hermes-agent/agent/error_classifier.py

"""API error classification for smart failover and recovery.

Provides a structured taxonomy of API errors and a priority-ordered
classification pipeline that determines the correct recovery action
(retry, rotate credential, fallback to another provider, compress
context, or abort).

Replaces scattered inline string-matching with a centralized classifier
that the main retry loop in run_agent.py consults for every API failure.
"""

from __future__ import annotations

import enum
import logging
from dataclasses import dataclass, field
from typing import Any, Dict, Optional

logger = logging.getLogger(__name__)


# ── Error taxonomy ──────────────────────────────────────────────────────

class FailoverReason(enum.Enum):
    """Why an API call failed — determines recovery strategy."""

    # Authentication / authorization
    auth = "auth"                        # Transient auth (401/403) — refresh/rotate
    auth_permanent = "auth_permanent"    # Auth failed after refresh — abort

    # Billing / quota
    billing = "billing"                  # 402 or confirmed credit exhaustion — rotate immediately
    rate_limit = "rate_limit"            # 429 or quota-based throttling — backoff then rotate

    # Server-side
    overloaded = "overloaded"            # 503/529 — provider overloaded, backoff
    server_error = "server_error"        # 500/502 — internal server error, retry

    # Transport
    timeout = "timeout"                  # Connection/read timeout — rebuild client + retry

    # Context / payload
    context_overflow = "context_overflow"  # Context too large — compress, not failover
    payload_too_large = "payload_too_large"  # 413 — compress payload
    image_too_large = "image_too_large"   # Native image part exceeds provider's per-image limit — shrink and retry

    # Model
    model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
    provider_policy_blocked = "provider_policy_blocked"  # Aggregator (e.g. OpenRouter) blocked the only endpoint due to account data/privacy policy

    # Request format
    format_error = "format_error"        # 400 bad request — abort or strip + retry

    # Provider-specific
    thinking_signature = "thinking_signature"  # Anthropic thinking block sig invalid
    long_context_tier = "long_context_tier"    # Anthropic "extra usage" tier gate
    oauth_long_context_beta_forbidden = "oauth_long_context_beta_forbidden"  # Anthropic OAuth subscription rejects 1M context beta — disable beta and retry
    llama_cpp_grammar_pattern = "llama_cpp_grammar_pattern"  # llama.cpp json-schema-to-grammar rejects regex escapes in `pattern` / `format` — strip from tools and retry

    # Catch-all
    unknown = "unknown"                  # Unclassifiable — retry with backoff


# ── Classification result ───────────────────────────────────────────────

@dataclass
class ClassifiedError:
    """Structured classification of an API error with recovery hints."""

    reason: FailoverReason
    status_code: Optional[int] = None
    provider: Optional[str] = None
    model: Optional[str] = None
    message: str = ""
    error_context: Dict[str, Any] = field(default_factory=dict)

    # Recovery action hints — the retry loop checks these instead of
    # re-classifying the error itself.
    retryable: bool = True
    should_compress: bool = False
    should_rotate_credential: bool = False
    should_fallback: bool = False

    @property
    def is_auth(self) -> bool:
        return self.reason in (FailoverReason.auth, FailoverReason.auth_permanent)



# ── Provider-specific patterns ──────────────────────────────────────────

# Patterns that indicate billing exhaustion (not transient rate limit)
_BILLING_PATTERNS = [
    "insufficient credits",
    "insufficient_quota",
    "insufficient balance",
    "credit balance",
    "credits have been exhausted",
    "top up your credits",
    "payment required",
    "billing hard limit",
    "exceeded your current quota",
    "account is deactivated",
    "plan does not include",
]

# Patterns that indicate rate limiting (transient, will resolve)
_RATE_LIMIT_PATTERNS = [
    "rate limit",
    "rate_limit",
    "too many requests",
    "throttled",
    "requests per minute",
    "tokens per minute",
    "requests per day",
    "try again in",
    "please retry after",
    "resource_exhausted",
    "rate increased too quickly",  # Alibaba/DashScope throttling
    # AWS Bedrock throttling
    "throttlingexception",
    "too many concurrent requests",
    "servicequotaexceededexception",
]

# Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
_USAGE_LIMIT_PATTERNS = [
    "usage limit",
    "quota",
    "limit exceeded",
    "key limit exceeded",
]

# Patterns confirming usage limit is transient (not billing)
_USAGE_LIMIT_TRANSIENT_SIGNALS = [
    "try again",
    "retry",
    "resets at",
    "reset in",
    "wait",
    "requests remaining",
    "periodic",
    "window",
]

# Payload-too-large patterns detected from message text (no status_code attr).
# Proxies and some backends embed the HTTP status in the error message.
_PAYLOAD_TOO_LARGE_PATTERNS = [
    "request entity too large",
    "payload too large",
    "error code: 413",
]

# Image-size patterns.  Matched against 400 bodies (not 413) because most
# providers return a 400 with a specific image-too-big message before the
# whole request hits the 413 size limit.  Anthropic's wording is the most
# important here (hard 5 MB per image, returned as
# "messages.N.content.K.image.source.base64: image exceeds 5 MB maximum").
_IMAGE_TOO_LARGE_PATTERNS = [
    "image exceeds",        # Anthropic: "image exceeds 5 MB maximum"
    "image too large",      # generic
    "image_too_large",      # error_code variant
    "image size exceeds",   # variant
    # "request_too_large" on a request known to contain an image → image is
    # the likely culprit; we still try the shrink path before giving up.
]

# Context overflow patterns
_CONTEXT_OVERFLOW_PATTERNS = [
    "context length",
    "context size",
    "maximum context",
    "token limit",
    "too many tokens",
    "reduce the length",
    "exceeds the limit",
    "context window",
    "prompt is too long",
    "prompt exceeds max length",
    "max_tokens",
    "maximum number of tokens",
    # vLLM / local inference server patterns
    "exceeds the max_model_len",
    "max_model_len",
    "prompt length",             # "engine prompt length X exceeds"
    "input is too long",
    "maximum model length",
    # Ollama patterns
    "context length exceeded",
    "truncating input",
    # llama.cpp / llama-server patterns
    "slot context",              # "slot context: N tokens, prompt N tokens"
    "n_ctx_slot",
    # Chinese error messages (some providers return these)
    "超过最大长度",
    "上下文长度",
    # AWS Bedrock Converse API error patterns
    "input is too long",
    "max input token",
    "input token",
    "exceeds the maximum number of input tokens",
]

# Model not found patterns
_MODEL_NOT_FOUND_PATTERNS = [
    "is not a valid model",
    "invalid model",
    "model not found",
    "model_not_found",
    "does not exist",
    "no such model",
    "unknown model",
    "unsupported model",
]

# OpenRouter aggregator policy-block patterns.
#
# When a user's OpenRouter account privacy setting (or a per-request
# `provider.data_collection: deny` preference) excludes the only endpoint
# serving a model, OpenRouter returns 404 with a *specific* message that is
# distinct from "model not found":
#
#   "No endpoints available matching your guardrail restrictions and
#    data policy. Configure: https://openrouter.ai/settings/privacy"
#
# We classify this as `provider_policy_blocked` rather than
# `model_not_found` because:
#   - The model *exists* — model_not_found is misleading in logs
#   - Provider fallback won't help: the account-level setting applies to
#     every call on the same OpenRouter account
#   - The error body already contains the fix URL, so the user gets
#     actionable guidance without us rewriting the message
_PROVIDER_POLICY_BLOCKED_PATTERNS = [
    "no endpoints available matching your guardrail",
    "no endpoints available matching your data policy",
    "no endpoints found matching your data policy",
]

# Auth patterns (non-status-code signals)
_AUTH_PATTERNS = [
    "invalid api key",
    "invalid_api_key",
    "authentication",
    "unauthorized",
    "forbidden",
    "invalid token",
    "token expired",
    "token revoked",
    "access denied",
]

# Anthropic thinking block signature patterns
_THINKING_SIG_PATTERNS = [
    "signature",  # Combined with "thinking" check
]

# Transport error type names
_TRANSPORT_ERROR_TYPES = frozenset({
    "ReadTimeout", "ConnectTimeout", "PoolTimeout",
    "ConnectError", "RemoteProtocolError",
    "ConnectionError", "ConnectionResetError",
    "ConnectionAbortedError", "BrokenPipeError",
    "TimeoutError", "ReadError",
    "ServerDisconnectedError",
    # SSL/TLS transport errors — transient mid-stream handshake/record
    # failures that should retry rather than surface as a stalled session.
    # ssl.SSLError subclasses OSError (caught by isinstance) but we list
    # the type names here so provider-wrapped SSL errors (e.g. when the
    # SDK re-raises without preserving the exception chain) still classify
    # as transport rather than falling through to the unknown bucket.
    "SSLError", "SSLZeroReturnError", "SSLWantReadError",
    "SSLWantWriteError", "SSLEOFError", "SSLSyscallError",
    # OpenAI SDK errors (not subclasses of Python builtins)
    "APIConnectionError",
    "APITimeoutError",
})

# Server disconnect patterns (no status code, but transport-level).
# These are the "ambiguous" patterns — a plain connection close could be
# transient transport hiccup OR server-side context overflow rejection
# (common when the API gateway disconnects instead of returning an HTTP
# error for oversized requests).  A large session + one of these patterns
# triggers the context-overflow-with-compression recovery path.
_SERVER_DISCONNECT_PATTERNS = [
    "server disconnected",
    "peer closed connection",
    "connection reset by peer",
    "connection was closed",
    "network connection lost",
    "unexpected eof",
    "incomplete chunked read",
]

# SSL/TLS transient failure patterns — intentionally distinct from
# _SERVER_DISCONNECT_PATTERNS above.
#
# An SSL alert mid-stream is almost always a transport-layer hiccup
# (flaky network, mid-session TLS renegotiation failure, load balancer
# dropping the connection) — NOT a server-side context overflow signal.
# So we want the retry path but NOT the compression path; lumping these
# into _SERVER_DISCONNECT_PATTERNS would trigger unnecessary (and
# expensive) context compression on any large-session SSL hiccup.
#
# The OpenSSL library constructs error codes by prepending a format string
# to the uppercased alert reason; OpenSSL 3.x changed the separator
# (e.g. `SSLV3_ALERT_BAD_RECORD_MAC` → `SSL/TLS_ALERT_BAD_RECORD_MAC`),
# which silently stopped matching anything explicit.  Matching on the
# stable substrings (`bad record mac`, `ssl alert`, `tls alert`, etc.)
# survives future OpenSSL format churn without code changes.
_SSL_TRANSIENT_PATTERNS = [
    # Space-separated (human-readable form, Python ssl module, most SDKs)
    "bad record mac",
    "ssl alert",
    "tls alert",
    "ssl handshake failure",
    "tlsv1 alert",
    "sslv3 alert",
    # Underscore-separated (OpenSSL error code tokens, e.g.
    # `ERR_SSL_SSL/TLS_ALERT_BAD_RECORD_MAC`, `SSLV3_ALERT_BAD_RECORD_MAC`)
    "bad_record_mac",
    "ssl_alert",
    "tls_alert",
    "tls_alert_internal_error",
    # Python ssl module prefix, e.g. "[SSL: BAD_RECORD_MAC]"
    "[ssl:",
]


# ── Classification pipeline ─────────────────────────────────────────────

def classify_api_error(
    error: Exception,
    *,
    provider: str = "",
    model: str = "",
    approx_tokens: int = 0,
    context_length: int = 200000,
    num_messages: int = 0,
) -> ClassifiedError:
    """Classify an API error into a structured recovery recommendation.

    Priority-ordered pipeline:
      1. Special-case provider-specific patterns (thinking sigs, tier gates)
      2. HTTP status code + message-aware refinement
      3. Error code classification (from body)
      4. Message pattern matching (billing vs rate_limit vs context vs auth)
      5. SSL/TLS transient alert patterns → retry as timeout
      6. Server disconnect + large session → context overflow
      7. Transport error heuristics
      8. Fallback: unknown (retryable with backoff)

    Args:
        error: The exception from the API call.
        provider: Current provider name (e.g. "openrouter", "anthropic").
        model: Current model slug.
        approx_tokens: Approximate token count of the current context.
        context_length: Maximum context length for the current model.

    Returns:
        ClassifiedError with reason and recovery action hints.
    """
    status_code = _extract_status_code(error)
    error_type = type(error).__name__
    # Copilot/GitHub Models RateLimitError may not set .status_code; force 429
    # so downstream rate-limit handling (classifier reason, pool rotation,
    # fallback gating) fires correctly instead of misclassifying as generic.
    if status_code is None and error_type == "RateLimitError":
        status_code = 429
    body = _extract_error_body(error)
    error_code = _extract_error_code(body)

    # Build a comprehensive error message string for pattern matching.
    # str(error) alone may not include the body message (e.g. OpenAI SDK's
    # APIStatusError.__str__ returns the first arg, not the body).  Append
    # the body message so patterns like "try again" in 402 disambiguation
    # are detected even when only present in the structured body.
    #
    # Also extract metadata.raw — OpenRouter wraps upstream provider errors
    # inside {"error": {"message": "Provider returned error", "metadata":
    # {"raw": "<actual error JSON>"}}} and the real error message (e.g.
    # "context length exceeded") is only in the inner JSON.
    _raw_msg = str(error).lower()
    _body_msg = ""
    _metadata_msg = ""
    if isinstance(body, dict):
        _err_obj = body.get("error", {})
        if isinstance(_err_obj, dict):
            _body_msg = str(_err_obj.get("message") or "").lower()
            # Parse metadata.raw for wrapped provider errors
            _metadata = _err_obj.get("metadata", {})
            if isinstance(_metadata, dict):
                _raw_json = _metadata.get("raw") or ""
                if isinstance(_raw_json, str) and _raw_json.strip():
                    try:
                        import json
                        _inner = json.loads(_raw_json)
                        if isinstance(_inner, dict):
                            _inner_err = _inner.get("error", {})
                            if isinstance(_inner_err, dict):
                                _metadata_msg = str(_inner_err.get("message") or "").lower()
                    except (json.JSONDecodeError, TypeError):
                        pass
        if not _body_msg:
            _body_msg = str(body.get("message") or "").lower()
    # Combine all message sources for pattern matching
    parts = [_raw_msg]
    if _body_msg and _body_msg not in _raw_msg:
        parts.append(_body_msg)
    if _metadata_msg and _metadata_msg not in _raw_msg and _metadata_msg not in _body_msg:
        parts.append(_metadata_msg)
    error_msg = " ".join(parts)
    provider_lower = (provider or "").strip().lower()
    model_lower = (model or "").strip().lower()

    def _result(reason: FailoverReason, **overrides) -> ClassifiedError:
        defaults = {
            "reason": reason,
            "status_code": status_code,
            "provider": provider,
            "model": model,
            "message": _extract_message(error, body),
        }
        defaults.update(overrides)
        return ClassifiedError(**defaults)

    # ── 1. Provider-specific patterns (highest priority) ────────────

    # Anthropic thinking block signature invalid (400).
    # Don't gate on provider — OpenRouter proxies Anthropic errors, so the
    # provider may be "openrouter" even though the error is Anthropic-specific.
    # The message pattern ("signature" + "thinking") is unique enough.
    if (
        status_code == 400
        and "signature" in error_msg
        and "thinking" in error_msg
    ):
        return _result(
            FailoverReason.thinking_signature,
            retryable=True,
            should_compress=False,
        )

    # Anthropic long-context tier gate (429 "extra usage" + "long context")
    if (
        status_code == 429
        and "extra usage" in error_msg
        and "long context" in error_msg
    ):
        return _result(
            FailoverReason.long_context_tier,
            retryable=True,
            should_compress=True,
        )

    # Anthropic OAuth subscription rejects the 1M-context beta header.
    # Observed error body: "The long context beta is not yet available for
    # this subscription." Returned as HTTP 400 from native Anthropic when
    # the subscription doesn't include 1M context, even though the request
    # carries ``anthropic-beta: context-1m-2025-08-07``. The recovery path
    # in run_agent.py rebuilds the Anthropic client with the beta stripped
    # and retries once. Pattern is narrow enough that it won't collide with
    # the 429 tier-gate pattern above (different status, different phrase).
    if (
        status_code == 400
        and "long context beta" in error_msg
        and "not yet available" in error_msg
    ):
        return _result(
            FailoverReason.oauth_long_context_beta_forbidden,
            retryable=True,
            should_compress=False,
        )

    # llama.cpp's ``json-schema-to-grammar`` converter (used by its OAI
    # server to build GBNF tool-call parsers) rejects regex escape classes
    # like ``\d``/``\w``/``\s`` and most ``format`` values. MCP servers
    # routinely emit ``"pattern": "\\d{4}-\\d{2}-\\d{2}"`` for date/phone/
    # email params. llama.cpp surfaces this as HTTP 400 with one of a few
    # recognizable phrases; on match we strip ``pattern``/``format`` from
    # ``self.tools`` in the retry loop and retry once. Cloud providers are
    # unaffected — they accept these keywords and we never hit this branch.
    if (
        status_code == 400
        and (
            "error parsing grammar" in error_msg
            or "json-schema-to-grammar" in error_msg
            or (
                "unable to generate parser" in error_msg
                and "template" in error_msg
            )
        )
    ):
        return _result(
            FailoverReason.llama_cpp_grammar_pattern,
            retryable=True,
            should_compress=False,
        )

    # ── 2. HTTP status code classification ──────────────────────────

    if status_code is not None:
        classified = _classify_by_status(
            status_code, error_msg, error_code, body,
            provider=provider_lower, model=model_lower,
            approx_tokens=approx_tokens, context_length=context_length,
            num_messages=num_messages,
            result_fn=_result,
        )
        if classified is not None:
            return classified

    # ── 3. Error code classification ────────────────────────────────

    if error_code:
        classified = _classify_by_error_code(error_code, error_msg, _result)
        if classified is not None:
            return classified

    # ── 4. Message pattern matching (no status code) ────────────────

    classified = _classify_by_message(
        error_msg, error_type,
        approx_tokens=approx_tokens,
        context_length=context_length,
        result_fn=_result,
    )
    if classified is not None:
        return classified

    # ── 5. SSL/TLS transient errors → retry as timeout (not compression) ──
    # SSL alerts mid-stream are transport hiccups, not server-side context
    # overflow signals.  Classify before the disconnect check so a large
    # session doesn't incorrectly trigger context compression when the real
    # cause is a flaky TLS handshake.  Also matches when the error is
    # wrapped in a generic exception whose message string carries the SSL
    # alert text but the type isn't ssl.SSLError (happens with some SDKs
    # that re-raise without chaining).
    if any(p in error_msg for p in _SSL_TRANSIENT_PATTERNS):
        return _result(FailoverReason.timeout, retryable=True)

    # ── 6. Server disconnect + large session → context overflow ─────
    # Must come BEFORE generic transport error catch — a disconnect on
    # a large session is more likely context overflow than a transient
    # transport hiccup.  Without this ordering, RemoteProtocolError
    # always maps to timeout regardless of session size.

    is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
    if is_disconnect and not status_code:
        # Absolute token/message-count thresholds are only a proxy for smaller
        # context windows.  Large-context sessions can have hundreds of
        # messages while still being far below their actual token budget.
        is_large = approx_tokens > context_length * 0.6 or (
            context_length <= 256000 and (approx_tokens > 120000 or num_messages > 200)
        )
        if is_large:
            return _result(
                FailoverReason.context_overflow,
                retryable=True,
                should_compress=True,
            )
        return _result(FailoverReason.timeout, retryable=True)

    # ── 7. Transport / timeout heuristics ───────────────────────────

    if error_type in _TRANSPORT_ERROR_TYPES or isinstance(error, (TimeoutError, ConnectionError, OSError)):
        return _result(FailoverReason.timeout, retryable=True)

    # ── 8. Fallback: unknown ────────────────────────────────────────

    return _result(FailoverReason.unknown, retryable=True)


# ── Status code classification ──────────────────────────────────────────

def _classify_by_status(
    status_code: int,
    error_msg: str,
    error_code: str,
    body: dict,
    *,
    provider: str,
    model: str,
    approx_tokens: int,
    context_length: int,
    num_messages: int = 0,
    result_fn,
) -> Optional[ClassifiedError]:
    """Classify based on HTTP status code with message-aware refinement."""

    if status_code == 401:
        # Not retryable on its own — credential pool rotation and
        # provider-specific refresh (Codex, Anthropic, Nous) run before
        # the retryability check in run_agent.py.  If those succeed, the
        # loop `continue`s.  If they fail, retryable=False ensures we
        # hit the client-error abort path (which tries fallback first).
        return result_fn(
            FailoverReason.auth,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    if status_code == 403:
        # OpenRouter 403 "key limit exceeded" is actually billing
        if "key limit exceeded" in error_msg or "spending limit" in error_msg:
            return result_fn(
                FailoverReason.billing,
                retryable=False,
                should_rotate_credential=True,
                should_fallback=True,
            )
        return result_fn(
            FailoverReason.auth,
            retryable=False,
            should_fallback=True,
        )

    if status_code == 402:
        return _classify_402(error_msg, result_fn)

    if status_code == 404:
        # OpenRouter policy-block 404 — distinct from "model not found".
        # The model exists; the user's account privacy setting excludes the
        # only endpoint serving it. Falling back to another provider won't
        # help (same account setting applies).  The error body already
        # contains the fix URL, so just surface it.
        if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
            return result_fn(
                FailoverReason.provider_policy_blocked,
                retryable=False,
                should_fallback=False,
            )
        if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
            return result_fn(
                FailoverReason.model_not_found,
                retryable=False,
                should_fallback=True,
            )
        # Generic 404 with no "model not found" signal — could be a wrong
        # endpoint path (common with local llama.cpp / Ollama / vLLM when
        # the URL is slightly misconfigured), a proxy routing glitch, or
        # a transient backend issue.  Classifying these as model_not_found
        # silently falls back to a different provider and tells the model
        # the model is missing, which is wrong and wastes a turn.  Treat
        # as unknown so the retry loop surfaces the real error instead.
        return result_fn(
            FailoverReason.unknown,
            retryable=True,
        )

    if status_code == 413:
        return result_fn(
            FailoverReason.payload_too_large,
            retryable=True,
            should_compress=True,
        )

    if status_code == 429:
        # Already checked long_context_tier above; this is a normal rate limit
        return result_fn(
            FailoverReason.rate_limit,
            retryable=True,
            should_rotate_credential=True,
            should_fallback=True,
        )

    if status_code == 400:
        return _classify_400(
            error_msg, error_code, body,
            provider=provider, model=model,
            approx_tokens=approx_tokens,
            context_length=context_length,
            num_messages=num_messages,
            result_fn=result_fn,
        )

    if status_code in (500, 502):
        return result_fn(FailoverReason.server_error, retryable=True)

    if status_code in (503, 529):
        return result_fn(FailoverReason.overloaded, retryable=True)

    # Other 4xx — non-retryable
    if 400 <= status_code < 500:
        return result_fn(
            FailoverReason.format_error,
            retryable=False,
            should_fallback=True,
        )

    # Other 5xx — retryable
    if 500 <= status_code < 600:
        return result_fn(FailoverReason.server_error, retryable=True)

    return None


def _classify_402(error_msg: str, result_fn) -> ClassifiedError:
    """Disambiguate 402: billing exhaustion vs transient usage limit.

    The key insight from OpenClaw: some 402s are transient rate limits
    disguised as payment errors.  "Usage limit, try again in 5 minutes"
    is NOT a billing problem — it's a periodic quota that resets.
    """
    # Check for transient usage-limit signals first
    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
    has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)

    if has_usage_limit and has_transient_signal:
        # Transient quota — treat as rate limit, not billing
        return result_fn(
            FailoverReason.rate_limit,
            retryable=True,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Confirmed billing exhaustion
    return result_fn(
        FailoverReason.billing,
        retryable=False,
        should_rotate_credential=True,
        should_fallback=True,
    )


def _classify_400(
    error_msg: str,
    error_code: str,
    body: dict,
    *,
    provider: str,
    model: str,
    approx_tokens: int,
    context_length: int,
    num_messages: int = 0,
    result_fn,
) -> ClassifiedError:
    """Classify 400 Bad Request — context overflow, format error, or generic."""

    # Image-too-large from 400 (Anthropic's 5 MB per-image check fires this way).
    # Must be checked BEFORE context_overflow because messages can trip both
    # patterns ("exceeds" + "image") and image-shrink is a cheaper recovery.
    if any(p in error_msg for p in _IMAGE_TOO_LARGE_PATTERNS):
        return result_fn(
            FailoverReason.image_too_large,
            retryable=True,
        )

    # Context overflow from 400
    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
        return result_fn(
            FailoverReason.context_overflow,
            retryable=True,
            should_compress=True,
        )

    # Some providers return model-not-found as 400 instead of 404 (e.g. OpenRouter).
    if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
        return result_fn(
            FailoverReason.provider_policy_blocked,
            retryable=False,
            should_fallback=False,
        )
    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
        return result_fn(
            FailoverReason.model_not_found,
            retryable=False,
            should_fallback=True,
        )

    # Some providers return rate limit / billing errors as 400 instead of 429/402.
    # Check these patterns before falling through to format_error.
    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
        return result_fn(
            FailoverReason.rate_limit,
            retryable=True,
            should_rotate_credential=True,
            should_fallback=True,
        )
    if any(p in error_msg for p in _BILLING_PATTERNS):
        return result_fn(
            FailoverReason.billing,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Generic 400 + large session → probable context overflow
    # Anthropic sometimes returns a bare "Error" message when context is too large
    err_body_msg = ""
    if isinstance(body, dict):
        err_obj = body.get("error", {})
        if isinstance(err_obj, dict):
            err_body_msg = str(err_obj.get("message") or "").strip().lower()
        # Responses API (and some providers) use flat body: {"message": "..."}
        if not err_body_msg:
            err_body_msg = str(body.get("message") or "").strip().lower()
    is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
    # Absolute token/message-count thresholds are only a proxy for smaller
    # context windows.  Large-context sessions can have many messages while
    # still being far below their actual token budget.
    is_large = approx_tokens > context_length * 0.4 or (
        context_length <= 256000 and (approx_tokens > 80000 or num_messages > 80)
    )

    if is_generic and is_large:
        return result_fn(
            FailoverReason.context_overflow,
            retryable=True,
            should_compress=True,
        )

    # Non-retryable format error
    return result_fn(
        FailoverReason.format_error,
        retryable=False,
        should_fallback=True,
    )


# ── Error code classification ───────────────────────────────────────────

def _classify_by_error_code(
    error_code: str, error_msg: str, result_fn,
) -> Optional[ClassifiedError]:
    """Classify by structured error codes from the response body."""
    code_lower = error_code.lower()

    if code_lower in ("resource_exhausted", "throttled", "rate_limit_exceeded"):
        return result_fn(
            FailoverReason.rate_limit,
            retryable=True,
            should_rotate_credential=True,
        )

    if code_lower in ("insufficient_quota", "billing_not_active", "payment_required"):
        return result_fn(
            FailoverReason.billing,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    if code_lower in ("model_not_found", "model_not_available", "invalid_model"):
        return result_fn(
            FailoverReason.model_not_found,
            retryable=False,
            should_fallback=True,
        )

    if code_lower in ("context_length_exceeded", "max_tokens_exceeded"):
        return result_fn(
            FailoverReason.context_overflow,
            retryable=True,
            should_compress=True,
        )

    return None


# ── Message pattern classification ──────────────────────────────────────

def _classify_by_message(
    error_msg: str,
    error_type: str,
    *,
    approx_tokens: int,
    context_length: int,
    result_fn,
) -> Optional[ClassifiedError]:
    """Classify based on error message patterns when no status code is available."""

    # Payload-too-large patterns (from message text when no status_code)
    if any(p in error_msg for p in _PAYLOAD_TOO_LARGE_PATTERNS):
        return result_fn(
            FailoverReason.payload_too_large,
            retryable=True,
            should_compress=True,
        )

    # Image-too-large patterns (from message text when no status_code)
    if any(p in error_msg for p in _IMAGE_TOO_LARGE_PATTERNS):
        return result_fn(
            FailoverReason.image_too_large,
            retryable=True,
        )

    # Usage-limit patterns need the same disambiguation as 402: some providers
    # surface "usage limit" errors without an HTTP status code.  A transient
    # signal ("try again", "resets at", …) means it's a periodic quota, not
    # billing exhaustion.
    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
    if has_usage_limit:
        has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
        if has_transient_signal:
            return result_fn(
                FailoverReason.rate_limit,
                retryable=True,
                should_rotate_credential=True,
                should_fallback=True,
            )
        return result_fn(
            FailoverReason.billing,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Billing patterns
    if any(p in error_msg for p in _BILLING_PATTERNS):
        return result_fn(
            FailoverReason.billing,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Rate limit patterns
    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
        return result_fn(
            FailoverReason.rate_limit,
            retryable=True,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Context overflow patterns
    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
        return result_fn(
            FailoverReason.context_overflow,
            retryable=True,
            should_compress=True,
        )

    # Auth patterns
    # Auth errors should NOT be retried directly — the credential is invalid and
    # retrying with the same key will always fail.  Set retryable=False so the
    # caller triggers credential rotation (should_rotate_credential=True) or
    # provider fallback rather than an immediate retry loop.
    if any(p in error_msg for p in _AUTH_PATTERNS):
        return result_fn(
            FailoverReason.auth,
            retryable=False,
            should_rotate_credential=True,
            should_fallback=True,
        )

    # Provider policy-block (aggregator-side guardrail) — check before
    # model_not_found so we don't mis-label as a missing model.
    if any(p in error_msg for p in _PROVIDER_POLICY_BLOCKED_PATTERNS):
        return result_fn(
            FailoverReason.provider_policy_blocked,
            retryable=False,
            should_fallback=False,
        )

    # Model not found patterns
    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
        return result_fn(
            FailoverReason.model_not_found,
            retryable=False,
            should_fallback=True,
        )

    return None


# ── Helpers ─────────────────────────────────────────────────────────────

def _extract_status_code(error: Exception) -> Optional[int]:
    """Walk the error and its cause chain to find an HTTP status code."""
    current = error
    for _ in range(5):  # Max depth to prevent infinite loops
        code = getattr(current, "status_code", None)
        if isinstance(code, int):
            return code
        # Some SDKs use .status instead of .status_code
        code = getattr(current, "status", None)
        if isinstance(code, int) and 100 <= code < 600:
            return code
        # Walk cause chain
        cause = getattr(current, "__cause__", None) or getattr(current, "__context__", None)
        if cause is None or cause is current:
            break
        current = cause
    return None


def _extract_error_body(error: Exception) -> dict:
    """Extract the structured error body from an SDK exception."""
    body = getattr(error, "body", None)
    if isinstance(body, dict):
        return body
    # Some errors have .response.json()
    response = getattr(error, "response", None)
    if response is not None:
        try:
            json_body = response.json()
            if isinstance(json_body, dict):
                return json_body
        except Exception:
            pass
    return {}


def _extract_error_code(body: dict) -> str:
    """Extract an error code string from the response body."""
    if not body:
        return ""
    error_obj = body.get("error", {})
    if isinstance(error_obj, dict):
        code = error_obj.get("code") or error_obj.get("type") or ""
        if isinstance(code, str) and code.strip():
            return code.strip()
    # Top-level code
    code = body.get("code") or body.get("error_code") or ""
    if isinstance(code, (str, int)):
        return str(code).strip()
    return ""


def _extract_message(error: Exception, body: dict) -> str:
    """Extract the most informative error message."""
    # Try structured body first
    if body:
        error_obj = body.get("error", {})
        if isinstance(error_obj, dict):
            msg = error_obj.get("message", "")
            if isinstance(msg, str) and msg.strip():
                return msg.strip()[:500]
        msg = body.get("message", "")
        if isinstance(msg, str) and msg.strip():
            return msg.strip()[:500]
    # Fallback to str(error)
    return str(error)[:500]