#!/bin/sh
# Last-resort source: queries a local LLM inference server (Ollama or
# LM Studio, both common on dev machines) for a fix, only when nothing
# cheaper matched. Silent no-op if no local server is reachable -- this
# never touches the network, never calls a paid API, and costs nothing
# when you don't have a local model running.
#
# Numbered 70, after every deterministic/heuristic source (10-50) and
# before the team-shared source (90): cheap, verified candidates should
# always win first. fx.sh's FX_AUTO picks the *first* candidate in
# source order, so this only gets auto-selected when it's the only
# opinion offered at all -- still review it, this is a guess, not a
# fact. Every other default source is either a cached human decision or
# a deterministic rule; this is the one source capable of confidently
# suggesting something wrong.
#
# Needs python3 (uses urllib, no extra dependency beyond stdlib) --
# silently no-ops without it rather than ship a fragile hand-rolled
# JSON encoder in shell.

cmd="$1"
[ -n "$cmd" ] || exit 0
command -v python3 >/dev/null 2>&1 || exit 0

OLLAMA_URL="${FX_LLM_OLLAMA_URL:-http://127.0.0.1:11434}"
LMSTUDIO_URL="${FX_LLM_LMSTUDIO_URL:-http://127.0.0.1:1234}"

python3 - "$cmd" "$FX_OUTPUT" "$OLLAMA_URL" "$LMSTUDIO_URL" <<'PYEOF'
import sys, json, urllib.request, urllib.error

cmd, output, ollama_url, lmstudio_url = sys.argv[1:5]

PROMPT = f"""You are suggesting a fix for a failed shell command, to be taught to a self-healing shell function called f().
Rules:
- f() will eval your fix ONCE as a precondition, then re-run the ORIGINAL command verbatim. Your fix never replaces the command; it only sets up state so the original command then succeeds.
- If the fix should generalize beyond this one invocation, define a shell function with the same name as the failing program, wrapping the real binary via `command <prog> "$@"`, and only special-case the failure inside it.
- Respond with EXACTLY ONE LINE of POSIX shell and nothing else: no explanation, no markdown, no code fences, no commentary.

Failing command: {cmd}

Its output:
{output}
"""

def http_json(url, payload, timeout):
    req = urllib.request.Request(
        url, data=json.dumps(payload).encode(),
        headers={"Content-Type": "application/json"}, method="POST",
    )
    with urllib.request.urlopen(req, timeout=timeout) as r:
        return json.loads(r.read().decode())

def http_get_json(url, timeout):
    with urllib.request.urlopen(url, timeout=timeout) as r:
        return json.loads(r.read().decode())

def try_ollama():
    tags = http_get_json(ollama_url.rstrip("/") + "/api/tags", 2)
    models = tags.get("models") or []
    if not models:
        return None
    model = models[0].get("name")
    if not model:
        return None
    resp = http_json(
        ollama_url.rstrip("/") + "/api/generate",
        {"model": model, "prompt": PROMPT, "stream": False},
        25,
    )
    return (resp.get("response") or "").strip()

def try_lmstudio():
    models = http_get_json(lmstudio_url.rstrip("/") + "/v1/models", 2)
    data = models.get("data") or []
    if not data:
        return None
    model = data[0].get("id")
    if not model:
        return None
    resp = http_json(
        lmstudio_url.rstrip("/") + "/v1/chat/completions",
        {
            "model": model,
            "messages": [{"role": "user", "content": PROMPT}],
            "temperature": 0,
        },
        25,
    )
    choices = resp.get("choices") or []
    if not choices:
        return None
    return (choices[0].get("message", {}).get("content") or "").strip()

for attempt in (try_ollama, try_lmstudio):
    try:
        result = attempt()
    except (urllib.error.URLError, TimeoutError, OSError, ValueError, KeyError):
        result = None
    if result:
        # Enforce the one-line contract even if the model ignores instructions.
        first_line = result.splitlines()[0].strip()
        first_line = first_line.strip("`")
        if first_line:
            print(first_line)
        break
PYEOF