package instancectl

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"net"
	"net/http"
	"net/url"
	"strconv"
	"strings"
	"time"

	"github.com/carlosframework/platform/internal/version"
)

// Deadlines per verb (design §5.3). A start or stop that exceeds its
// deadline is a failed wake or an unproven stop, never a hang: §6.7 puts
// one such call on a path that must not stall the activator. The seed's is
// long because a seed is allowed to be slow.
const (
	DeadlineControl = 30 * time.Second
	DeadlineSeed    = 150 * time.Second
	DeadlineSweep   = 60 * time.Second
	DeadlineReady   = 5 * time.Second

	// DeadlineCmdPoll bounds GET /cmd/{host}; the server answers within 30 s.
	DeadlineCmdPoll = 35 * time.Second
)

// Client is the agent's side of the control channel. It is plain HTTP over
// the unix socket at Path; unixdial's checks are for UPSTREAMS the edge
// proxies to, and this socket is the one path they refuse, so the client
// dials it directly.
type Client struct {
	Path string
	// Dial is the dialer; nil means net.Dialer. Tests do not need to override
	// it, but a caller composing several clients may.
	Dial func(ctx context.Context, path string) (net.Conn, error)
	// Build is the build this agent runs. Ready refuses a service whose
	// BuildHeader does not name it (#256); empty skips the comparison,
	// for tests that build a Client literal. NewClient sets version.Build.
	Build string
}

func NewClient(path string) *Client { return &Client{Path: path, Build: version.Build} }

// StaleBuildError is Ready's answer to a control service running a build
// other than the agent's own: the service outlived a binary change and
// serves this release's units with the previous release's code (#256).
type StaleBuildError struct{ Running, Want string }

func (e *StaleBuildError) Error() string {
	if e.Running == "" {
		return fmt.Sprintf("instance control: carlos-instance-control.service is running an older build than this agent (%s); restart carlos-instance-control.service", e.Want)
	}
	return fmt.Sprintf("instance control: carlos-instance-control.service is running build %s, this agent is %s; restart carlos-instance-control.service", e.Running, e.Want)
}

// NotReadyError carries the probe verdict a 503 /ready returned.
type NotReadyError struct{ Report ProbeReport }

func (e *NotReadyError) Error() string {
	var fails []string
	for _, l := range e.Report.Lines {
		if l.Verdict != "ok" {
			fails = append(fails, l.Check+" "+l.Verdict+" "+l.Detail)
		}
	}
	if len(fails) == 0 {
		return "instance control: box not ready (no verdict yet)"
	}
	return "instance control: box not ready: " + strings.Join(fails, "; ")
}

// httpClient builds a fresh Transport per call rather than caching one on c.
// DisableKeepAlives is what makes that the right trade: a pooled idle
// connection nothing ever reuses (each call already builds its own client)
// would just sit open, leaking one file descriptor per call instead of
// closing when the response is read.
func (c *Client) httpClient() *http.Client {
	dial := c.Dial
	if dial == nil {
		dial = func(ctx context.Context, path string) (net.Conn, error) {
			return (&net.Dialer{}).DialContext(ctx, "unix", path)
		}
	}
	return &http.Client{Transport: &http.Transport{
		DialContext:       func(ctx context.Context, _, _ string) (net.Conn, error) { return dial(ctx, c.Path) },
		DisableKeepAlives: true,
	}}
}

// do issues one verb with the given deadline and decodes a JSON body when
// there is one. A non-2xx answer becomes an error carrying the server's
// message; a dial failure names the socket so a forgotten enable reads as
// what it is from carlos logs.
func (c *Client) do(ctx context.Context, deadline time.Duration, method, path string, q url.Values, out any) (int, http.Header, error) {
	ctx, cancel := context.WithTimeout(ctx, deadline)
	defer cancel()
	u := "http://control" + path
	if len(q) > 0 {
		u += "?" + q.Encode()
	}
	req, err := http.NewRequestWithContext(ctx, method, u, nil)
	if err != nil {
		return 0, nil, err
	}
	resp, err := c.httpClient().Do(req)
	if err != nil {
		return 0, nil, fmt.Errorf("instance control socket %s: %w", c.Path, err)
	}
	defer resp.Body.Close()
	body, _ := io.ReadAll(io.LimitReader(resp.Body, 64<<10))
	if resp.StatusCode == http.StatusServiceUnavailable && path == "/ready" {
		var r ProbeReport
		_ = json.Unmarshal(body, &r)
		return resp.StatusCode, resp.Header, &NotReadyError{Report: r}
	}
	// A 502 from /sweep still carries the units it did and didn't manage to
	// stop, so it is decoded into out here even though it is about to be
	// reported as an error too; the caller needs the partial list alongside
	// the failure, not instead of it.
	if out != nil && len(body) > 0 && (resp.StatusCode/100 == 2 || (resp.StatusCode == http.StatusBadGateway && path == "/sweep")) {
		if err := json.Unmarshal(body, out); err != nil {
			return resp.StatusCode, resp.Header, fmt.Errorf("instance control %s: %v", path, err)
		}
	}
	if resp.StatusCode/100 != 2 {
		return resp.StatusCode, resp.Header, fmt.Errorf("instance control %s: %d: %s", path, resp.StatusCode, strings.TrimSpace(string(body)))
	}
	return resp.StatusCode, resp.Header, nil
}

func hostRole(host string, role Role) url.Values {
	q := url.Values{"host": {host}}
	if role != "" {
		q.Set("role", string(role))
	}
	return q
}

// Start starts the run or sidecar unit for host with the memory tier and
// returns the invocation id the server read after the start.
func (c *Client) Start(ctx context.Context, host string, role Role, memoryMax int64) (string, error) {
	q := hostRole(host, role)
	q.Set("memory_max", strconv.FormatInt(memoryMax, 10))
	var out StartResponse
	if _, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/start", q, &out); err != nil {
		return "", err
	}
	return out.InvocationID, nil
}

// Seed runs the seed unit to completion and returns its retained result.
func (c *Client) Seed(ctx context.Context, host string, memoryMax int64) (SeedResponse, error) {
	return c.seedQuery(ctx, host, memoryMax, nil)
}

// SeedExe is Seed with the seed's executable named: the staged build the
// wake recorded (settings spec §4.2), which root validates and binds in
// place of the live link. A 403 is root's refusal, reported as
// ErrStagedExe: nothing was laid out or run.
func (c *Client) SeedExe(ctx context.Context, host string, memoryMax int64, x StagedExe) (SeedResponse, error) {
	return c.seedQuery(ctx, host, memoryMax, &x)
}

func (c *Client) seedQuery(ctx context.Context, host string, memoryMax int64, x *StagedExe) (SeedResponse, error) {
	q := hostRole(host, "")
	q.Set("memory_max", strconv.FormatInt(memoryMax, 10))
	if x != nil {
		setStagedExe(q, *x)
	}
	var out SeedResponse
	status, _, err := c.do(ctx, DeadlineSeed, http.MethodPost, "/seed", q, &out)
	if err != nil && status == http.StatusForbidden && x != nil {
		return out, fmt.Errorf("%w: %v", ErrStagedExe, err)
	}
	return out, err
}

// setStagedExe puts x on a start or seed query.
func setStagedExe(q url.Values, x StagedExe) {
	q.Set("exe", x.Path)
	q.Set("version", x.Version)
	q.Set("digest", x.Digest)
}

func (c *Client) Stop(ctx context.Context, host string, role Role) error {
	_, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/stop", hostRole(host, role), nil)
	return err
}

// Cmd starts host's cmd unit and returns its invocation (run spec §5.4).
func (c *Client) Cmd(ctx context.Context, host string, memoryMax int64) (string, error) {
	return c.cmdQuery(ctx, host, memoryMax, nil)
}

// CmdExe is Cmd with the executable named: the serving generation's staged
// build, which root validates and mounts in place of the live link, as for
// the legacy sidecar (zero-downtime spec §7.5). A 403 is root's refusal,
// reported as ErrStagedExe.
func (c *Client) CmdExe(ctx context.Context, host string, memoryMax int64, x StagedExe) (string, error) {
	return c.cmdQuery(ctx, host, memoryMax, &x)
}

func (c *Client) cmdQuery(ctx context.Context, host string, memoryMax int64, x *StagedExe) (string, error) {
	q := hostRole(host, "")
	q.Set("memory_max", strconv.FormatInt(memoryMax, 10))
	if x != nil {
		q.Set("exe", x.Path)
		q.Set("version", x.Version)
		q.Set("digest", x.Digest)
	}
	var out StartResponse
	status, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/cmd", q, &out)
	if err != nil {
		if status == http.StatusForbidden && x != nil {
			return "", fmt.Errorf("%w: %v", ErrStagedExe, err)
		}
		return "", err
	}
	return out.InvocationID, nil
}

// CmdStatus long-polls the named invocation of host's cmd unit.
func (c *Client) CmdStatus(ctx context.Context, host, invocation string) (CmdStatus, error) {
	var out CmdStatus
	_, _, err := c.do(ctx, DeadlineCmdPoll, http.MethodGet, "/cmd/"+url.PathEscape(host), url.Values{"invocation": {invocation}}, &out)
	return out, err
}

func (c *Client) Reset(ctx context.Context, host string, role Role) error {
	_, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/reset", hostRole(host, role), nil)
	return err
}

// genValues is the query of a generation verb: the run role and gen=<n>.
func genValues(host string, n uint64) url.Values {
	q := hostRole(host, RoleRun)
	q.Set("gen", strconv.FormatUint(n, 10))
	return q
}

// StartGen starts generation n's unit (zero-downtime spec §7.6) with its
// tier and returns the invocation id the server read after the start. A
// failure whose cleanup could not prove the unit gone wraps ErrGenUnproven.
func (c *Client) StartGen(ctx context.Context, host string, n uint64, memoryMax int64) (string, error) {
	return c.startUnitQuery(ctx, genValues(host, n), memoryMax, nil)
}

// StartGenExe is StartGen with the generation's executable named: the
// staged build root validates and mounts in place of the live link. A 403
// is root's refusal, reported as ErrStagedExe.
func (c *Client) StartGenExe(ctx context.Context, host string, n uint64, memoryMax int64, x StagedExe) (string, error) {
	return c.startUnitQuery(ctx, genValues(host, n), memoryMax, &x)
}

// StartExe is Start with the unit's executable named: a staged build root
// validates and mounts in place of the live link, for the original
// template's run unit (the build a cold wake recorded, settings spec §4.2)
// or the legacy sidecar. A 403 is root's refusal, reported as
// ErrStagedExe.
func (c *Client) StartExe(ctx context.Context, host string, role Role, memoryMax int64, x StagedExe) (string, error) {
	return c.startUnitQuery(ctx, hostRole(host, role), memoryMax, &x)
}

// StartSidecarExe is StartExe for the legacy sidecar role: the serving
// generation's staged build (zero-downtime spec §7.5).
func (c *Client) StartSidecarExe(ctx context.Context, host string, memoryMax int64, x StagedExe) (string, error) {
	return c.StartExe(ctx, host, RoleSidecar, memoryMax, x)
}

// startUnitQuery is /start for a generation or the sidecar, optionally with
// a staged executable. One place maps root's two distinct refusals: 403 is
// ErrStagedExe (nothing was mounted), and the generation verbs' unproven
// status is ErrGenUnproven.
func (c *Client) startUnitQuery(ctx context.Context, q url.Values, memoryMax int64, x *StagedExe) (string, error) {
	q.Set("memory_max", strconv.FormatInt(memoryMax, 10))
	if x != nil {
		setStagedExe(q, *x)
	}
	var out StartResponse
	status, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/start", q, &out)
	if err != nil {
		switch {
		case status == http.StatusForbidden && x != nil:
			return "", fmt.Errorf("%w: %v", ErrStagedExe, err)
		case status == statusGenUnproven && q.Has("gen"):
			return "", fmt.Errorf("%w: %w", ErrGenUnproven, err)
		}
		return "", err
	}
	return out.InvocationID, nil
}

// StopGen stops generation n's unit only. kill kills it outright and
// returns once its cgroup is empty.
func (c *Client) StopGen(ctx context.Context, host string, n uint64, kill bool) error {
	q := genValues(host, n)
	if kill {
		q.Set("kill", "1")
	}
	_, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/stop", q, nil)
	return err
}

func (c *Client) ResetGen(ctx context.Context, host string, n uint64) error {
	_, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/reset", genValues(host, n), nil)
	return err
}

// Parent sets host's slice memory, the generation parent's backstop (spec
// §7.3): one tier, or two summed during an overlap.
func (c *Client) Parent(ctx context.Context, host string, memoryMax int64) error {
	q := url.Values{"host": {host}, "memory_max": {strconv.FormatInt(memoryMax, 10)}}
	_, _, err := c.do(ctx, DeadlineControl, http.MethodPost, "/parent", q, nil)
	return err
}

// Sweep stops every instance unit on the box (design §6.7). A 502 carries
// the units that were stopped and the ones that would not; both are
// returned with the error.
func (c *Client) Sweep(ctx context.Context) (SweepResponse, error) {
	var out SweepResponse
	status, _, err := c.do(ctx, DeadlineSweep, http.MethodPost, "/sweep", nil, &out)
	if err != nil && status == http.StatusBadGateway {
		return out, errors.Join(err, errors.New("some instance units would not stop"))
	}
	return out, err
}

// Ready is nil on 204 from a service of this agent's own build, a
// *NotReadyError on 503, and a *StaleBuildError on a 204 whose BuildHeader
// is missing or names another build (#256). The verdict is asked first:
// a service that is both stale and not ready says why it is not ready.
func (c *Client) Ready(ctx context.Context) error {
	_, hdr, err := c.do(ctx, DeadlineReady, http.MethodGet, "/ready", nil, nil)
	if err != nil {
		return err
	}
	if got := hdr.Get(BuildHeader); c.Build != "" && got != c.Build {
		return &StaleBuildError{Running: got, Want: c.Build}
	}
	return nil
}