VC Investment Screening

def upload_documents(self, file_paths: list[str]) -> list[int]:
    """Upload files, wait for embedding, return the list of file IDs."""
    workspace_id = self._discover_workspace_id()
    file_ids = [self._upload_one(p, workspace_id) for p in file_paths]
    self._wait_for_embedding(file_ids)
    return file_ids

def _wait_for_embedding(self, file_ids: list[int]) -> None:
    deadline = time.time() + self.POLL_TIMEOUT  # 180s default
    pending = set(file_ids)
    while pending and time.time() < deadline:
        for fid in list(pending):
            status = self._get_file_status(fid)
            if status == "embedded":
                pending.discard(fid)
            elif status == "failed":
                raise RuntimeError(f"File {fid} failed to process on Paradigm.")
        if pending:
            time.sleep(self.POLL_INTERVAL)  # 3s
    if pending:
        raise TimeoutError(f"Files did not embed within {self.POLL_TIMEOUT}s")

EXTRACTION_QUERY = """You are an expert venture-capital analyst. Provide a comprehensive,
structured analysis of this investment opportunity. Extract the following information
and name each section explicitly in your answer:

1. Target company name and legal entity structure.
2. Business model and core products / services.
3. Geographic presence and expansion plans, explicitly noting any GCC activity
   or joint-venture structures.
4. Financial position: current revenue and EBITDA, runway to profitability,
   funding requirements, dividend policy if mentioned.
5. Deal terms: proposed ticket size (USD), management fees, process timeline
   in weeks, round structure (primary vs secondary).
6. Sector and sub-sector classification.
7. Return projections, including IRR if disclosed.
8. Syndicate: is there a lead investor, and who are the co-investors.
9. Any mention of a group / strategic co-investment structure.

Be specific with numbers. If information is not disclosed in the document,
state "not disclosed" explicitly rather than omitting the section."""

SEARCH_TOP_K = 40   # chunks retrieved by embedding similarity
SEARCH_TOP_N = 20   # chunks kept after re-ranking

def document_search(self, query: str, file_ids: list[int]) -> str:
    payload = {
        "query": query,
        "force_tool": "document_search",
        "file_ids": file_ids,
        "tool_parameters": {
            "document_search": {
                "top_k": self.SEARCH_TOP_K,
                "top_n": self.SEARCH_TOP_N,
            }
        },
    }
    resp = requests.post(
        f"{self.base_url}/api/v3/threads/turns",
        headers=self.headers, json=payload, timeout=240,
    )
    resp.raise_for_status()
    return self._extract_assistant_text(resp.json())

# Size thresholds (USD millions)
SIZE_MIN = 5.0
SIZE_STRONG = 8.0

# Return threshold (percent)
IRR_MIN = 15.0

# Timeline thresholds (weeks)
TIMELINE_MIN = 8
TIMELINE_MIN_COINVEST = 3

# Sector targeting
TARGET_SECTORS = [
    "healthcare", "healthtech", "education", "edtech",
    "data economy", "saas", "energy transition", "cleantech", "industrials",
]
EXCLUDED_SECTORS = ["consumer", "traditional infrastructure"]

def _check_investment_size(analysis: str) -> CriterionResult:
    size = _ticket_size_usd_m(analysis)  # regex for "$Xm" near ticket/raise keywords
    if size >= SIZE_STRONG:
        return CriterionResult("MET", f"Ticket size ${size}m meets strong-preference threshold (>=${SIZE_STRONG}m).")
    if size >= SIZE_MIN:
        return CriterionResult("MET", f"Ticket size ${size}m meets minimum threshold (>=${SIZE_MIN}m).")
    if size > 0:
        return CriterionResult("NOT MET", f"Ticket size ${size}m below minimum threshold (${SIZE_MIN}m).")
    return CriterionResult("NOT MET", "Ticket size not disclosed.")


def _check_return_threshold(analysis: str) -> CriterionResult:
    irr = _first_irr_pct(analysis)
    low_risk = _has_any(analysis, ["low risk", "low-risk"])
    if irr >= IRR_MIN:
        return CriterionResult("MET", f"Projected IRR of {irr}% meets {IRR_MIN}% threshold.")
    if irr > 0 and low_risk:
        return CriterionResult("MET", f"Projected IRR of {irr}% below {IRR_MIN}% but justified as low-risk.")
    if irr > 0:
        return CriterionResult("NOT MET", f"Projected IRR of {irr}% below {IRR_MIN}% with no low-risk justification.")
    return CriterionResult("NOT MET", "Return projections / IRR not disclosed in the document.")

if met == total:
    recommendation = "RECOMMEND for further due diligence"
elif met >= 7:
    recommendation = "CONDITIONAL RECOMMEND — address the gaps before proceeding"
elif met >= 5:
    recommendation = "WEAK RECOMMEND — significant gaps, requires committee discussion"
else:
    recommendation = "DO NOT RECOMMEND — does not meet enough criteria"

SYSTEM_PROMPT = """You are an associate at a venture-capital firm preparing a concise
reply email to a banker who forwarded an investment opportunity. Write in
professional but warm English. No emojis. No marketing language. Keep the
email to 5-8 short sentences. Return only the email body — no subject line,
no commentary before or after."""

def _reply_prompt(company, recommendation, met, total, failed_criteria):
    if "DO NOT RECOMMEND" in recommendation:
        brief = ("Draft a diplomatic decline that thanks the counterparty, "
                 "acknowledges the merit of the business, does not itemise every "
                 "reason for declining, and leaves the door open for future opportunities.")
    elif "CONDITIONAL" in recommendation or "WEAK" in recommendation:
        failed_text = ", ".join(failed_criteria) or "a few gaps"
        brief = (f"The following criteria were not met: {failed_text}. "
                 "Draft a reply that thanks the counterparty, expresses interest, asks "
                 "for a follow-up call to discuss the specific open points, and proposes "
                 "a couple of dates next week.")
    else:
        brief = ("Draft a positive reply that expresses strong interest and asks for "
                 "a meeting with the founders plus access to the data room.")
    return f"Company under review: {company}.\n{brief}"

{
  "company": "MedSync Health FZ-LLC",
  "recommendation": "CONDITIONAL RECOMMEND — address the gaps before proceeding",
  "summary": { "met": 8, "total": 9, "failed_criteria": ["Return Threshold"] },
  "criteria": [
    { "key": "geography_structure", "label": "Geography / Structure",
      "status": "MET", "explanation": "GCC joint-venture / expansion structure identified." },
    { "key": "return_threshold", "label": "Return Threshold",
      "status": "NOT MET", "explanation": "Return projections / IRR not disclosed in the document." }
  ],
  "reply_email": "Dear Marcus, thank you for sharing the MedSync Health opportunity ...",
  "analysis": "1. Target company name and legal entity structure.\n   - Company Name: MedSync Health FZ-LLC ..."
}

def _check_founder_background(analysis: str) -> CriterionResult:
    lc = analysis.lower()
    if _has_any(analysis, ["ex-founder", "second-time founder", "prior exit"]):
        return CriterionResult("MET", "Founder has prior entrepreneurial experience.")
    return CriterionResult("NOT MET", "No prior founder experience mentioned.")