package gateway

// Failover: a second and third provider, for when the first one says no.
//
// THE PROBLEM THIS SOLVES IS A CEILING, NOT A BUG. A free tier is a token
// budget per minute, and one agent run can exceed a whole minute's worth by
// itself — a three-call run measured 12,123 tokens against a ceiling of 8,000.
// withRetry already fires three times, and on a rate limit all three are
// refused, because waiting 1.6 seconds does not buy back a minute's budget. The
// run then ends GatewayFailure and a person reads "the model did not answer".
//
// Retrying harder cannot fix that. Asking somebody else can: the ceilings are
// per provider, so a second key is a second budget. Groq, Cerebras, Gemini,
// Mistral and OpenRouter all serve the same chat-completions shape, which is
// the whole reason this is a list of Configs and not a second implementation.
//
// WHAT IT DOES NOT DO, stated because the gap is where the next bug lives:
// it does not make a run cheaper, it does not raise any one provider's ceiling,
// and it does not help when every configured provider is exhausted at once. It
// converts "one busy provider" from an outage into a slower answer.

import (
	"context"
	"errors"
)

// failover tries each provider in order until one answers.
type failover struct {
	providers []Gateway
}

// NewFailover builds a gateway that falls back through `rest` when `primary`
// cannot answer. With no fallbacks it returns the primary unchanged, so a
// single-provider deployment carries no wrapper and behaves exactly as before.
func NewFailover(primary Gateway, rest ...Gateway) Gateway {
	if len(rest) == 0 {
		return primary
	}
	return &failover{providers: append([]Gateway{primary}, rest...)}
}

// Standby is a gateway that has somewhere else to go.
//
// The runtime needs this and must NOT learn what a provider is. A mid-run
// failure cannot be moved by this package — the conversation is half built and
// its tool calls belong to whoever issued them (see canFailOver) — so the only
// thing that can rescue it is starting the run again somewhere else, and only
// the loop can do that. This is the whole of what the loop is told: "there is
// another one, here it is", with no vendor, credential or model id crossing the
// boundary.
type Standby interface {
	// Standby returns a gateway beginning at the NEXT provider, and whether
	// there was one. The receiver is unchanged.
	Standby() (Gateway, bool)
}

// Standby drops the provider that just failed and returns the rest.
//
// The remainder keeps its own fallbacks, so a second failure on a three
// provider deployment still has somewhere to go. With one provider left there
// is no wrapper at all, which is NewFailover's own rule.
func (f *failover) Standby() (Gateway, bool) {
	if len(f.providers) < 2 {
		return nil, false
	}
	return NewFailover(f.providers[1], f.providers[2:]...), true
}

func (f *failover) Complete(ctx context.Context, req Request) (*Response, error) {
	var last error
	for i, p := range f.providers {
		if i > 0 && !canFailOver(req, last) {
			break
		}
		resp, err := p.Complete(ctx, req)
		if err == nil {
			return resp, nil
		}
		last = err
		// The caller's deadline governs. A deployment with four providers must
		// not spend four timeouts' worth of a person's patience discovering
		// that none of them is available.
		if ctx.Err() != nil {
			break
		}
	}
	return nil, last
}

// Stream falls over only before the first fragment has been delivered.
//
// After a delta reaches the client, the answer has begun in the reader's own
// window. Starting a second provider would continue that sentence in a
// different voice from a different model, or repeat its opening — so once text
// is out, the error is the answer.
func (f *failover) Stream(ctx context.Context, req Request, onDelta func(string)) (*Response, error) {
	var last error
	for i, p := range f.providers {
		if i > 0 && !canFailOver(req, last) {
			break
		}
		var delivered bool
		wrapped := func(s string) {
			delivered = true
			onDelta(s)
		}
		resp, err := StreamComplete(ctx, p, req, wrapped)
		if err == nil {
			return resp, nil
		}
		last = err
		if delivered || ctx.Err() != nil {
			break
		}
	}
	return nil, last
}

// canFailOver decides whether asking a DIFFERENT provider is sound.
//
// Two conditions, and both are necessary.
//
//  1. THE FAILURE MUST BE TRANSIENT. Error.Retryable() already draws that line
//     for retries and it is the same line here: a rate limit or a 5xx is the
//     provider being unable, and somebody else may be able. A 400 is a
//     malformed request and will be malformed for everyone; a 401 is this
//     deployment's own credential. Failing over on those turns one provider's
//     configuration error into every provider's, and buries the fault.
//
//  2. THE CONVERSATION MUST CARRY NO TOOL CALL AT ALL. Not merely "no
//     provider metadata" — ANY tool call pins the conversation, and the
//     difference is a bug this got wrong first time round.
//
//     The reasoning that failed: ToolCall.Extra carries provider metadata
//     echoed back verbatim (Gemini 3's thought signature), so it looked
//     sufficient to refuse only when Extra was present. But Extra is populated
//     by the provider that ISSUED the call. A conversation begun on Groq
//     carries no Extra at all, so it looked movable — and moving it hands
//     Gemini an assistant turn containing a function call with no thought
//     signature, which is exactly the 400 that took production down on
//     2026-09-22. The absent field was read as "safe to move" when it meant
//     "came from somewhere that does not sign".
//
//     So the test is the tool call, not the metadata. A conversation that has
//     called a tool belongs to whoever has been answering it. Failover is
//     available on the first model call of a run, which is where a rate limit
//     lands anyway, and nowhere else.
func canFailOver(req Request, err error) bool {
	var gwErr *Error
	if !errors.As(err, &gwErr) || !gwErr.Retryable() {
		return false
	}
	for _, m := range req.Messages {
		if len(m.ToolCalls) > 0 || len(m.ToolResults) > 0 {
			return false
		}
	}
	return true
}