Merge pull request 'node-tools without the controller's paging and handover reads (issue 1126 group B)' (#55) from feat/1126-removal into main
This commit was merged in pull request #55.
This commit is contained in:
@@ -45,7 +45,7 @@ MESH_OPERATOR_ACCOUNT whose machine this is, and MESH_OPERATOR_HOME where thei
|
||||
MESH_BROKER_URL a plain URL instead of the credential, for the bootstrap case
|
||||
```
|
||||
|
||||
`node dist/main.js`. On a node the controller composes the variables and the host supervises the
|
||||
`node dist/main.js`. On a node the mesh composes the variables and the node-engine supervises the
|
||||
process like any other host-side workload (novox/hq to-be 38). As `node-tools` the same process is
|
||||
the console: MCP on `127.0.0.1:4270` (or `MESH_CONSOLE_LISTEN`).
|
||||
|
||||
@@ -66,14 +66,14 @@ answer took, its size in bytes, how many modules and tools it announced, whether
|
||||
fit the bus, when it was last heard — and who was expected and not heard).
|
||||
|
||||
`mesh_search` also finds a tool by the shell command it replaces (novox/hq ADR 0245): each seat verb and
|
||||
module tool says what it replaces in the controller's records (`replaces`, read from the controller's
|
||||
module tool says what it replaces in the indexer's records (`replaces`, read from its
|
||||
`tools` and `modules` answers), so `journalctl -u x`, `systemctl status x` or `docker ps` puts the verb
|
||||
for it first, and says the command it matched as `instead_of`. A word also matches through a short table
|
||||
of the words agents use for the mesh's (`logs` finds the journal). Best first: a replaced command, then
|
||||
words in a name or a replaced command, then words in a description; seats before modules on a tie.
|
||||
|
||||
Discovery asks the bus (ADR 0197): every runtime answers the NATS services protocol's `$SRV.PING` and
|
||||
`$SRV.INFO` with what it serves at that moment, and the console reads where the controller's records
|
||||
`$SRV.INFO` with what it serves at that moment, and the console reads where the placement seat's records
|
||||
place each module. The console waits at least 750 ms, and up to 5 s for every runtime that answered
|
||||
PING to send what it serves — a large runtime's answer crossing the bus to a broker on another machine
|
||||
can arrive well after the rest. A runtime that said it is there and did not say what it serves, or
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
The node's tool runtime as a module (novox/hq ADR 0175, to-be 38 WP3). Assigned to a machine, it is
|
||||
one process the host runs from this bundle, as the operator's account: it serves every assigned
|
||||
module's tools and every held seat's verbs on the bus, and answers MCP on the machine's loopback —
|
||||
the console (design 34). The controller composes the process (which bundles to load, where the
|
||||
the console (design 34). The mesh composes the process (which bundles to load, where the
|
||||
credential is, whose machine it is); this manifest says only what the machine must have for it: the
|
||||
interpreter, a place for the credential, the loopback port, and leave to call every tool.
|
||||
|
||||
|
||||
+1
-1
@@ -8,7 +8,7 @@ require (
|
||||
)
|
||||
|
||||
require (
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261101235037-c21d8fd9692c
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261102112556-abf5eace7791
|
||||
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op // indirect
|
||||
github.com/google/go-tpm v0.9.8 // indirect
|
||||
github.com/klauspost/compress v1.20.0 // indirect
|
||||
|
||||
+2
-4
@@ -1,7 +1,5 @@
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261101085317-790d1c82d027 h1:a33dsavoaqllh40eVICbhxi6Kero1EGSjt1V+2fa2Hk=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261101085317-790d1c82d027/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261101235037-c21d8fd9692c h1:/YCxh+NYfqry3PxZYY1nQXaccupobxpsFt8c9BYuGBg=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261101235037-c21d8fd9692c/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261102112556-abf5eace7791 h1:7SYIDPMxbPBr8dMB6k9fYsgVt4ZyWVL41q4LMFsfAvs=
|
||||
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261102112556-abf5eace7791/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
|
||||
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0=
|
||||
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI=
|
||||
github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo=
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
// **A machine heard and its runtime gone is a machine nobody can ask anything.** The node-engine says
|
||||
// every minute that the machine is there; nothing said whether the runtime serving every module's
|
||||
// tools and every held seat's verbs was. Now it says so too, on its own subject, every interval, with
|
||||
// the interval — the controller's watchdog raises `tools-silent` after three missed — and its build.
|
||||
// the interval — the mesh's watchdog raises `tools-silent` after three missed — and its build.
|
||||
// Core NATS, kept by nobody, as the host's heartbeat: a lost one is the next one.
|
||||
package alive
|
||||
|
||||
|
||||
@@ -32,9 +32,7 @@ import (
|
||||
"github.com/novox/mesh-tools/node-tools/internal/wire"
|
||||
)
|
||||
|
||||
// RequestTimeout is how long a call waits for its answer — what modules already expect. The
|
||||
// controller answers its verbs well inside it (its AnswerWithin, ten seconds), with a call id while a
|
||||
// verb still runs, so a caller is never left guessing past this (novox/hq issue 265).
|
||||
// RequestTimeout is how long a call waits for its answer — what modules already expect.
|
||||
const RequestTimeout = 30 * time.Second
|
||||
|
||||
// Credential is a broker credential as the mesh delivers it (novox/hq ADR 0120).
|
||||
@@ -344,7 +342,7 @@ func (c *Conn) Credential() Credential { return c.cred }
|
||||
// Follow reads a module's membership on this machine once and follows it live, so its tools are
|
||||
// served where the mesh issued them (ADR 0175). It is read from the grants part's state memberships, its key
|
||||
// `<node>.<module>` (novox/hq ADR 0571 clause 7 and 10, mesh-sdk buscompose.GrantsMembershipsBucket), and nowhere else:
|
||||
// the controller's assignments stream is not read and its subject is not heard.
|
||||
// the old assignments stream is not read and its subject is not heard.
|
||||
func (c *Conn) Follow(module string) {
|
||||
c.mu.Lock()
|
||||
if c.node == "" {
|
||||
@@ -790,83 +788,47 @@ func (c *Conn) Ask(key string, body any, on string) (Answered, error) {
|
||||
// account publish with its own name alone; asked again on the subject that names no caller only when the
|
||||
// first reached nobody — nothing serves it yet, or the bus does not grant it yet — so no call is done twice.
|
||||
if called := CalledSubject(subject, c.cred.User); called != "" {
|
||||
answered, handingOver, fallBack, err := c.askCalled(called, data)
|
||||
answered, fallBack, err := c.askCalled(called, data)
|
||||
if !fallBack {
|
||||
if !handingOver {
|
||||
return answered, err
|
||||
}
|
||||
time.Sleep(HandoverPause)
|
||||
answered, again, _, err := c.askCalled(called, data)
|
||||
if err != nil && again {
|
||||
return Answered{}, fmt.Errorf("asked twice, %s apart, and both times refused as a handover: %w", HandoverPause, err)
|
||||
}
|
||||
return answered, err
|
||||
}
|
||||
}
|
||||
answered, handingOver, err := c.askOnce(subject, data)
|
||||
if !handingOver {
|
||||
return answered, err
|
||||
}
|
||||
// **Refused because the controller is handing over: asked once more** (novox/hq issue 289). The
|
||||
// controller being replaced did nothing and said so; the one after it answers the same call. Once:
|
||||
// a second refusal is a controller that is not coming back, and the caller is told.
|
||||
time.Sleep(HandoverPause)
|
||||
answered, again, err := c.askOnce(subject, data)
|
||||
if err != nil && again {
|
||||
return Answered{}, fmt.Errorf("asked twice, %s apart, and both times refused as a handover: %w", HandoverPause, err)
|
||||
}
|
||||
return answered, err
|
||||
return c.askOnce(subject, data)
|
||||
}
|
||||
|
||||
// HandoverPause is how long a call refused as a handover waits before it is asked once more: the
|
||||
// supervisor's restart of the controller, which stops the one being replaced and starts the next. A
|
||||
// variable so a test need not wait.
|
||||
var HandoverPause = 3 * time.Second
|
||||
|
||||
// RetryHandingOver is the mark the controller puts on a call it refused because it is being replaced
|
||||
// (mesh-controller internal/link, `"retry": "handing-over"`).
|
||||
const RetryHandingOver = "handing-over"
|
||||
|
||||
// ErrNoResponders is the bus's own refusal: nothing subscribes to the subject asked. It is told apart
|
||||
// from a tool's own error by errors.Is, never by its text (a tool may say "503" itself, issue 1529).
|
||||
var ErrNoResponders = errors.New("503 no responders")
|
||||
|
||||
// askOnce asks once, and says whether the answer was a refusal marked to be asked again.
|
||||
func (c *Conn) askOnce(subject string, data []byte) (Answered, bool, error) {
|
||||
// askOnce asks once.
|
||||
func (c *Conn) askOnce(subject string, data []byte) (Answered, error) {
|
||||
msg, err := c.nc.Request(subject, data, RequestTimeout)
|
||||
if err != nil {
|
||||
if errors.Is(err, nats.ErrNoResponders) {
|
||||
return Answered{}, false, ErrNoResponders
|
||||
return Answered{}, ErrNoResponders
|
||||
}
|
||||
if errors.Is(err, nats.ErrTimeout) {
|
||||
return Answered{}, false, errors.New("timeout")
|
||||
return Answered{}, errors.New("timeout")
|
||||
}
|
||||
return Answered{}, false, err
|
||||
return Answered{}, err
|
||||
}
|
||||
return c.answerOf(subject, msg.Data)
|
||||
return answerOf(msg.Data)
|
||||
}
|
||||
|
||||
// answerOf reads one answer, asking the rest of a paged one on the subject it was asked on, and says whether it
|
||||
// was a refusal marked to be asked again.
|
||||
func (c *Conn) answerOf(subject string, data []byte) (Answered, bool, error) {
|
||||
// An answer larger than one message comes in parts (pages.go, novox/hq issue 314).
|
||||
body, err := c.whole(subject, data)
|
||||
if err != nil {
|
||||
return Answered{}, false, err
|
||||
}
|
||||
// answerOf reads one answer.
|
||||
func answerOf(data []byte) (Answered, error) {
|
||||
var r struct {
|
||||
Result json.RawMessage `json:"result"`
|
||||
Error string `json:"error"`
|
||||
Node string `json:"node"`
|
||||
Retry string `json:"retry"`
|
||||
}
|
||||
if err := json.Unmarshal(body, &r); err != nil {
|
||||
return Answered{}, false, err
|
||||
if err := json.Unmarshal(data, &r); err != nil {
|
||||
return Answered{}, err
|
||||
}
|
||||
if r.Error != "" {
|
||||
return Answered{}, r.Retry == RetryHandingOver, errors.New(r.Error)
|
||||
return Answered{}, errors.New(r.Error)
|
||||
}
|
||||
return Answered{Result: r.Result, Node: r.Node}, false, nil
|
||||
return Answered{Result: r.Result, Node: r.Node}, nil
|
||||
}
|
||||
|
||||
// PublishAs emits an event as a module: published into JetStream and awaited, de-duplicated by its
|
||||
@@ -1070,7 +1032,7 @@ func (c *Conn) AskAs(module, key string, body any) (Answered, error) {
|
||||
}
|
||||
|
||||
// EventsStream is where every module's events land, and ConsumerOf the durable consumer the
|
||||
// controller makes for a module on a machine: the same names the module's own runtime bound
|
||||
// mesh makes for a module on a machine: the same names the module's own runtime bound
|
||||
// (node-tools/src/broker-nats.ts), so moving the module into the node's runtime neither loses an
|
||||
// event nor sees one twice.
|
||||
const EventsStream = "EVENTS"
|
||||
@@ -1085,7 +1047,7 @@ func ConsumerOf(node, module string) string {
|
||||
|
||||
// NakDelay is how long an event a handler failed waits before it is offered again: a transient cause
|
||||
// gets another attempt, a permanent one exhausts the consumer's max-deliver rather than spinning. The
|
||||
// consumer then gives the event up, and the controller keeps it in DEAD_LETTERS until a person delivers
|
||||
// consumer then gives the event up, and the mesh keeps it in DEAD_LETTERS until a person delivers
|
||||
// it again — under `mesh.again.<consumer>.…`, from which keyOf reads the same key — or drops it
|
||||
// (novox/hq issue 330).
|
||||
var NakDelay = 5 * time.Second
|
||||
@@ -1099,7 +1061,7 @@ var EventHeartbeat = 10 * time.Second
|
||||
// ConsumeAs reads a module's durable consumer on EVENTS, and each one on a module's stream its
|
||||
// membership names (novox/hq ADR 0363 §8), and hands each event to deliver one at a time (novox/hq
|
||||
// ADR 0198): acknowledged when deliver returns nil, negatively acknowledged after NakDelay when it
|
||||
// returns an error, terminated when it is not an event at all. The consumers are the controller's to
|
||||
// returns an error, terminated when it is not an event at all. The consumers are the mesh's to
|
||||
// create; this binds to them and never makes one. Runs until stopped.
|
||||
func (c *Conn) ConsumeAs(module string, deliver func(Envelope) error) (func(), error) {
|
||||
durable := ConsumerOf(c.node, module)
|
||||
@@ -1109,7 +1071,7 @@ func (c *Conn) ConsumeAs(module string, deliver func(Envelope) error) (func(), e
|
||||
}
|
||||
h := newHearing(c, js, module, deliver)
|
||||
// Bound by name, never created and never matched against a subject: the consumer and its
|
||||
// filters are the controller's (design 29 §3), exactly as the module's own runtime bound it.
|
||||
// filters are the mesh's (design 29 §3), exactly as the module's own runtime bound it.
|
||||
events, _, doing, err := h.bind(EventsStream, durable, nil)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("%s %s's consumer %s: %w", doing, module, durable, err)
|
||||
|
||||
@@ -18,7 +18,7 @@ import (
|
||||
// mesh.seat.<seat>.call.<verb>.<caller> a mesh seat's verb
|
||||
// mesh.seat.<seat>.call.<verb>.<node>.<caller> a node seat's verb on one machine
|
||||
//
|
||||
// The last token is the bus user that published the call, and the controller grants each user the publish of
|
||||
// The last token is the bus user that published the call, and the mesh grants each user the publish of
|
||||
// these subjects with its own name there and no other — so the caller is a fact the bus server enforces, and
|
||||
// the runtime hands it to the module from the subject a call arrived on, never from the payload.
|
||||
//
|
||||
@@ -32,7 +32,7 @@ import (
|
||||
const CallKind = "call"
|
||||
|
||||
// A bus user's name carries dots (`<node>.<module>`, `person.<name>`); a subject token cannot. In the token
|
||||
// each dot is written `~`, which no part of a bus user's name may hold (the controller refuses any part that
|
||||
// each dot is written `~`, which no part of a bus user's name may hold (the mesh refuses any part that
|
||||
// is not letters, digits, `_` or `-`), so the token is the user's name and nothing else.
|
||||
const userDot = "~"
|
||||
|
||||
@@ -118,7 +118,7 @@ type callers struct {
|
||||
pending map[string]map[uint64]context.CancelCauseFunc
|
||||
}
|
||||
|
||||
// errCallRefused is the bus refusing a caller-named publish: this user is not granted it yet (the controller's
|
||||
// errCallRefused is the bus refusing a caller-named publish: this user is not granted it yet (the mesh's
|
||||
// grant not delivered to the bus), so the call is asked again on the subject that names no caller.
|
||||
var errCallRefused = errors.New("the bus refused the caller-named subject")
|
||||
|
||||
@@ -150,7 +150,7 @@ func (c *Conn) publishRefused(err error) bool {
|
||||
// askCalled asks once on a caller-named subject. fallBack says the call reached nobody — nothing serves that
|
||||
// subject yet, or the bus refused this user its publish — so it may be asked on the subject that names no
|
||||
// caller without being done twice.
|
||||
func (c *Conn) askCalled(subject string, data []byte) (answered Answered, handingOver, fallBack bool, err error) {
|
||||
func (c *Conn) askCalled(subject string, data []byte) (answered Answered, fallBack bool, err error) {
|
||||
ctx, cancel := context.WithCancelCause(context.Background())
|
||||
ctx, stop := context.WithTimeout(ctx, RequestTimeout)
|
||||
defer stop()
|
||||
@@ -180,22 +180,22 @@ func (c *Conn) askCalled(subject string, data []byte) (answered Answered, handin
|
||||
if err != nil {
|
||||
switch {
|
||||
case errors.Is(context.Cause(ctx), errCallRefused):
|
||||
return Answered{}, false, true, nil
|
||||
return Answered{}, true, nil
|
||||
case errors.Is(err, nats.ErrNoResponders):
|
||||
c.saidFallBack(subject)
|
||||
return Answered{}, false, true, nil
|
||||
return Answered{}, true, nil
|
||||
case errors.Is(err, context.DeadlineExceeded) || errors.Is(err, nats.ErrTimeout):
|
||||
return Answered{}, false, false, errors.New("timeout")
|
||||
return Answered{}, false, errors.New("timeout")
|
||||
}
|
||||
return Answered{}, false, false, err
|
||||
return Answered{}, false, err
|
||||
}
|
||||
answered, handingOver, err = c.answerOf(subject, msg.Data)
|
||||
return answered, handingOver, false, err
|
||||
answered, err = answerOf(msg.Data)
|
||||
return answered, false, err
|
||||
}
|
||||
|
||||
// saidFallBack says, once per subject, that a caller-named call reached nobody and is asked on the subject that
|
||||
// names no caller: a runtime or holder not yet serving it, or a grant that drifted, is seen in the log rather
|
||||
// than read later as a quiet "unproven" (novox/hq issue 365; expected for the controller's seat until hq issue
|
||||
// than read later as a quiet "unproven" (novox/hq issue 365; expected until hq issue
|
||||
// 464).
|
||||
func (c *Conn) saidFallBack(subject string) {
|
||||
c.calls.mu.Lock()
|
||||
|
||||
@@ -16,7 +16,7 @@ import (
|
||||
mt "github.com/novox/mesh-tools/node-tools/internal/meshtest"
|
||||
)
|
||||
|
||||
// A bus whose users are granted as the controller grants them (mesh-controller internal/broker): each named
|
||||
// A bus whose users are granted as the controller grants them (mesh-placement internal/broker): each named
|
||||
// user publishes the subjects listed for it.
|
||||
func grantedBus(t *testing.T, publish map[string][]string) string {
|
||||
t.Helper()
|
||||
|
||||
@@ -1,73 +0,0 @@
|
||||
package bus_test
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"sync/atomic"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-tools/node-tools/internal/bus"
|
||||
"github.com/novox/mesh-tools/node-tools/internal/meshtest"
|
||||
)
|
||||
|
||||
// **A call the controller refused because it is handing over is asked once more** (novox/hq issue 289):
|
||||
// the controller being replaced did nothing and marked its refusal, and the one after it answers. A
|
||||
// refusal not so marked is final, and a second handover refusal is said, not asked a third time.
|
||||
func TestAHandoverRefusalIsAskedOnceMore(t *testing.T) {
|
||||
was := bus.HandoverPause
|
||||
bus.HandoverPause = 10 * time.Millisecond
|
||||
t.Cleanup(func() { bus.HandoverPause = was })
|
||||
|
||||
url := meshtest.URL(t)
|
||||
seat, err := nats.Connect(url)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer seat.Close()
|
||||
c, err := bus.Connect(bus.Credential{URL: url, Module: "console", Node: "anchor"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer c.Close()
|
||||
|
||||
serve := func(t *testing.T, verb string, answers ...map[string]any) *atomic.Int32 {
|
||||
t.Helper()
|
||||
var asked atomic.Int32
|
||||
sub, err := seat.Subscribe(bus.SeatToolSubject("mesh-controller", verb, "", ""), func(m *nats.Msg) {
|
||||
n := int(asked.Add(1)) - 1
|
||||
if n >= len(answers) {
|
||||
n = len(answers) - 1
|
||||
}
|
||||
body, _ := json.Marshal(answers[n])
|
||||
_ = m.Respond(body)
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(func() { _ = sub.Unsubscribe() })
|
||||
_ = seat.Flush()
|
||||
return &asked
|
||||
}
|
||||
handingOver := map[string]any{"error": "the controller is handing over to the next one; nothing was done, ask again",
|
||||
"retry": bus.RetryHandingOver}
|
||||
|
||||
asked := serve(t, "rotate", handingOver, map[string]any{"result": "rotated"})
|
||||
got, err := c.Ask("seat:mesh-controller.rotate", map[string]any{}, "")
|
||||
if err != nil || string(got.Result) != `"rotated"` || asked.Load() != 2 {
|
||||
t.Fatalf("after a handover refusal: %s %v, asked %d times", got.Result, err, asked.Load())
|
||||
}
|
||||
|
||||
asked = serve(t, "push", map[string]any{"error": "refused for its own reason"})
|
||||
if _, err := c.Ask("seat:mesh-controller.push", map[string]any{}, ""); err == nil || asked.Load() != 1 {
|
||||
t.Fatalf("an unmarked refusal was asked again: %v, asked %d times", err, asked.Load())
|
||||
}
|
||||
|
||||
asked = serve(t, "status", handingOver)
|
||||
_, err = c.Ask("seat:mesh-controller.status", map[string]any{}, "")
|
||||
if err == nil || asked.Load() != 2 || !strings.Contains(err.Error(), "both times refused as a handover") {
|
||||
t.Fatalf("two handover refusals: %v, asked %d times", err, asked.Load())
|
||||
}
|
||||
}
|
||||
@@ -17,7 +17,7 @@ import (
|
||||
)
|
||||
|
||||
// A module's log on the bus (novox/hq ADR 0297): a stream of operations, one subject per key, that the
|
||||
// controller creates from what the module declared under `logs` and issues to the module's own instances
|
||||
// mesh creates from what the module declared under `logs` and issues to the module's own instances
|
||||
// in its membership. It mirrors a bucket (ADR 0201) in how it is reached: what a module may reach is
|
||||
// decided here, from its membership, and refused with the reason before anything is sent.
|
||||
//
|
||||
@@ -139,7 +139,7 @@ func (c *Conn) issuedLog(module, name string) (LogIssued, error) {
|
||||
|
||||
// notOnTheBus says a log is issued and its stream is not there yet.
|
||||
func notOnTheBus(l LogIssued) error {
|
||||
return fmt.Errorf("the log %q is issued and its stream %s is not on the bus yet: the controller creates "+
|
||||
return fmt.Errorf("the log %q is issued and its stream %s is not on the bus yet: the mesh creates "+
|
||||
"it from the catalogue on its next raise (novox/hq ADR 0297)", l.Name, l.Stream)
|
||||
}
|
||||
|
||||
|
||||
@@ -1,13 +1,7 @@
|
||||
package bus
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/nats-io/nats.go"
|
||||
|
||||
"github.com/novox/mesh-tools/node-tools/internal/wire"
|
||||
)
|
||||
@@ -15,97 +9,8 @@ import (
|
||||
// An answer larger than the bus carries in one message (novox/hq issue 314).
|
||||
//
|
||||
// The bus carries one message of at most its max_payload, and the client library refuses a larger one
|
||||
// before it leaves the process that sent it. Until this, a holder whose answer was too large wrote one
|
||||
// line to its own log and its caller waited out RequestTimeout and read "did not answer" — the
|
||||
// controller's `conditions` and `status` for hours on 2026-10-08, and the operator's channel with them.
|
||||
//
|
||||
// The controller pages such an answer (mesh-controller internal/link, pages.go): it answers an error
|
||||
// carrying `paged` — the call it holds the answer under, its size and its parts — and a caller asks the
|
||||
// same subject again once per part with PageHeader, each part answered raw with PartHeader. Asking the
|
||||
// same subject means no grant beyond the one the caller already had. A module's answer too large is
|
||||
// refused here, loudly, in a message that fits: its instances may be several, and a part asked again
|
||||
// could reach another.
|
||||
|
||||
const (
|
||||
// PageHeader asks for one part of a paged answer: `<call> <part>`, from zero.
|
||||
PageHeader = "Mesh-Page"
|
||||
// PartHeader is on a part: `<part>/<parts>`.
|
||||
PartHeader = "Mesh-Part"
|
||||
// partTries is how often one part is asked: during a handover a part can reach the controller that
|
||||
// did not hold it.
|
||||
partTries = 3
|
||||
)
|
||||
|
||||
// PartTimeout bounds the asking of one part.
|
||||
var PartTimeout = 10 * time.Second
|
||||
|
||||
// paged is what a too-large answer says instead of itself.
|
||||
type paged struct {
|
||||
Call string `json:"call"`
|
||||
Bytes int `json:"bytes"`
|
||||
Parts int `json:"parts"`
|
||||
}
|
||||
|
||||
func pagedIn(data []byte) (paged, bool) {
|
||||
if !bytes.Contains(data, []byte(`"paged"`)) {
|
||||
return paged{}, false
|
||||
}
|
||||
var r struct {
|
||||
Paged *paged `json:"paged"`
|
||||
}
|
||||
if json.Unmarshal(data, &r) != nil || r.Paged == nil || r.Paged.Call == "" || r.Paged.Parts < 1 {
|
||||
return paged{}, false
|
||||
}
|
||||
return *r.Paged, true
|
||||
}
|
||||
|
||||
// whole is a reply's whole answer: the reply itself, or every part of a paged one, joined. A part that
|
||||
// cannot be had is an error naming it, never a shorter answer.
|
||||
func (c *Conn) whole(subject string, data []byte) ([]byte, error) {
|
||||
p, ok := pagedIn(data)
|
||||
if !ok {
|
||||
return data, nil
|
||||
}
|
||||
out := make([]byte, 0, p.Bytes)
|
||||
for n := 0; n < p.Parts; n++ {
|
||||
var part []byte
|
||||
var err error
|
||||
for try := 0; try < partTries; try++ {
|
||||
if part, err = c.askPart(subject, p, n); err == nil {
|
||||
break
|
||||
}
|
||||
}
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("the answer was %d bytes, more than the bus carries in one message, paged as %s "+
|
||||
"in %d parts, and part %d could not be had: %w", p.Bytes, p.Call, p.Parts, n, err)
|
||||
}
|
||||
out = append(out, part...)
|
||||
}
|
||||
if len(out) != p.Bytes {
|
||||
return nil, fmt.Errorf("the answer paged as %s was %d bytes, and its parts joined are %d", p.Call, p.Bytes, len(out))
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func (c *Conn) askPart(subject string, p paged, n int) ([]byte, error) {
|
||||
ask := nats.NewMsg(subject)
|
||||
ask.Header.Set(PageHeader, fmt.Sprintf("%s %d", p.Call, n))
|
||||
ask.Data = []byte(`{}`)
|
||||
reply, err := c.nc.RequestMsg(ask, PartTimeout)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if got := reply.Header.Get(PartHeader); got != fmt.Sprintf("%d/%d", n, p.Parts) {
|
||||
var r struct {
|
||||
Error string `json:"error"`
|
||||
}
|
||||
if json.Unmarshal(reply.Data, &r) == nil && r.Error != "" {
|
||||
return nil, errors.New(r.Error)
|
||||
}
|
||||
return nil, fmt.Errorf("asked part %d/%d, answered %q", n, p.Parts, got)
|
||||
}
|
||||
return reply.Data, nil
|
||||
}
|
||||
// before it leaves the process that sent it. A module's answer too large is refused here, loudly, in a
|
||||
// message that fits, so its caller reads why instead of waiting out RequestTimeout.
|
||||
|
||||
// fits is an answer the bus can carry: the answer itself, or — when it is larger than one message —
|
||||
// an error that says so, which is.
|
||||
|
||||
@@ -2,7 +2,6 @@ package bus_test
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
@@ -13,8 +12,8 @@ import (
|
||||
"github.com/novox/mesh-tools/node-tools/internal/meshtest"
|
||||
)
|
||||
|
||||
// novox/hq issue 314: an answer larger than the bus carries in one message arrives whole when the
|
||||
// controller pages it, and a module's is said to be too large — neither is a 30-second silence.
|
||||
// novox/hq issue 314: a module's answer larger than the bus carries in one message is said to be too large,
|
||||
// at once, not a 30-second silence. (The controller's paging ended with the controller, issue 1126.)
|
||||
func TestAnAnswerLargerThanOneMessage(t *testing.T) {
|
||||
url := meshtest.URL(t)
|
||||
seat, err := nats.Connect(url)
|
||||
@@ -27,43 +26,8 @@ func TestAnAnswerLargerThanOneMessage(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer c.Close()
|
||||
limit := int(seat.MaxPayload())
|
||||
large := strings.Repeat("a condition held past its bound; ", 3*int(seat.MaxPayload())/32)
|
||||
|
||||
// The controller as it pages (mesh-controller internal/link, pages.go): the first answer an error
|
||||
// with `paged`, each part asked again on the same subject with the page header.
|
||||
large := strings.Repeat("a condition held past its bound; ", 3*limit/32)
|
||||
whole, _ := json.Marshal(map[string]any{"result": large})
|
||||
partSize := limit - 1024
|
||||
parts := (len(whole) + partSize - 1) / partSize
|
||||
sub, err := seat.Subscribe(bus.SeatToolSubject("mesh-controller", "conditions", "", ""), func(m *nats.Msg) {
|
||||
if page := m.Header.Get(bus.PageHeader); page != "" {
|
||||
var id string
|
||||
var n int
|
||||
fmt.Sscanf(page, "%s %d", &id, &n)
|
||||
end := min((n+1)*partSize, len(whole))
|
||||
part := nats.NewMsg(m.Reply)
|
||||
part.Header.Set(bus.PartHeader, fmt.Sprintf("%d/%d", n, parts))
|
||||
part.Data = whole[n*partSize : end]
|
||||
_ = m.RespondMsg(part)
|
||||
return
|
||||
}
|
||||
body, _ := json.Marshal(map[string]any{"error": "too large for one message",
|
||||
"paged": map[string]any{"call": "call-1-1", "bytes": len(whole), "parts": parts}})
|
||||
_ = m.Respond(body)
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer sub.Unsubscribe()
|
||||
_ = seat.Flush()
|
||||
|
||||
got, err := c.Ask("seat:mesh-controller.conditions", map[string]any{}, "")
|
||||
var said string
|
||||
if err != nil || json.Unmarshal(got.Result, &said) != nil || said != large {
|
||||
t.Fatalf("an answer of %d bytes in %d parts arrived as %d bytes: %v", len(whole), parts, len(got.Result), err)
|
||||
}
|
||||
|
||||
// A module's answer too large is refused here in words, at once.
|
||||
stop, err := c.HandleSubject("mesh.mod.journal.tool.lines", func(json.RawMessage) (any, error) { return large, nil })
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
|
||||
@@ -14,16 +14,16 @@ import (
|
||||
// ADR 0370 changes it, issue 685).
|
||||
//
|
||||
// While a module's code runs here, its asks reach the bus under this runtime's account, and the bus proves only
|
||||
// that account. So the runtime asks its own machine's client on ProvisionAskSubject — which the controller grants
|
||||
// that account. So the runtime asks its own machine's client on ProvisionAskSubject — which the mesh grants
|
||||
// this machine's tool runner alone to publish (ADR 0370 §3) — naming the module itself, from the bundle that asks
|
||||
// and never from the module's code or arguments (§4). The client answers that module's config values, for what its
|
||||
// manifest declares, and no secret: the vault hands a secret only to a caller the bus proves (§2).
|
||||
|
||||
// ProvisionAskSubject is where this machine's tool runner asks its provisioner client (mesh-controller
|
||||
// ProvisionAskSubject is where this machine's tool runner asks its provisioner client (the node-engine
|
||||
// internal/broker ProvisionerAskSubject): `prov.ask.<node>`.
|
||||
func ProvisionAskSubject(node string) string { return "prov.ask." + node }
|
||||
|
||||
// ProvisionChangedSubjects is every module's word of what moved on a machine (mesh-controller internal/broker
|
||||
// ProvisionChangedSubjects is every module's word of what moved on a machine (the node-engine
|
||||
// ProvisionerChangedSubject): `prov.changed.<node>.<module>`, a module's name dots and all.
|
||||
func ProvisionChangedSubjects(node string) string { return "prov.changed." + node + ".>" }
|
||||
|
||||
|
||||
@@ -24,7 +24,7 @@ import (
|
||||
// and anything else is refused here, with the reason, before it is sent. A bundle reaches this only through
|
||||
// its own standard input and output: no tool call does.
|
||||
|
||||
// SeatTraffic is what a membership lists of a module's seat traffic (the controller's broker.SeatTraffic).
|
||||
// SeatTraffic is what a membership lists of a module's seat traffic (the grants part's record).
|
||||
type SeatTraffic struct {
|
||||
Publish []string `json:"publish,omitempty"`
|
||||
Subscribe []string `json:"subscribe,omitempty"`
|
||||
@@ -32,7 +32,7 @@ type SeatTraffic struct {
|
||||
Workers []SeatWorker `json:"workers,omitempty"`
|
||||
Records []string `json:"records,omitempty"`
|
||||
// Kinds are the holders of every kinded bench the module uses or watches, with what each promises: the
|
||||
// controller's record of their claims (novox/hq ADR 0259 §5).
|
||||
// record of their claims (novox/hq ADR 0259 §5).
|
||||
Kinds []KindHeld `json:"kinds,omitempty"`
|
||||
}
|
||||
|
||||
@@ -45,7 +45,7 @@ type KindHeld struct {
|
||||
Capabilities []string `json:"capabilities,omitempty"`
|
||||
}
|
||||
|
||||
// SeatKinds is the kinds the module's membership names, as the controller issued them.
|
||||
// SeatKinds is the kinds the module's membership names, as the grants part issued them.
|
||||
func (c *Conn) SeatKinds(module string) ([]KindHeld, error) {
|
||||
t, err := c.trafficOf(module)
|
||||
if err != nil {
|
||||
@@ -249,7 +249,7 @@ type Work struct {
|
||||
|
||||
// SeatTake reads a worker the module's seat traffic lists and hands each message to deliver: acknowledged
|
||||
// when deliver returns nil, offered again after NakDelay when it returns an error, ended when it is not
|
||||
// JSON. The worker is the controller's to create; this binds to it by name and never makes one.
|
||||
// JSON. The worker is the mesh's to create; this binds to it by name and never makes one.
|
||||
func (c *Conn) SeatTake(module, consumer string, deliver func(Work) error) (func(), error) {
|
||||
t, err := c.trafficOf(module)
|
||||
if err != nil {
|
||||
|
||||
@@ -98,7 +98,7 @@ func TestAModuleSubmitsAndSaysOnlyUnderItsOwnNameAndKind(t *testing.T) {
|
||||
t.Fatalf("an asker could not ask under its own name: %v", err)
|
||||
}
|
||||
for module, subject := range map[string]string{
|
||||
"mesh-delivery": "mesh.seat.operator-channel.accept.ask.mesh-controller",
|
||||
"mesh-delivery": "mesh.seat.operator-channel.accept.ask.mesh-placement",
|
||||
"telegram": "mesh.seat.intake.event.choice.desktop",
|
||||
"messenger": "mesh.seat.intake.event.choice.telegram",
|
||||
} {
|
||||
@@ -206,7 +206,7 @@ func TestAnAskerReadsItsOwnRecordAndNoOther(t *testing.T) {
|
||||
if _, err := kv.Put("mesh-delivery.a1", []byte(`{"state":"open"}`)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := kv.Put("mesh-controller.a1", []byte(`{"state":"open"}`)); err != nil {
|
||||
if _, err := kv.Put("mesh-placement.a1", []byte(`{"state":"open"}`)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
got, err := conn.SeatRecord("mesh-delivery", "messenger_asks", "a1")
|
||||
|
||||
@@ -14,7 +14,7 @@ import (
|
||||
"github.com/nats-io/nats.go/jetstream"
|
||||
)
|
||||
|
||||
// A module's state on the bus (novox/hq ADR 0201): key-value buckets the controller creates from what
|
||||
// A module's state on the bus (novox/hq ADR 0201): key-value buckets the mesh creates from what
|
||||
// the module declared, and issues to each assignment in its membership by the name the module uses —
|
||||
// its own state by the local name, another module's as `<module>.<name>`.
|
||||
//
|
||||
@@ -89,7 +89,7 @@ func (c *Conn) bucket(ctx context.Context, s StateIssued) (jetstream.KeyValue, e
|
||||
kv, err := js.KeyValue(ctx, s.Bucket)
|
||||
if err != nil {
|
||||
if errors.Is(err, jetstream.ErrBucketNotFound) {
|
||||
return nil, fmt.Errorf("the state %q is issued and its bucket is not on the bus yet: the controller "+
|
||||
return nil, fmt.Errorf("the state %q is issued and its bucket is not on the bus yet: the mesh "+
|
||||
"creates it from the catalogue on its next raise", s.Name)
|
||||
}
|
||||
return nil, err
|
||||
|
||||
@@ -33,7 +33,7 @@ func TestAWatchHoldsWhileItsCurrentValuesKeepArriving(t *testing.T) {
|
||||
for i := 0; i < older; i++ {
|
||||
keys = append(keys, fmt.Sprintf("novox/mesh-catalog.%d.%040x.status=mesh/check", 400+i, i))
|
||||
}
|
||||
for _, member := range []string{"novox/mesh-sdk.76.34f210e5", "novox/mesh-controller.453.c06f75d0", "novox/mesh-delivery.33.28ee22ef"} {
|
||||
for _, member := range []string{"novox/mesh-sdk.76.34f210e5", "novox/mesh-placement.453.c06f75d0", "novox/mesh-delivery.33.28ee22ef"} {
|
||||
keys = append(keys, member+strings.Repeat("0", 32)+".status=mesh/check")
|
||||
}
|
||||
for _, k := range keys {
|
||||
|
||||
@@ -14,7 +14,7 @@ import (
|
||||
|
||||
// A module's own stream, as the runtime publishes to it and hears it (novox/hq ADR 0363 §8, issue 725).
|
||||
//
|
||||
// A module may declare a stream of its own; the controller creates it and says, in the module's
|
||||
// A module may declare a stream of its own; the mesh creates it and says, in the module's
|
||||
// membership, which of its events go there and on which subject (`streams`), and, in the membership of
|
||||
// each module granted to hear it, which durable consumer on it to bind (`hears`). The runtime publishes and
|
||||
// binds exactly as the membership says. A membership naming neither is what every membership was before:
|
||||
@@ -30,7 +30,7 @@ type StreamIssued struct {
|
||||
}
|
||||
|
||||
// HeardIssued is one module stream an assignment hears: the stream and the durable consumer on it the
|
||||
// runtime binds. The consumer is the controller's to make, to filter and to delete.
|
||||
// runtime binds. The consumer is the mesh's to make, to filter and to delete.
|
||||
type HeardIssued struct {
|
||||
Stream string `json:"stream"`
|
||||
Consumer string `json:"consumer"`
|
||||
@@ -73,7 +73,7 @@ func eventMatches(pattern, event string) bool {
|
||||
}
|
||||
|
||||
// RebindEvery is how often a consumer the membership names and the bus did not let the runtime bind is
|
||||
// tried again: the controller makes the consumer and sends the user list carrying its grant in the
|
||||
// tried again: the mesh makes the consumer and sends the user list carrying its grant in the
|
||||
// composition that issues the membership, so one may arrive before the other (ADR 0363 §6).
|
||||
var RebindEvery = 30 * time.Second
|
||||
|
||||
@@ -294,7 +294,7 @@ func (h *hearing) reconcile() {
|
||||
}
|
||||
}
|
||||
// **A loop the bus ended is no longer reading** (nats.go ends a pull loop on its own when its consumer is
|
||||
// deleted): the controller deletes and makes again under the same name a restricted consumer it cannot
|
||||
// deleted): the mesh deletes and makes again under the same name a restricted consumer it cannot
|
||||
// narrow (ADR 0363 §6), and the membership, unchanged, says nothing — so it is bound again here.
|
||||
// **A loop the bus did not end is asked about**: nats.go learns of a deleted consumer only from the answer
|
||||
// to a pull it has pending, and a consumer deleted and made again between two pulls, or while none is
|
||||
|
||||
@@ -50,7 +50,7 @@ const (
|
||||
// searchCap is how many matches a search answers before it says how many more there were.
|
||||
const searchCap = 25
|
||||
|
||||
const grammar = "Addresses: `<seat>.<verb>` for a seat held once for the mesh (e.g. `mesh-controller.nodes`); " +
|
||||
const grammar = "Addresses: `<seat>.<verb>` for a seat held once for the mesh (e.g. `mesh-placement.placement`); " +
|
||||
"`<node>/<seat>.<verb>` for a seat every machine holds (e.g. `ace/node-packet-filter.rules`); " +
|
||||
"`<node>/<module>.<tool>` for a module on one machine (e.g. `novox/postgres.postgres_list_databases`); " +
|
||||
"and `<module>.<tool>` also for a module whose instances are interchangeable."
|
||||
@@ -242,7 +242,7 @@ type recordedModule struct {
|
||||
}
|
||||
|
||||
// indexOn asks the mesh what it holds (novox/hq ADR 0197): what answers, from every runtime's own
|
||||
// announcement on the bus — one `$SRV.INFO` request — and what should, from the controller's records
|
||||
// announcement on the bus — one `$SRV.INFO` request — and what should, from the indexer's records
|
||||
// read as JSON. Nothing is inferred from a roster and nothing is parsed from print.
|
||||
//
|
||||
// `held` is what the console holds already, so an instance whose announcement is unchanged is not
|
||||
@@ -257,9 +257,9 @@ func indexOn(conn *bus.Conn, held announce.Known, before func(announce.Discovery
|
||||
var recordsWhy []string
|
||||
wg.Add(2)
|
||||
// Which modules there are and where they are placed, and which machines the mesh has, from the bus (ADR 0571
|
||||
// clauses 4 and 5): the indexer's modules and manifests and the placement seat's placements, never the controller.
|
||||
// clauses 4 and 5): the indexer's modules and manifests and the placement seat's placements, never any other record.
|
||||
go func() { defer wg.Done(); recorded, known, recordsWhy = recordsOn(conn) }()
|
||||
// Who holds which seat on which node, from placement (ADR 0571 clause 4): no call of the controller.
|
||||
// Who holds which seat on which node, from placement (ADR 0571 clause 4): no other call.
|
||||
go func() { defer wg.Done(); placed, placedErr = seatHoldersOn(conn) }()
|
||||
d, err := announce.Gather(conn, held)
|
||||
wg.Wait()
|
||||
@@ -815,7 +815,7 @@ func firstLine(s string) string {
|
||||
// the machine, `node` is taken out: the machine is in the address. Where it does not — a seat held
|
||||
// once for the mesh, or an interchangeable module — `node` is the tool's own argument, and is kept.
|
||||
//
|
||||
// **Taking it out everywhere made the mesh's own verbs lie** (novox/hq issue 244): the controller's
|
||||
// **Taking it out everywhere made the mesh's own verbs lie** (novox/hq issue 244): the old controller verbs
|
||||
// `push`, `plan`, `assign`, `pin` and `settings` take the machine they act on as `node`, and were
|
||||
// described without it — `push` as taking nothing at all, so a push naming one machine arrived as a
|
||||
// push of every machine behind.
|
||||
|
||||
@@ -71,9 +71,9 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
}
|
||||
|
||||
// The controller: its own seat's verbs announced on the bus like every runtime's; its records are asked by no one.
|
||||
controller := connect(t, "mesh-controller", "bench")
|
||||
controller := connect(t, "mesh-placement", "bench")
|
||||
// Its verb nodes, called through the console as any seat's verb is.
|
||||
stopNodes, err := controller.HandleSubject("mesh.seat.mesh-controller.tool.nodes", func(json.RawMessage) (any, error) {
|
||||
stopNodes, err := controller.HandleSubject("mesh.seat.mesh-placement.tool.nodes", func(json.RawMessage) (any, error) {
|
||||
return map[string]any{"ok": true, "output": `[{"name":"bench","mode":"converged"},{"name":"desk","mode":"converged"}]`}, nil
|
||||
})
|
||||
if err != nil {
|
||||
@@ -82,8 +82,8 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
t.Cleanup(stopNodes)
|
||||
// What the mesh holds, as the indexer and placement write it (ADR 0571 clauses 4, 5): never the controller's records.
|
||||
tools := map[string][]string{"alpha": {"one", "two"}, "beta": {"three"}, "gamma": {"given"}, "delta": nil,
|
||||
"epsilon": {"seven"}, "mesh-controller": {"nodes"}}
|
||||
mesh.Placed(t, tools, map[string][]string{"desk": {"alpha", "beta", "delta"}, "bench": {"epsilon", "mesh-controller"}})
|
||||
"epsilon": {"seven"}, "mesh-placement": {"nodes"}}
|
||||
mesh.Placed(t, tools, map[string][]string{"desk": {"alpha", "beta", "delta"}, "bench": {"epsilon", "mesh-placement"}})
|
||||
console := mt.MembershipOf("node-tools", "desk", false, nil)
|
||||
console.State = mt.ConsoleReads()
|
||||
mesh.Issue(t, console)
|
||||
@@ -93,11 +93,11 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
}
|
||||
return nil
|
||||
})
|
||||
stopAnn, err := announce.Serve(controller, announce.Service{Name: "mesh-controller", ID: "bench"}, func() []announce.Endpoint {
|
||||
return []announce.Endpoint{{Kind: announce.KindSeat, Module: "mesh-controller", Seat: "mesh-controller", Scope: "mesh",
|
||||
stopAnn, err := announce.Serve(controller, announce.Service{Name: "mesh-placement", ID: "bench"}, func() []announce.Endpoint {
|
||||
return []announce.Endpoint{{Kind: announce.KindSeat, Module: "mesh-placement", Seat: "mesh-placement", Scope: "mesh",
|
||||
// As the live controller announces: a mesh seat's holder names no machine.
|
||||
Tool: "nodes", Node: "", Description: "Every machine the mesh knows.", Schema: json.RawMessage(`{}`),
|
||||
Subject: "mesh.seat.mesh-controller.tool.nodes"}}
|
||||
Subject: "mesh.seat.mesh-placement.tool.nodes"}}
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -131,13 +131,13 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
|
||||
// The overview names the mesh's seats, the machines' seats and the machines.
|
||||
overview, isErr := call(t, endpoint, "mesh_overview", nil)
|
||||
if isErr || !strings.Contains(overview, "mesh-controller.nodes") || !strings.Contains(overview, "<node>/node-shelf.list") ||
|
||||
if isErr || !strings.Contains(overview, "mesh-placement.nodes") || !strings.Contains(overview, "<node>/node-shelf.list") ||
|
||||
!strings.Contains(overview, `"bench"`) || !strings.Contains(overview, `"desk"`) {
|
||||
t.Errorf("overview: %s", overview)
|
||||
}
|
||||
// Silence is named only where tools should have answered: epsilon declares tools on bench and
|
||||
// nothing there announced it; delta declares none and is never a name.
|
||||
if strings.Contains(overview, "mesh-controller on bench") {
|
||||
if strings.Contains(overview, "mesh-placement on bench") {
|
||||
t.Errorf("a mesh seat's holder that announced no machine is called silent on its machine:\n%s", overview)
|
||||
}
|
||||
if !strings.Contains(overview, "epsilon on bench") || strings.Contains(overview, "delta") {
|
||||
@@ -150,7 +150,7 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
}
|
||||
|
||||
// A mesh seat, a node seat, an assignment and an interchangeable module, each by address.
|
||||
if got, isErr := call(t, endpoint, "mesh_call", map[string]any{"address": "mesh-controller.nodes"}); isErr || !strings.Contains(got, "converged") {
|
||||
if got, isErr := call(t, endpoint, "mesh_call", map[string]any{"address": "mesh-placement.nodes"}); isErr || !strings.Contains(got, "converged") {
|
||||
t.Errorf("mesh seat: %s", got)
|
||||
}
|
||||
if got, isErr := call(t, endpoint, "mesh_call", map[string]any{"address": "desk/node-shelf.list"}); isErr || !strings.Contains(got, `"a"`) {
|
||||
@@ -166,11 +166,11 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
|
||||
// Refused, by name, where the address does not say enough or says the wrong thing.
|
||||
for address, want := range map[string]string{
|
||||
"beta.three": "keeps state on each machine it runs on, so a call names the machine: write <node>/beta.three — it runs on desk",
|
||||
"node-shelf.list": "held once per machine: write <node>/node-shelf.list — it is held on desk",
|
||||
"desk/mesh-controller.nodes": "held once for the whole mesh",
|
||||
"bench/beta.three": "beta does not run on bench; it runs on desk",
|
||||
"nonsense": "is not an address",
|
||||
"beta.three": "keeps state on each machine it runs on, so a call names the machine: write <node>/beta.three — it runs on desk",
|
||||
"node-shelf.list": "held once per machine: write <node>/node-shelf.list — it is held on desk",
|
||||
"desk/mesh-placement.nodes": "held once for the whole mesh",
|
||||
"bench/beta.three": "beta does not run on bench; it runs on desk",
|
||||
"nonsense": "is not an address",
|
||||
} {
|
||||
got, isErr := call(t, endpoint, "mesh_call", map[string]any{"address": address})
|
||||
if !isErr || !strings.Contains(got, want) {
|
||||
@@ -201,7 +201,7 @@ func TestTheMeshsToolsAreFoundByAddress(t *testing.T) {
|
||||
t.Fatalf("gamma was found before it served: %s", got)
|
||||
}
|
||||
mesh.Issue(t, mt.MembershipOf("gamma", "desk", false, nil))
|
||||
mesh.Placed(t, tools, map[string][]string{"desk": {"alpha", "beta", "delta", "gamma"}, "bench": {"epsilon", "mesh-controller"}})
|
||||
mesh.Placed(t, tools, map[string][]string{"desk": {"alpha", "beta", "delta", "gamma"}, "bench": {"epsilon", "mesh-placement"}})
|
||||
late := connect(t, "node-tools", "desk")
|
||||
stopLate, err := runtime.Run(late, []runtime.Served{{Module: "gamma", Entrypoints: []string{mt.Fixture("env-gamma.serve.mjs")}}},
|
||||
nil, (&mt.Logs{}).Logf)
|
||||
|
||||
@@ -118,9 +118,6 @@ var (
|
||||
timedOut = regexp.MustCompile(`(?i)timeout`)
|
||||
)
|
||||
|
||||
// controllerSeat is the seat whose holder keeps what came of every call (novox/hq issue 265).
|
||||
const controllerSeat = "mesh-controller"
|
||||
|
||||
// whyItFailed says why a call failed, so the remedy is in the words.
|
||||
func whyItFailed(key string, err error) string {
|
||||
if err == nil {
|
||||
@@ -145,12 +142,6 @@ func whyItFailed(key string, err error) string {
|
||||
said := key + " did not answer within " + bus.RequestTimeout.String() + ". That is not a failure: " +
|
||||
"something is serving it, so it may still be running and may already have done what was " +
|
||||
"asked — check before repeating a call that changes the mesh."
|
||||
if strings.HasPrefix(strings.TrimPrefix(key, "seat:"), controllerSeat+".") {
|
||||
// The controller answers every call within seconds, with an id while it runs, so silence
|
||||
// from it is an answer lost on the way — which it keeps.
|
||||
said += " The controller answers every call within seconds, so its answer was lost on the " +
|
||||
"way; " + controllerSeat + ".calls lists its recent calls and what came of each."
|
||||
}
|
||||
return said
|
||||
}
|
||||
return key + " failed: " + msg
|
||||
|
||||
@@ -63,7 +63,7 @@ type Surface struct {
|
||||
}
|
||||
|
||||
// MethodSeats is the console's JSON-RPC method beside MCP's that answers every seat's verbs and holders, in the shape
|
||||
// the controller's `tools` answered: `{seats: [{seat, scope, tools: [{name, description, input, replaces}], holders:
|
||||
// the old `tools` answered: `{seats: [{seat, scope, tools: [{name, description, input, replaces}], holders:
|
||||
// [{module, node}]}], holders_why}`.
|
||||
const MethodSeats = "mesh/seats"
|
||||
|
||||
@@ -157,7 +157,7 @@ func (s *Surface) HandleContext(ctx context.Context, r Request) *Reply {
|
||||
return answer(r.ID, map[string]any{})
|
||||
case MethodSeats:
|
||||
// The seats' contract and who holds each, for a client on this machine that has no seat definitions of its own
|
||||
// (the TypeScript `mesh`): read in-process from mesh-sdk and from placement, never asked of the controller
|
||||
// (the TypeScript `mesh`): read in-process from mesh-sdk and from placement, never asked of anything else
|
||||
// (novox/hq ADR 0571 clauses 4 and 5).
|
||||
return answer(r.ID, s.seatsAnswer())
|
||||
case "tools/list":
|
||||
@@ -338,7 +338,7 @@ func (s *Surface) instructions() string {
|
||||
"that serves it; what may be called was fixed when this account was issued, so a " +
|
||||
"refusal means the account, not the tool. The list is what the running modules " +
|
||||
"answered, plus every role's tools from the mesh's records — the mesh's own verbs " +
|
||||
"(mesh-controller.status, .push, .assign …) among them; a module that did not answer " +
|
||||
"(mesh-delivery.deliveries, mesh-placement.propose …) among them; a module that did not answer " +
|
||||
"is named in the list's _meta and can still be called by <module>.<tool>."
|
||||
}
|
||||
return "The tools of a Novox mesh, reached as " + s.who + ", found by address rather than listed " +
|
||||
|
||||
@@ -11,9 +11,9 @@ import (
|
||||
// 2026-10-05 the controller's push was described as taking nothing, and a push naming one machine
|
||||
// ran as a push of every machine behind.
|
||||
func TestAMeshSeatsNodeIsItsOwnArgument(t *testing.T) {
|
||||
push := Tool{Module: "mesh-controller", Name: "push", Seat: true, Scope: "mesh",
|
||||
push := Tool{Module: "mesh-placement", Name: "push", Seat: true, Scope: "mesh",
|
||||
Input: json.RawMessage(`{"type":"object","properties":{"node":{"type":"string"},"behind":{"type":"string"}}}`)}
|
||||
mesh := target{Address: "mesh-controller.push", Tool: push, Seat: true}
|
||||
mesh := target{Address: "mesh-placement.push", Tool: push, Seat: true}
|
||||
|
||||
props := schemaAsPassed(mesh)["properties"].(map[string]any)
|
||||
if _, has := props["node"]; !has {
|
||||
|
||||
@@ -22,16 +22,23 @@ func TestARefusalIsSaidOnlyForTheBussOwn(t *testing.T) {
|
||||
}
|
||||
|
||||
// **A timeout says it is not a failure** (novox/hq issue 265): a push that outlasted the wait had
|
||||
// pushed, and the caller read "did not answer in time". And from the controller, where its answer is.
|
||||
// pushed, and the caller read "did not answer in time". No hint names a seat that is gone (novox/hq issue 1126):
|
||||
// the grammar's example, the handshake's instructions and a timeout's remedy named the controller's verbs.
|
||||
func TestATimeoutIsNotAFailure(t *testing.T) {
|
||||
got := whyItFailed("seat:mesh-controller.push", errors.New("timeout"))
|
||||
for _, want := range []string{"not a failure", "may already have done", "mesh-controller.calls"} {
|
||||
got := whyItFailed("seat:mesh-delivery.deliveries", errors.New("timeout"))
|
||||
for _, want := range []string{"not a failure", "may already have done"} {
|
||||
if !strings.Contains(got, want) {
|
||||
t.Errorf("a controller timeout does not say %q: %s", want, got)
|
||||
t.Errorf("a seat's timeout does not say %q: %s", want, got)
|
||||
}
|
||||
}
|
||||
if other := whyItFailed("novox/postgres.postgres_list_databases", errors.New("timeout")); !strings.Contains(other, "not a failure") ||
|
||||
strings.Contains(other, "calls") {
|
||||
t.Errorf("a module's timeout: %s", other)
|
||||
for name, text := range map[string]string{
|
||||
"grammar": grammar,
|
||||
"flat instructions": (&Surface{Flat: true, who: "x"}).instructions(),
|
||||
"deep instructions": (&Surface{who: "x"}).instructions(),
|
||||
"timeout": got,
|
||||
} {
|
||||
if strings.Contains(text, "controller") {
|
||||
t.Errorf("%s names the controller: %s", name, text)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -95,7 +95,7 @@ func TestARuntimeThatAnswersLateIsFoundAndOneThatNeverDoesIsNamed(t *testing.T)
|
||||
Subject: "mesh.mod.nextcloud-client.tool.nextcloud_check.desktop"},
|
||||
})
|
||||
|
||||
controller := connect(t, "mesh-controller", "bench")
|
||||
controller := connect(t, "mesh-placement", "bench")
|
||||
var toolsAsked atomic.Int32
|
||||
for verb, output := range map[string]string{
|
||||
// The controller's records are served here only to see that none is asked (ADR 0571 clauses 4 and 5).
|
||||
@@ -104,7 +104,7 @@ func TestARuntimeThatAnswersLateIsFoundAndOneThatNeverDoesIsNamed(t *testing.T)
|
||||
"tools": `{"seats":[]}`,
|
||||
} {
|
||||
output, verb := output, verb
|
||||
stop, err := controller.HandleSubject("mesh.seat.mesh-controller.tool."+verb, func(json.RawMessage) (any, error) {
|
||||
stop, err := controller.HandleSubject("mesh.seat.mesh-placement.tool."+verb, func(json.RawMessage) (any, error) {
|
||||
toolsAsked.Add(1)
|
||||
return map[string]any{"output": output, "ok": true}, nil
|
||||
})
|
||||
|
||||
@@ -33,8 +33,8 @@ func meshToSearch(t *testing.T) *index {
|
||||
"node": "What one machine reported it can do, what it is assigned, and why.",
|
||||
"nodes": "Every machine the mesh knows, with whether it is converged or adopted.",
|
||||
} {
|
||||
endpoints = append(endpoints, announce.Endpoint{Kind: announce.KindSeat, Module: "mesh-controller", Seat: "mesh-controller",
|
||||
Tool: verb, Scope: "mesh", Description: does, Subject: "mesh.seat.mesh-controller.tool." + verb})
|
||||
endpoints = append(endpoints, announce.Endpoint{Kind: announce.KindSeat, Module: "mesh-placement", Seat: "mesh-placement",
|
||||
Tool: verb, Scope: "mesh", Description: does, Subject: "mesh.seat.mesh-placement.tool." + verb})
|
||||
}
|
||||
for tool, does := range map[string]string{
|
||||
"docker_list": "Every container on this machine: name, image, state, ports.",
|
||||
@@ -56,22 +56,21 @@ func meshToSearch(t *testing.T) *index {
|
||||
func TestSearchFindsTheToolThatReplacesACommandFirst(t *testing.T) {
|
||||
x := meshToSearch(t)
|
||||
for query, want := range map[string]string{
|
||||
"journalctl": "anchor/node-service-manager.journal",
|
||||
"journalctl -u mesh-controller -n 50": "anchor/node-service-manager.journal",
|
||||
"sudo journalctl -fu sshd": "anchor/node-service-manager.journal",
|
||||
"/usr/bin/journalctl": "anchor/node-service-manager.journal",
|
||||
"logs": "anchor/node-service-manager.journal",
|
||||
"systemctl status": "anchor/node-service-manager.status",
|
||||
"systemctl status nats.service": "anchor/node-service-manager.status",
|
||||
"systemctl restart mesh-controller": "anchor/node-service-manager.restart",
|
||||
"systemctl --failed": "anchor/node-service-manager.failed",
|
||||
"docker ps": "anchor/docker.docker_list",
|
||||
"docker ps -a": "anchor/docker.docker_list",
|
||||
"docker logs": "anchor/docker.docker_logs",
|
||||
"docker logs --tail 100 nats": "anchor/docker.docker_logs",
|
||||
"docker restart nats": "anchor/docker.docker_restart",
|
||||
"container logs": "anchor/docker.docker_logs",
|
||||
"uptime": "mesh-controller.node",
|
||||
"journalctl": "anchor/node-service-manager.journal",
|
||||
"journalctl -u mesh-placement -n 50": "anchor/node-service-manager.journal",
|
||||
"sudo journalctl -fu sshd": "anchor/node-service-manager.journal",
|
||||
"/usr/bin/journalctl": "anchor/node-service-manager.journal",
|
||||
"logs": "anchor/node-service-manager.journal",
|
||||
"systemctl status": "anchor/node-service-manager.status",
|
||||
"systemctl status nats.service": "anchor/node-service-manager.status",
|
||||
"systemctl restart mesh-placement": "anchor/node-service-manager.restart",
|
||||
"systemctl --failed": "anchor/node-service-manager.failed",
|
||||
"docker ps": "anchor/docker.docker_list",
|
||||
"docker ps -a": "anchor/docker.docker_list",
|
||||
"docker logs": "anchor/docker.docker_logs",
|
||||
"docker logs --tail 100 nats": "anchor/docker.docker_logs",
|
||||
"docker restart nats": "anchor/docker.docker_restart",
|
||||
"container logs": "anchor/docker.docker_logs",
|
||||
} {
|
||||
hits := x.search(query)
|
||||
if len(hits) == 0 {
|
||||
@@ -112,7 +111,7 @@ func TestASearchByCommandSaysWhatItReplaces(t *testing.T) {
|
||||
// A synonym is a word, never part of one: `logs` matches through `log`, and finds no `login`.
|
||||
func TestSearchStillMatchesEveryWord(t *testing.T) {
|
||||
x := meshToSearch(t)
|
||||
if hits := x.search("machine converged"); len(hits) != 1 || hits[0].Address != "mesh-controller.nodes" {
|
||||
if hits := x.search("machine converged"); len(hits) != 1 || hits[0].Address != "mesh-placement.nodes" {
|
||||
t.Errorf("words in a description: %+v", hits)
|
||||
}
|
||||
if hits := x.search("journalctl kubernetes"); len(hits) != 1 || hits[0].Address != "anchor/node-service-manager.journal" {
|
||||
|
||||
@@ -3,7 +3,7 @@ package console
|
||||
// mesh_wait: a session waits on the bus for one event instead of polling (novox/hq ADR 0367).
|
||||
//
|
||||
// **Only the families the tool runner was issued** (§2, §6): its membership names them, composed by the
|
||||
// controller from the tool runner's manifest together with the grant that lets this account subscribe them.
|
||||
// mesh from the tool runner's manifest together with the grant that lets this account subscribe them.
|
||||
// A name not listed there is refused here, before the bus would refuse it; no argument or setting adds one.
|
||||
// **An event only wakes the session** (§4): what it says is read again from the verb that owns it.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
// Package meshtest raises what the controller would, for tests against a real bus: the ASSIGNMENTS
|
||||
// Package meshtest raises what the mesh would, for tests against a real bus: the ASSIGNMENTS
|
||||
// and EVENTS streams, memberships issued by hand, and a fixture's path.
|
||||
//
|
||||
// **Every test has a bus of its own** (novox/hq ADR 0237, the controller's internal/testbus): a server
|
||||
// **Every test has a bus of its own** (novox/hq ADR 0237, the old testbus): a server
|
||||
// linked in at the release go.mod pins — the release the mesh runs, held so by a test beside this one —
|
||||
// started for the one test and gone after it. The packages shared one bus and had to run one at a time:
|
||||
// each test raised the streams afresh, and the console discovers every runtime that announces itself on
|
||||
@@ -72,7 +72,7 @@ func URL(t *testing.T) string {
|
||||
// buses are the running tests' buses, by test.
|
||||
var buses sync.Map
|
||||
|
||||
// Mesh is the controller's job, done by hand.
|
||||
// Mesh is the mesh's job, done by hand.
|
||||
type Mesh struct {
|
||||
nc *nats.Conn
|
||||
js nats.JetStreamContext
|
||||
@@ -230,7 +230,7 @@ func (m *Mesh) NextEvent(t *testing.T, pattern string) <-chan string {
|
||||
return ch
|
||||
}
|
||||
|
||||
// MembershipOf is a membership as the controller issues one on a machine.
|
||||
// MembershipOf is a membership as the mesh issues one on a machine.
|
||||
func MembershipOf(module, node string, plain bool, seats map[string][]string) bus.Membership {
|
||||
own := "mesh.mod." + module
|
||||
serves := []bus.Served{{Subject: own + ".tool.{tool}." + node}}
|
||||
@@ -291,7 +291,7 @@ func (l *Logs) Has(fragments ...string) bool {
|
||||
// All is every line.
|
||||
func (l *Logs) All() string { return strings.Join(l.lines, "\n") }
|
||||
|
||||
// Consumer makes a module's durable consumer on a machine as the controller does: pull, on the
|
||||
// Consumer makes a module's durable consumer on a machine as the mesh does: pull, on the
|
||||
// EVENTS stream, filtered to what the module consumes, with a short ack wait so a test sees a
|
||||
// redelivery in seconds rather than the mesh's minutes.
|
||||
func (m *Mesh) Consumer(t *testing.T, node, module string, filters []string, ackWait time.Duration) {
|
||||
@@ -351,7 +351,7 @@ func (m *Mesh) BucketKeeping(t *testing.T, name string, history uint8) nats.KeyV
|
||||
return kv
|
||||
}
|
||||
|
||||
// Bucket makes a module's state afresh as the controller does from the catalogue (novox/hq ADR 0201),
|
||||
// Bucket makes a module's state afresh as the mesh does from the catalogue (novox/hq ADR 0201),
|
||||
// and answers it for writing what is there before a bundle starts.
|
||||
func (m *Mesh) Bucket(t *testing.T, name string) nats.KeyValue {
|
||||
t.Helper()
|
||||
@@ -363,7 +363,7 @@ func (m *Mesh) Bucket(t *testing.T, name string) nats.KeyValue {
|
||||
return kv
|
||||
}
|
||||
|
||||
// BucketKeyTTL makes a module's state afresh as the controller does for one declared `key-ttl` (mesh-sdk buscompose:
|
||||
// BucketKeyTTL makes a module's state afresh as the mesh does for one declared `key-ttl` (mesh-sdk buscompose:
|
||||
// a time to live per key allowed, its end leaving a marker kept a minute; issue 1952).
|
||||
func (m *Mesh) BucketKeyTTL(t *testing.T, name string) {
|
||||
t.Helper()
|
||||
@@ -380,10 +380,10 @@ func (m *Mesh) BucketKeyTTL(t *testing.T, name string) {
|
||||
}
|
||||
}
|
||||
|
||||
// Log makes a module's log afresh as the controller does from the catalogue (novox/hq ADR 0297): a file
|
||||
// Log makes a module's log afresh as the mesh does from the catalogue (novox/hq ADR 0297): a file
|
||||
// stream named LOG_<module>_<name> on mesh.log.<module>.<name>.>, limits retention, no age, no cap per
|
||||
// key, the declared cap, 260 KiB a message (a 256 KiB value and its headers), refusing new entries when full, direct get, no delete or
|
||||
// purge. It answers the membership entry the controller issues for it.
|
||||
// purge. It answers the membership entry the mesh issues for it.
|
||||
func (m *Mesh) Log(t *testing.T, module, name string, maxBytes int64) bus.LogIssued {
|
||||
t.Helper()
|
||||
stream := "LOG_" + module + "_" + name
|
||||
@@ -409,7 +409,7 @@ func (m *Mesh) Consumers(t *testing.T, stream string) int {
|
||||
return info.State.Consumers
|
||||
}
|
||||
|
||||
// ModuleStream makes a module's own stream afresh as the controller does from the catalogue (novox/hq ADR
|
||||
// ModuleStream makes a module's own stream afresh as the mesh does from the catalogue (novox/hq ADR
|
||||
// 0363 §1): named in capitals, taking `mesh.stream.<module>.event.>`, a subject space EVENTS does not take.
|
||||
func (m *Mesh) ModuleStream(t *testing.T, module, name string) {
|
||||
t.Helper()
|
||||
@@ -455,7 +455,7 @@ func (m *Mesh) Messages(t *testing.T, stream string) uint64 {
|
||||
return info.State.Msgs
|
||||
}
|
||||
|
||||
// RemoveConsumer deletes a module's consumer on a machine on a stream, as the controller does when a grant
|
||||
// RemoveConsumer deletes a module's consumer on a machine on a stream, as the mesh does when a grant
|
||||
// it cannot narrow is withdrawn (novox/hq ADR 0363 §6).
|
||||
func (m *Mesh) RemoveConsumer(t *testing.T, stream, node, module string) {
|
||||
t.Helper()
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
// Package provide is the runtime's half of node-tools being a provider of `mcp-endpoint`: it runs the mesh SDK's
|
||||
// provider helper, so a consumer handed to the provisioner (claude-code's `${bound:mcp-endpoint:port}`) is answered
|
||||
// from an entry node-tools writes in its own bucket, not from the controller's binding file (novox/hq ADR 0349
|
||||
// from an entry node-tools writes in its own bucket, not from the old binding file (novox/hq ADR 0349
|
||||
// clause 12, issue 791).
|
||||
//
|
||||
// The offer carries no credential: the console's authority is the machine's login (ADR 0152, 0175), so the helper
|
||||
@@ -40,7 +40,7 @@ func Offers() map[string]provider.Offer {
|
||||
|
||||
// busOf is the helper's bus over the runtime's own state: the provider's bucket is its state `bound`, and the
|
||||
// provisions and plans of the seat mesh-provisioner are the states it reads, by mesh-sdk's names (novox/hq ADR 0570,
|
||||
// issue 1954 L6-T1). The controller's assignments are read no more (mesh-sdk 692dbf9, L6-P3).
|
||||
// issue 1954 L6-T1). The old assignments are read no more (mesh-sdk 692dbf9, L6-P3).
|
||||
type busOf struct{ conn *bus.Conn }
|
||||
|
||||
func (b busOf) state(bucket string) (string, error) {
|
||||
|
||||
@@ -160,8 +160,8 @@ func TestTheOfferServesThePortTheManifestServes(t *testing.T) {
|
||||
}
|
||||
}
|
||||
for _, r := range m.Reads {
|
||||
if r == "mesh-controller.assignments" {
|
||||
t.Error("the manifest still reads mesh-controller.assignments, which the sdk's helper no longer reads (issue 1954)")
|
||||
if r == "mesh-placement.assignments" {
|
||||
t.Error("the manifest still reads mesh-placement.assignments, which the sdk's helper no longer reads (issue 1954)")
|
||||
}
|
||||
}
|
||||
for _, a := range m.Build.Artifacts {
|
||||
@@ -195,9 +195,9 @@ func TestOnlyTheMachinesRuntimeStartsTheHelper(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// 774/S33 (ADR 0571 clause 13): this manifest, read as the lease write's check reads it, is not refused at the write: it
|
||||
// reads and invokes nothing of the controller and consumes nothing of it.
|
||||
func TestTheManifestIsNotRefusedAtTheLeaseWrite(t *testing.T) {
|
||||
// 1126/B19 (ADR 0590): this manifest is not refused by the check that refuses any manifest naming the controller:
|
||||
// it reads, invokes, claims and requires nothing of it.
|
||||
func TestTheManifestNamesNothingOfTheController(t *testing.T) {
|
||||
raw, err := os.ReadFile("../../module.json")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -206,7 +206,7 @@ func TestTheManifestIsNotRefusedAtTheLeaseWrite(t *testing.T) {
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if refused := catalogue.ManifestRefusals(map[string]catalogue.Manifest{Module: m}, catalogue.PhaseWrite); len(refused) != 0 {
|
||||
t.Errorf("the lease write's check refuses node-tools' manifest: %v", refused)
|
||||
if refused := catalogue.ManifestRefusals(map[string]catalogue.Manifest{Module: m}); len(refused) != 0 {
|
||||
t.Errorf("the controller-dependence check refuses node-tools' manifest: %v", refused)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -70,7 +70,7 @@ func TestABundlesSeatTrafficGoesThroughItsModulesBus(t *testing.T) {
|
||||
if !strings.Contains(string(first), `"duplicate":false`) || !strings.Contains(string(again), `"duplicate":true`) {
|
||||
t.Errorf("the same id twice: %s, then %s", first, again)
|
||||
}
|
||||
if _, err := asking.Seat("publish", json.RawMessage(`{"subject":"mesh.seat.operator-channel.accept.ask.mesh-controller","body":{}}`), nil); err == nil {
|
||||
if _, err := asking.Seat("publish", json.RawMessage(`{"subject":"mesh.seat.operator-channel.accept.ask.mesh-placement","body":{}}`), nil); err == nil {
|
||||
t.Error("a module submitted under another's name")
|
||||
}
|
||||
got, err := asking.Seat("record", json.RawMessage(`{"key":"d-1"}`), nil)
|
||||
|
||||
@@ -433,7 +433,7 @@ export async function connectNats(
|
||||
/**
|
||||
* React to events.
|
||||
*
|
||||
* The durable consumer is the **controller's** to create, from what this module declared it
|
||||
* The durable consumer is the **mesh's** to create, from what this module declared it
|
||||
* consumes (design 29 §3) — this binds to it and never creates one. A runtime that created
|
||||
* its own would be a module deciding its own delivery semantics, and its account cannot
|
||||
* reach the JetStream API to do it anyway.
|
||||
@@ -499,14 +499,14 @@ async function deliver(
|
||||
env = toEnvelope<unknown>(msg);
|
||||
} catch {
|
||||
// Unparseable: terminate it. Redelivering a message no version of this code can read is
|
||||
// an infinite loop, and what the controller keeps of a message given up on (DEAD_LETTERS,
|
||||
// an infinite loop, and what the mesh keeps of a message given up on (DEAD_LETTERS,
|
||||
// novox/hq issue 330) is for handlers that fail, not for bytes that were never an envelope.
|
||||
msg.term();
|
||||
return;
|
||||
}
|
||||
const forThis = listeners.filter((l) => topicMatches(l.pattern, env.key));
|
||||
if (forThis.length === 0) {
|
||||
// The consumer's filters are the controller's, derived from what the module declared it
|
||||
// The consumer's filters are the mesh's, derived from what the module declared it
|
||||
// consumes, and may be wider than anything it registered a handler for. Acknowledge it, or it
|
||||
// would be redelivered until it expired.
|
||||
msg.ack();
|
||||
@@ -518,10 +518,10 @@ async function deliver(
|
||||
} catch {
|
||||
// Negative-acknowledge with a delay, so a handler failing on a transient cause gets another
|
||||
// attempt, and one failing permanently exhausts max-deliver rather than spinning: the consumer
|
||||
// gives the event up, and the controller keeps it in DEAD_LETTERS until a person delivers it
|
||||
// gives the event up, and the mesh keeps it in DEAD_LETTERS until a person delivers it
|
||||
// again or drops it (novox/hq issue 330). Delivered again, it arrives under
|
||||
// `mesh.again.<consumer>.…`, and keyFromSubject reads the same key from it. The consumer's
|
||||
// limits are the controller's; this only says "not done".
|
||||
// limits are the mesh's; this only says "not done".
|
||||
msg.nak(5_000);
|
||||
}
|
||||
}
|
||||
@@ -592,7 +592,7 @@ function toolSubject(key: string, self: string): string {
|
||||
}
|
||||
|
||||
/** A seat's verb, as its holder serves it: flat for a mesh seat, carrying the machine for a
|
||||
* node-scoped one (design 33 §4) — the same shape the controller grants. */
|
||||
* node-scoped one (design 33 §4) — the same shape the mesh grants. */
|
||||
export function seatToolSubject(seat: string, verb: string, scope: string | undefined, node: string | undefined): string {
|
||||
const base = `mesh.seat.${seat}.tool.${verb}`;
|
||||
return scope === "node" && node ? `${base}.${node}` : base;
|
||||
|
||||
@@ -28,7 +28,7 @@ const CATALOGUE_MODULES = "mesh-catalog.catalog_modules";
|
||||
|
||||
/** Where every role's tools are answered: the console on this machine, the Go runtime, which holds mesh-sdk's seat
|
||||
* definitions and reads who holds each seat from placement (novox/hq ADR 0571 clauses 4 and 5). Asked over the loopback
|
||||
* channel `mesh --console` already uses, by the method `mesh/seats` beside MCP's; never the controller. */
|
||||
* channel `mesh --console` already uses, by the method `mesh/seats` beside MCP's; never another record. */
|
||||
export const SEATS_METHOD = "mesh/seats";
|
||||
const DEFAULT_CONSOLE = "http://127.0.0.1:4270";
|
||||
|
||||
|
||||
@@ -97,7 +97,7 @@ export function mcpSurface(bus: Broker, who: string): Surface {
|
||||
`that serves it; what may be called was fixed when this account was issued, so a ` +
|
||||
`refusal means the account, not the tool. The list is what the running modules ` +
|
||||
`answered, plus every role's tools from the mesh's records — the mesh's own verbs ` +
|
||||
`(mesh-controller.status, .push, .assign …) among them; a module that did not answer ` +
|
||||
`(mesh-delivery.deliveries, mesh-placement.propose …) among them; a module that did not answer ` +
|
||||
`is named in the list's _meta and can still be called by <module>.<tool>.`,
|
||||
});
|
||||
|
||||
|
||||
@@ -40,15 +40,15 @@ async function aMeshWithTools() {
|
||||
await shop.handle("price", async (body: { of?: string }) => ({ of: body.of ?? "nothing", cost: 12 }));
|
||||
// Every role's tools, from the console on this machine (ADR 0571), the method beside MCP's; the controller's
|
||||
// verb answers a call of its seat and is never asked for the roles.
|
||||
const controller = await connectNats({ url: url!, module: "mesh-controller" });
|
||||
const controller = await connectNats({ url: url!, module: "mesh-placement" });
|
||||
let controllerToolsAsked = 0;
|
||||
await controller.handle("seat:mesh-controller.tools", async () => {
|
||||
await controller.handle("seat:mesh-placement.tools", async () => {
|
||||
controllerToolsAsked++;
|
||||
return { seats: [] };
|
||||
});
|
||||
await controller.handle("seat:mesh-controller.status", async () => ({ output: "all quiet", ok: true }));
|
||||
await controller.handle("seat:mesh-placement.status", async () => ({ output: "all quiet", ok: true }));
|
||||
const local = await aConsoleWithSeats([
|
||||
{ seat: "mesh-controller", scope: "mesh", tools: [{ name: "status", description: "what is wrong", input: {} }] },
|
||||
{ seat: "mesh-placement", scope: "mesh", tools: [{ name: "status", description: "what is wrong", input: {} }] },
|
||||
{ seat: "node-dns-resolver", scope: "node", tools: [{ name: "lookup", description: "one machine's", input: {} }] },
|
||||
]);
|
||||
return {
|
||||
@@ -71,12 +71,12 @@ test("a person sees what the running modules answer, sorted, and who did not ans
|
||||
const have = await toolsOn(person);
|
||||
assert.deepEqual(
|
||||
have.tools.map((x) => `${x.module}.${x.name}`),
|
||||
["mesh-catalog.catalog_modules", "mesh-controller.status", "node-dns-resolver.lookup", "shop.price"],
|
||||
["mesh-catalog.catalog_modules", "mesh-placement.status", "node-dns-resolver.lookup", "shop.price"],
|
||||
"the list is what the modules answered plus every role's tools, in a stable order",
|
||||
);
|
||||
// A role's tool is marked as one; a node-scoped seat's carries its scope, so a caller names
|
||||
// the machine and the verb resolves as the seat's (design 33 §4, ADR 0170).
|
||||
assert.ok(have.tools.find((x) => x.module === "mesh-controller")!.seat);
|
||||
assert.ok(have.tools.find((x) => x.module === "mesh-placement")!.seat);
|
||||
const lookup = have.tools.find((x) => x.module === "node-dns-resolver")!;
|
||||
assert.ok(lookup.seat && lookup.scope === "node");
|
||||
assert.equal(toolKey("node-dns-resolver.lookup", seatsIn(have)), "seat:node-dns-resolver.lookup");
|
||||
@@ -146,12 +146,12 @@ test("a role's tool is reached through the seat, and a module's own name is neve
|
||||
const person = await connectNats({ url, module: "person.ada" });
|
||||
try {
|
||||
const roles = seatsIn(await toolsOn(person));
|
||||
assert.equal(toolKey("mesh-controller.status", roles), "seat:mesh-controller.status");
|
||||
assert.equal(toolKey("mesh-controller.other", roles), "mesh-controller.other", "a verb the seat does not declare is a module's");
|
||||
assert.equal(toolKey("mesh-placement.status", roles), "seat:mesh-placement.status");
|
||||
assert.equal(toolKey("mesh-placement.other", roles), "mesh-placement.other", "a verb the seat does not declare is a module's");
|
||||
assert.equal(toolKey("shop.price", roles), "shop.price");
|
||||
const answer = await callTool(person, "mesh-controller.status", {}, roles);
|
||||
const answer = await callTool(person, "mesh-placement.status", {}, roles);
|
||||
assert.deepEqual(answer.result, { output: "all quiet", ok: true });
|
||||
const direct = await callTool(person, "seat:mesh-controller.status", {});
|
||||
const direct = await callTool(person, "seat:mesh-placement.status", {});
|
||||
assert.deepEqual(direct.result, { output: "all quiet", ok: true });
|
||||
} finally {
|
||||
await person.close();
|
||||
|
||||
@@ -30,10 +30,10 @@ async function aMeshAndACredential(t: { after: (fn: () => Promise<void> | void)
|
||||
tools: [{ name: "price", description: "what something costs", input: { of: { type: "string" } } }],
|
||||
}));
|
||||
await shop.handle("price", async (body: { of?: string }) => ({ of: body.of ?? "nothing", cost: 12 }));
|
||||
const controller = await connectNats({ url: url!, module: "mesh-controller" });
|
||||
const controller = await connectNats({ url: url!, module: "mesh-placement" });
|
||||
// Every role's tools, from the console on this machine (ADR 0571), which the spawned `mesh` asks through MESH_CONSOLE.
|
||||
const local = await aConsoleWithSeats([
|
||||
{ seat: "mesh-controller", scope: "mesh", tools: [
|
||||
{ seat: "mesh-placement", scope: "mesh", tools: [
|
||||
{ name: "status", description: "what is wrong", input: {} },
|
||||
{ name: "push", description: "tell a machine", input: { node: { type: "string" } } },
|
||||
] },
|
||||
@@ -41,8 +41,8 @@ async function aMeshAndACredential(t: { after: (fn: () => Promise<void> | void)
|
||||
{ seat: "node-dns-resolver", scope: "node", tools: [{ name: "lookup", description: "one machine's", input: {} }] },
|
||||
]);
|
||||
await controller.handle("seat:node-dns-resolver.lookup@anchor", async () => ({ machine: "anchor", answered: true }));
|
||||
await controller.handle("seat:mesh-controller.status", async () => ({ output: "all quiet", ok: true }));
|
||||
await controller.handle("seat:mesh-controller.push", async (body: { node?: string }) => ({ told: body.node ?? "nobody" }));
|
||||
await controller.handle("seat:mesh-placement.status", async () => ({ output: "all quiet", ok: true }));
|
||||
await controller.handle("seat:mesh-placement.push", async (body: { node?: string }) => ({ told: body.node ?? "nobody" }));
|
||||
t.after(async () => {
|
||||
await catalogue.close();
|
||||
await shop.close();
|
||||
@@ -107,7 +107,7 @@ test("a host initialises, lists the mesh's tools and calls one", async (t) => {
|
||||
|
||||
const listed = byId.get(2)!.result.tools;
|
||||
assert.deepEqual(listed.map((x: { name: string }) => x.name),
|
||||
["mesh-controller.push", "mesh-controller.status", "node-dns-resolver.lookup", "shop.price"],
|
||||
["mesh-placement.push", "mesh-placement.status", "node-dns-resolver.lookup", "shop.price"],
|
||||
"the modules' tools and the roles', named the way a person names them");
|
||||
// A node-scoped seat's verb takes the machine, and requires it (ADR 0170).
|
||||
const lookup = listed[2];
|
||||
@@ -164,7 +164,7 @@ test("a seat's verb keeps a node of its own; only a module's tool gives it to th
|
||||
if (!url) return t.skip("MESH_TEST_NATS unset");
|
||||
const credential = await aMeshAndACredential(t);
|
||||
const replies = await driving(credential, [
|
||||
{ jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "mesh-controller.push", arguments: { node: "anchor" } } },
|
||||
{ jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "mesh-placement.push", arguments: { node: "anchor" } } },
|
||||
]);
|
||||
const result = replies[0].result;
|
||||
assert.ok(!result.isError, JSON.stringify(replies[0]));
|
||||
@@ -175,7 +175,7 @@ test("a host calls the mesh's own verb through the seat", async (t) => {
|
||||
if (!url) return t.skip("MESH_TEST_NATS unset");
|
||||
const credential = await aMeshAndACredential(t);
|
||||
const replies = await driving(credential, [
|
||||
{ jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "mesh-controller.status", arguments: {} } },
|
||||
{ jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "mesh-placement.status", arguments: {} } },
|
||||
]);
|
||||
const result = replies[0].result;
|
||||
assert.ok(!result.isError, JSON.stringify(replies[0]));
|
||||
|
||||
@@ -69,12 +69,12 @@ test("preparing with nothing named fails rather than passing quietly", async ()
|
||||
// therefore pure and tested as such: what a message is for is decided by the patterns registered, not
|
||||
// by which reader happened to fetch it.
|
||||
test("a message is for every pattern that matches it, and nothing else", () => {
|
||||
const registered = ["mesh-build-machine.built", "mesh-controller.built-before"];
|
||||
const registered = ["mesh-build-machine.built", "mesh-placement.built-before"];
|
||||
const matched = (key: string) => registered.filter((p) => topicMatches(p, key));
|
||||
assert.deepEqual(matched("mesh-build-machine.built"), ["mesh-build-machine.built"]);
|
||||
assert.deepEqual(matched("mesh-controller.built-before"), ["mesh-controller.built-before"]);
|
||||
assert.deepEqual(matched("mesh-placement.built-before"), ["mesh-placement.built-before"]);
|
||||
// Nothing registered for it: the consumer's filter is the controller's and may be wider.
|
||||
assert.deepEqual(matched("mesh-catalog.upgraded"), []);
|
||||
// And a handler that asked for everything gets both, which is what the audit logger does.
|
||||
assert.deepEqual(["#"].filter((p) => topicMatches(p, "mesh-controller.built-before")), ["#"]);
|
||||
assert.deepEqual(["#"].filter((p) => topicMatches(p, "mesh-placement.built-before")), ["#"]);
|
||||
});
|
||||
|
||||
@@ -5,7 +5,7 @@ import { connectNats } from "../dist/broker-nats.js";
|
||||
|
||||
const URL = "nats://127.0.0.1:14222";
|
||||
|
||||
// The controller's job, done by hand here: the stream and the module's durable consumer.
|
||||
// The mesh's job, done by hand here: the stream and the module's durable consumer.
|
||||
const admin = await connect({ servers: URL });
|
||||
const jsm = await admin.jetstreamManager();
|
||||
await jsm.streams.add({ name: "EVENTS", subjects: ["mesh.mod.*.event.>", "mesh.seat.*.event.>"] });
|
||||
|
||||
Reference in New Issue
Block a user