER_BASE
from gpu import get_gpu_stats
from security import read_json_body, BODY_LIMIT_DEFAULT_BYTES
@@ -20,34 +20,33 @@ router = APIRouter()
async def list_models():
async with httpx.AsyncClient() as client:
try:
resp = await client.get(f"{OLLAMA_BASE}/v1/models", timeout=10)
resp = await client.get(f"{LLAMA_SERVER_BASE}/v1/models", timeout=10)
data = resp.json()
models = [{"name": m["id"], "model": m["id"]} for m in data.get("data", [])]
return {"models": models}
except httpx.ConnectError:
raise HTTPException(status_code=502, detail="Cannot connect to llama-server.")
raise HTTPException(status_code=502, detail="Cannot connect to inference server.")
@router.get("/api/ps")
async def running_models():
async with httpx.AsyncClient() as client:
try:
resp = await client.get(f"{OLLAMA_BASE}/api/ps", timeout=10)
resp = await client.get(f"{LLAMA_SERVER_BASE}/v1/models", timeout=10)
return resp.json()
except httpx.ConnectError:
raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
raise HTTPException(status_code=502, detail="Cannot connect to inference server.")
@router.post("/api/show")
async def show_model(request: Request):
from security import BODY_LIMIT_DEFAULT_BYTES
body = await read_json_body(request, BODY_LIMIT_DEFAULT_BYTES)
async with httpx.AsyncClient() as client:
try:
resp = await client.post(f"{OLLAMA_BASE}/api/show", json=body, timeout=10)
resp = await client.post(f"{LLAMA_SERVER_BASE}/api/show", json=body, timeout=10)
return resp.json()
except httpx.ConnectError:
raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
raise HTTPException(status_code=502, detail="Cannot connect to inference server.")
@router.get("/api/stats")

7
routers/search_route.py
View File

@@ -35,14 +35,14 @@ async def explicit_search(request: Request):
if not conv_id:
conv_id = str(uuid.uuid4())
title = f"🔍 {query[:70]}..." if len(query) > 70 else f"🔍 {query}"
title = query[:70] + "..." if len(query) > 70 else query
db.execute("INSERT INTO conversations (id, title, model, created_at, updated_at) VALUES (?, ?, ?, ?, ?)",
(conv_id, title, model, now, now))
else:
db.execute("UPDATE conversations SET updated_at = ? WHERE id = ?", (now, conv_id))
db.execute("INSERT INTO messages (conversation_id, role, content, created_at) VALUES (?, ?, ?, ?)",
(conv_id, "user", f"🔍 {query}", now))
(conv_id, "user", query, now))
db.commit()
db.close()
@@ -80,7 +80,7 @@ async def explicit_search(request: Request):
) as resp:
async for line in resp.aiter_lines():
if line.strip():
token, done, _ = parse_llama_stream_chunk(line)
token, done, _, _ = parse_llama_stream_chunk(line)
if token:
full_response.append(token)
yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
@@ -102,7 +102,6 @@ async def explicit_search(request: Request):
db2.commit()
db2.close()
yield f"data: {json.dumps({'raw_results': results, 'conversation_id': conv_id})}\n\n"
yield f"data: {json.dumps({'done': True, 'conversation_id': conv_id, 'searched': True})}\n\n"
return StreamingResponse(stream_search(), media_type="text/event-stream")