teleo-codex/ops/pipeline-v2/lib/attribution.py

"""Attribution module — shared between post_extract.py and merge.py.

Owns: parsing attribution from YAML frontmatter, validating role entries,
computing role counts for contributor upserts, building attribution blocks.

Avoids circular dependency between post_extract.py (validates attribution at
extraction time) and merge.py (records attribution at merge time). Both
import from this shared module.

Schema reference: schemas/attribution.md
Weights reference: schemas/contribution-weights.yaml

Epimetheus owns this module. Leo reviews changes.
"""

import logging
import re
from pathlib import Path

logger = logging.getLogger("pipeline.attribution")

VALID_ROLES = frozenset({"sourcer", "extractor", "challenger", "synthesizer", "reviewer"})


# ─── Parse attribution from claim content ──────────────────────────────────


def parse_attribution(fm: dict) -> dict[str, list[dict]]:
    """Extract attribution block from claim frontmatter.

    Returns {role: [{"handle": str, "agent_id": str|None, "context": str|None}]}
    Handles both nested YAML format and flat field format.
    """
    result = {role: [] for role in VALID_ROLES}

    attribution = fm.get("attribution")
    if isinstance(attribution, dict):
        # Nested format (from schema spec)
        for role in VALID_ROLES:
            entries = attribution.get(role, [])
            if isinstance(entries, list):
                for entry in entries:
                    if isinstance(entry, dict) and "handle" in entry:
                        result[role].append({
                            "handle": entry["handle"].strip().lower().lstrip("@"),
                            "agent_id": entry.get("agent_id"),
                            "context": entry.get("context"),
                        })
                    elif isinstance(entry, str):
                        result[role].append({"handle": entry.strip().lower().lstrip("@"), "agent_id": None, "context": None})
            elif isinstance(entries, str):
                # Single entry as string
                result[role].append({"handle": entries.strip().lower().lstrip("@"), "agent_id": None, "context": None})
        return result

    # Flat format fallback (attribution_sourcer, attribution_extractor, etc.)
    for role in VALID_ROLES:
        flat_val = fm.get(f"attribution_{role}")
        if flat_val:
            if isinstance(flat_val, str):
                result[role].append({"handle": flat_val.strip().lower().lstrip("@"), "agent_id": None, "context": None})
            elif isinstance(flat_val, list):
                for v in flat_val:
                    if isinstance(v, str):
                        result[role].append({"handle": v.strip().lower().lstrip("@"), "agent_id": None, "context": None})

    # Legacy fallback: infer from source field
    if not any(result[r] for r in VALID_ROLES):
        source = fm.get("source", "")
        if isinstance(source, str) and source:
            # Try to extract author handle from source string
            # Patterns: "@handle", "Author Name", "org, description"
            handle_match = re.search(r"@(\w+)", source)
            if handle_match:
                result["sourcer"].append({"handle": handle_match.group(1).lower(), "agent_id": None, "context": source})
            else:
                # Use first word/phrase before comma as sourcer handle
                author = source.split(",")[0].strip().lower().replace(" ", "-")
                if author and len(author) > 1:
                    result["sourcer"].append({"handle": author, "agent_id": None, "context": source})

    return result


def parse_attribution_from_file(filepath: str) -> dict[str, list[dict]]:
    """Read a claim file and extract attribution. Returns role→entries dict."""
    try:
        content = Path(filepath).read_text()
    except (FileNotFoundError, PermissionError):
        return {role: [] for role in VALID_ROLES}

    from .post_extract import parse_frontmatter
    fm, _ = parse_frontmatter(content)
    if fm is None:
        return {role: [] for role in VALID_ROLES}

    return parse_attribution(fm)


# ─── Validate attribution ──────────────────────────────────────────────────


def validate_attribution(fm: dict, agent: str | None = None) -> list[str]:
    """Validate attribution block in claim frontmatter.

    Returns list of issues. Block on missing extractor, warn on missing sourcer.
    (Leo: extractor is always known, sourcer is best-effort.)

    If agent is provided and extractor is missing, auto-fix by setting the
    agent as extractor (same pattern as created-date auto-fix).

    Only validates if an attribution block is explicitly present. Legacy claims
    without attribution blocks are not blocked — they'll get attribution when
    enriched. New claims from v2 extraction always have attribution.
    """
    issues = []

    # Only validate if attribution block exists (don't break legacy claims)
    has_attribution = (
        fm.get("attribution") is not None
        or any(fm.get(f"attribution_{role}") for role in VALID_ROLES)
    )
    if not has_attribution:
        return []  # No attribution block = legacy claim, not an error

    attribution = parse_attribution(fm)

    if not attribution["extractor"]:
        if agent:
            # Auto-fix: set the processing agent as extractor
            attr = fm.get("attribution")
            if isinstance(attr, dict):
                attr["extractor"] = [{"handle": agent}]
            else:
                fm["attribution"] = {"extractor": [{"handle": agent}]}
            issues.append("fixed_missing_extractor")
        else:
            issues.append("missing_attribution_extractor")

    return issues


# ─── Build attribution block ──────────────────────────────────────────────


def build_attribution_block(
    agent: str,
    agent_id: str | None = None,
    source_handle: str | None = None,
    source_context: str | None = None,
) -> dict:
    """Build an attribution dict for a newly extracted claim.

    Called by openrouter-extract-v2.py when reconstructing claim content.
    """
    attribution = {
        "extractor": [{"handle": agent}],
        "sourcer": [],
        "challenger": [],
        "synthesizer": [],
        "reviewer": [],
    }

    if agent_id:
        attribution["extractor"][0]["agent_id"] = agent_id

    if source_handle:
        entry = {"handle": source_handle.strip().lower().lstrip("@")}
        if source_context:
            entry["context"] = source_context
        attribution["sourcer"].append(entry)

    return attribution


# ─── Compute role counts for contributor upserts ──────────────────────────


def role_counts_from_attribution(attribution: dict[str, list[dict]]) -> dict[str, list[str]]:
    """Extract {role: [handle, ...]} for contributor table upserts.

    Returns a dict mapping each role to the list of contributor handles.
    Used by merge.py to credit contributors after merge.
    """
    counts: dict[str, list[str]] = {}
    for role in VALID_ROLES:
        handles = [entry["handle"] for entry in attribution.get(role, []) if entry.get("handle")]
        if handles:
            counts[role] = handles
    return counts