Migrate to litellm for model compatability

.env.example

@@ -2,10 +2,11 @@
 # Copy to ~/.applypilot/.env and fill in your values.
 
 # LLM Provider (pick one)
-GEMINI_API_KEY=           # Gemini 2.0 Flash (recommended, cheapest)
-# OPENAI_API_KEY=         # OpenAI (GPT-4o-mini)
-# LLM_URL=http://127.0.0.1:8080/v1  # Local LLM (llama.cpp, Ollama)
-# LLM_MODEL=              # Override model name
+GEMINI_API_KEY=                 # Gemini (recommended, cheapest)
+# OPENAI_API_KEY=               # OpenAI
+# ANTHROPIC_API_KEY=            # Anthropic Claude
+# LLM_URL=http://127.0.0.1:8080/v1  # Local LLM (OpenAI-compatible: llama.cpp, Ollama, vLLM)
+# LLM_MODEL=                    # Override model name (provider-specific)
 
 # Auto-Apply (optional)
 CAPSOLVER_API_KEY=        # For CAPTCHA solving during auto-apply

README.md

@@ -43,12 +43,12 @@ applypilot apply --dry-run  # fill forms without submitting
 ## Two Paths
 
 ### Full Pipeline (recommended)
-**Requires:** Python 3.11+, Node.js (for npx), Gemini API key (free), Claude Code CLI, Chrome
+**Requires:** Python 3.11+, Node.js (for npx), an LLM key (Gemini/OpenAI/Claude) or `LLM_URL`, Claude Code CLI, Chrome
 
 Runs all 6 stages, from job discovery to autonomous application submission. This is the full power of ApplyPilot.
 
 ### Discovery + Tailoring Only
-**Requires:** Python 3.11+, Gemini API key (free)
+**Requires:** Python 3.11+, an LLM key (Gemini/OpenAI/Claude) or `LLM_URL`
 
 Runs stages 1-5: discovers jobs, scores them, tailors your resume, generates cover letters. You submit applications manually with the AI-prepared materials.
 
@@ -88,18 +88,25 @@ Each stage is independent. Run them all or pick what you need.
 |-----------|-------------|---------|
 | Python 3.11+ | Everything | Core runtime |
 | Node.js 18+ | Auto-apply | Needed for `npx` to run Playwright MCP server |
-| Gemini API key | Scoring, tailoring, cover letters | Free tier (15 RPM / 1M tokens/day) is enough |
+| LLM credentials or local endpoint | Scoring, tailoring, cover letters | Set one of `GEMINI_API_KEY`, `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `LLM_URL`. Optional: set `LLM_MODEL` (for example `gemini/gemini-3.0-flash`) to override the default model. |
 | Chrome/Chromium | Auto-apply | Auto-detected on most systems |
 | Claude Code CLI | Auto-apply | Install from [claude.ai/code](https://claude.ai/code) |
 
-**Gemini API key is free.** Get one at [aistudio.google.com](https://aistudio.google.com). OpenAI and local models (Ollama/llama.cpp) are also supported.
+**Gemini API key is free.** Get one at [aistudio.google.com](https://aistudio.google.com). OpenAI, Claude, and local models (Ollama/llama.cpp/vLLM) are also supported.
+ApplyPilot uses Gemini through LiteLLM's native Gemini provider path, and Gemini API version routing is owned by LiteLLM.
 
 ### Optional
 
 | Component | What It Does |
 |-----------|-------------|
 | CapSolver API key | Solves CAPTCHAs during auto-apply (hCaptcha, reCAPTCHA, Turnstile, FunCaptcha). Without it, CAPTCHA-blocked applications just fail gracefully |
 
+### Gemini Smoke Check (optional)
+
+```bash
+GEMINI_API_KEY=your_key_here pytest -m smoke -q tests/test_gemini_smoke.py
+```
+
 > **Note:** python-jobspy is installed separately with `--no-deps` because it pins an exact numpy version in its metadata that conflicts with pip's resolver. It works fine with modern numpy at runtime.
 
 ---
@@ -115,7 +122,7 @@ Your personal data in one structured file: contact info, work authorization, com
 Job search queries, target titles, locations, boards. Run multiple searches with different parameters.
 
 ### `.env`
-API keys and runtime config: `GEMINI_API_KEY`, `LLM_MODEL`, `CAPSOLVER_API_KEY` (optional).
+API keys and runtime config: `GEMINI_API_KEY`, `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `LLM_URL`, optional `LLM_MODEL`, optional `LLM_API_KEY`, and `CAPSOLVER_API_KEY`.
 
 ### Package configs (shipped with ApplyPilot)
 - `config/employers.yaml` - Workday employer registry (48 preconfigured)

pyproject.toml

@@ -20,6 +20,7 @@ classifiers = [
 dependencies = [
     "typer>=0.9.0",
     "rich>=13.0",
+    "litellm~=1.63.0",
     "httpx>=0.24",
     "beautifulsoup4>=4.12",
     "playwright>=1.40",

src/applypilot/apply/dashboard.py

@@ -7,7 +7,7 @@
 import logging
 import threading
 import time
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
 

src/applypilot/apply/launcher.py

@@ -25,7 +25,7 @@
 
 from applypilot import config
 from applypilot.database import get_connection
-from applypilot.apply import chrome, dashboard, prompt as prompt_mod
+from applypilot.apply import prompt as prompt_mod
 from applypilot.apply.chrome import (
     launch_chrome, cleanup_worker, kill_all_chrome,
     reset_worker_dir, cleanup_on_exit, _kill_process_tree,
@@ -125,7 +125,7 @@ def acquire_job(target_url: str | None = None, min_score: int = 7,
                 params.extend(blocked_sites)
             url_clauses = ""
             if blocked_patterns:
-                url_clauses = " ".join(f"AND url NOT LIKE ?" for _ in blocked_patterns)
+                url_clauses = " ".join("AND url NOT LIKE ?" for _ in blocked_patterns)
                 params.extend(blocked_patterns)
             row = conn.execute(f"""
                 SELECT url, title, site, application_url, tailored_resume_path,

src/applypilot/cli.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import logging
+import os
 from typing import Optional
 
 import typer
@@ -11,11 +12,37 @@
 
 from applypilot import __version__
 
-logging.basicConfig(
-    level=logging.INFO,
-    format="%(asctime)s - %(levelname)s - %(message)s",
-    datefmt="%H:%M:%S",
-)
+
+def _configure_logging() -> None:
+    """Set consistent logging output for CLI runs."""
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
+        datefmt="%H:%M:%S",
+    )
+
+    # Keep LiteLLM internals quiet by default; warnings/errors still surface.
+    for name in ("LiteLLM", "litellm"):
+        noisy = logging.getLogger(name)
+        noisy.handlers.clear()
+        noisy.setLevel(logging.WARNING)
+        noisy.propagate = True
+
+    # Route verbose tailor/cover loggers to a file instead of the terminal.
+    # Per-attempt warnings and validation details are useful for debugging
+    # but too noisy for normal CLI output.
+    from applypilot.config import LOG_DIR
+    LOG_DIR.mkdir(parents=True, exist_ok=True)
+    _file_fmt = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s", datefmt="%H:%M:%S")
+    for logger_name in ("applypilot.scoring.tailor", "applypilot.scoring.cover_letter"):
+        file_log = logging.getLogger(logger_name)
+        file_log.propagate = False  # suppress terminal output
+        fh = logging.FileHandler(LOG_DIR / f"{logger_name.split('.')[-1]}.log", encoding="utf-8")
+        fh.setFormatter(_file_fmt)
+        file_log.addHandler(fh)
+
+
+_configure_logging()
 
 app = typer.Typer(
     name="applypilot",
@@ -211,7 +238,7 @@ def apply(
             raise typer.Exit(code=1)
 
     if gen:
-        from applypilot.apply.launcher import gen_prompt, BASE_CDP_PORT
+        from applypilot.apply.launcher import gen_prompt
         target = url or ""
         if not target:
             console.print("[red]--gen requires --url to specify which job.[/red]")
@@ -222,7 +249,7 @@ def apply(
             raise typer.Exit(code=1)
         mcp_path = _profile_path.parent / ".mcp-apply-0.json"
         console.print(f"[green]Wrote prompt to:[/green] {prompt_file}")
-        console.print(f"\n[bold]Run manually:[/bold]")
+        console.print("\n[bold]Run manually:[/bold]")
         console.print(
             f"  claude --model {model} -p "
             f"--mcp-config {mcp_path} "
@@ -338,7 +365,7 @@ def doctor() -> None:
     import shutil
     from applypilot.config import (
         load_env, PROFILE_PATH, RESUME_PATH, RESUME_PDF_PATH,
-        SEARCH_CONFIG_PATH, ENV_PATH, get_chrome_path,
+        SEARCH_CONFIG_PATH, get_chrome_path,
     )
 
     load_env()
@@ -379,21 +406,25 @@ def doctor() -> None:
                         "pip install --no-deps python-jobspy && pip install pydantic tls-client requests markdownify regex"))
 
     # --- Tier 2 checks ---
-    import os
-    has_gemini = bool(os.environ.get("GEMINI_API_KEY"))
-    has_openai = bool(os.environ.get("OPENAI_API_KEY"))
-    has_local = bool(os.environ.get("LLM_URL"))
-    if has_gemini:
-        model = os.environ.get("LLM_MODEL", "gemini-2.0-flash")
-        results.append(("LLM API key", ok_mark, f"Gemini ({model})"))
-    elif has_openai:
-        model = os.environ.get("LLM_MODEL", "gpt-4o-mini")
-        results.append(("LLM API key", ok_mark, f"OpenAI ({model})"))
-    elif has_local:
-        results.append(("LLM API key", ok_mark, f"Local: {os.environ.get('LLM_URL')}"))
-    else:
-        results.append(("LLM API key", fail_mark,
-                        "Set GEMINI_API_KEY in ~/.applypilot/.env (run 'applypilot init')"))
+    from applypilot.llm import resolve_llm_config
+
+    try:
+        llm_cfg = resolve_llm_config()
+        if llm_cfg.api_base:
+            results.append(("LLM API key", ok_mark, f"Custom endpoint: {llm_cfg.api_base} ({llm_cfg.model})"))
+        else:
+            label = {
+                "gemini": "Gemini",
+                "openai": "OpenAI",
+                "anthropic": "Anthropic",
+            }.get(llm_cfg.provider, llm_cfg.provider)
+            results.append(("LLM API key", ok_mark, f"{label} ({llm_cfg.model})"))
+    except RuntimeError:
+        results.append(
+            ("LLM API key", fail_mark,
+             "Set one of GEMINI_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, LLM_URL, "
+             "or set LLM_MODEL with LLM_API_KEY in ~/.applypilot/.env")
+        )
 
     # --- Tier 3 checks ---
     # Claude Code CLI

src/applypilot/config.py

@@ -206,7 +206,14 @@ def get_tier() -> int:
     """
     load_env()
 
-    has_llm = any(os.environ.get(k) for k in ("GEMINI_API_KEY", "OPENAI_API_KEY", "LLM_URL"))
+    has_provider_source = any(
+        os.environ.get(k)
+        for k in ("GEMINI_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "LLM_URL")
+    )
+    has_model_and_generic_key = bool((os.environ.get("LLM_MODEL") or "").strip()) and bool(
+        (os.environ.get("LLM_API_KEY") or "").strip()
+    )
+    has_llm = has_provider_source or has_model_and_generic_key
     if not has_llm:
         return 1
 
@@ -238,8 +245,19 @@ def check_tier(required: int, feature: str) -> None:
     _console = Console(stderr=True)
 
     missing: list[str] = []
-    if required >= 2 and not any(os.environ.get(k) for k in ("GEMINI_API_KEY", "OPENAI_API_KEY", "LLM_URL")):
-        missing.append("LLM API key — run [bold]applypilot init[/bold] or set GEMINI_API_KEY")
+    has_provider_source = any(
+        os.environ.get(k)
+        for k in ("GEMINI_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "LLM_URL")
+    )
+    has_model_and_generic_key = bool((os.environ.get("LLM_MODEL") or "").strip()) and bool(
+        (os.environ.get("LLM_API_KEY") or "").strip()
+    )
+    if required >= 2 and not (has_provider_source or has_model_and_generic_key):
+        missing.append(
+            "LLM config — run [bold]applypilot init[/bold] or set one of "
+            "GEMINI_API_KEY / OPENAI_API_KEY / ANTHROPIC_API_KEY / LLM_URL "
+            "(or set LLM_MODEL with LLM_API_KEY)"
+        )
     if required >= 3:
         if not shutil.which("claude"):
             missing.append("Claude Code CLI — install from [bold]https://claude.ai/code[/bold]")

src/applypilot/discovery/jobspy.py

@@ -15,7 +15,7 @@
 from jobspy import scrape_jobs
 
 from applypilot import config
-from applypilot.database import get_connection, init_db, store_jobs
+from applypilot.database import get_connection, init_db
 
 log = logging.getLogger(__name__)
 

src/applypilot/discovery/smartextract.py

@@ -20,17 +20,15 @@
 import time
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime, timezone
-from pathlib import Path
 from urllib.parse import quote_plus
 
-import httpx
 import yaml
 from bs4 import BeautifulSoup
 from playwright.sync_api import sync_playwright
 
 from applypilot import config
 from applypilot.config import CONFIG_DIR
-from applypilot.database import get_connection, init_db, store_jobs, get_stats
+from applypilot.database import init_db, get_stats
 from applypilot.llm import get_client
 
 log = logging.getLogger(__name__)
@@ -393,7 +391,7 @@ def judge_api_responses(api_responses: list[dict]) -> list[dict]:
         )
 
         try:
-            raw = client.ask(prompt, temperature=0.0, max_tokens=1024)
+            raw = client.chat([{"role": "user", "content": prompt}], max_output_tokens=1024)
             verdict = extract_json(raw)
             is_relevant = verdict.get("relevant", False)
             reason = verdict.get("reason", "?")
@@ -424,7 +422,7 @@ def format_strategy_briefing(intel: dict) -> str:
             sections.append(f"\nJSON-LD: {len(job_postings)} JobPosting entries found (usable!)")
             sections.append(f"First JobPosting:\n{json.dumps(job_postings[0], indent=2)[:3000]}")
         else:
-            sections.append(f"\nJSON-LD: NO JobPosting entries (json_ld strategy will NOT work)")
+            sections.append("\nJSON-LD: NO JobPosting entries (json_ld strategy will NOT work)")
         if other:
             types = [j.get("@type", "?") if isinstance(j, dict) else "?" for j in other]
             sections.append(f"Other JSON-LD types (NOT job data): {types}")
@@ -642,7 +640,7 @@ def ask_llm(prompt: str) -> tuple[str, float, dict]:
     """Send prompt to LLM. Returns (response_text, seconds_taken, metadata)."""
     client = get_client()
     t0 = time.time()
-    text = client.ask(prompt, temperature=0.0, max_tokens=4096)
+    text = client.chat([{"role": "user", "content": prompt}], max_output_tokens=4096)
     elapsed = time.time() - t0
     meta = {
         "finish_reason": "stop",

src/applypilot/enrichment/detail.py

@@ -22,9 +22,7 @@
 from bs4 import BeautifulSoup
 from playwright.sync_api import sync_playwright
 
-from applypilot import config
-from applypilot.config import DB_PATH
-from applypilot.database import get_connection, init_db, ensure_columns
+from applypilot.database import init_db
 from applypilot.llm import get_client
 
 log = logging.getLogger(__name__)
@@ -465,7 +463,7 @@ def extract_with_llm(page, url: str) -> dict:
     try:
         client = get_client()
         t0 = time.time()
-        raw = client.ask(prompt, temperature=0.0, max_tokens=4096)
+        raw = client.chat([{"role": "user", "content": prompt}], max_output_tokens=4096)
         elapsed = time.time() - t0
         log.info("LLM: %d chars in, %.1fs", len(prompt), elapsed)