From 1a4305213d0899bb9a068e7182fff4812790be47 Mon Sep 17 00:00:00 2001 From: jochen Date: Thu, 8 Oct 2026 13:58:53 +0200 Subject: [PATCH] Open every explanation with what the operator needs to do, and offer the answers The operator could not tell from a notification whether to act, and was told to have an agent do it. Each condition now says "Nothing for you to do." or "Needs you:" with one thing they can do themselves, and carries the actions the operator channel performs when chosen (hq ADR 0253). --- cmd/mesh-controller/delivery_conditions.go | 2 +- cmd/mesh-controller/machine_units.go | 6 +- cmd/mesh-controller/module_health.go | 9 +- cmd/mesh-controller/plain_words.go | 336 +++++++++++++-------- cmd/mesh-controller/plain_words_test.go | 104 +++++-- cmd/mesh-controller/signals.go | 18 +- internal/conditions/condition.go | 6 + internal/conditions/plain.go | 114 +++++-- internal/conditions/plain_test.go | 38 ++- internal/conditions/store.go | 4 +- 10 files changed, 430 insertions(+), 207 deletions(-) diff --git a/cmd/mesh-controller/delivery_conditions.go b/cmd/mesh-controller/delivery_conditions.go index b0352e2b..b8f4cbd0 100644 --- a/cmd/mesh-controller/delivery_conditions.go +++ b/cmd/mesh-controller/delivery_conditions.go @@ -113,7 +113,7 @@ func stalledObservations(lines []stalledLine) []conditions.Observation { if l.operatorsOnly() { o.Resolver = conditions.ResolverOperator } - o.Headline, o.Explanation, o.Resolved = stalledWords(l, o) + o.Headline, o.Explanation, o.Resolved, o.Needs, o.Actions = stalledWords(l, o) out = append(out, o) } return out diff --git a/cmd/mesh-controller/machine_units.go b/cmd/mesh-controller/machine_units.go index 275ccab7..0060f0fb 100644 --- a/cmd/mesh-controller/machine_units.go +++ b/cmd/mesh-controller/machine_units.go @@ -117,8 +117,10 @@ func machineUnitsObservation(node string, u *link.UnitsHealth) (conditions.Obser failed = fmt.Sprintf("%d failed services", len(u.Failed)) } o.Headline = fmt.Sprintf("%s on %s", conditions.Capital(failed), node) - o.Explanation = fmt.Sprintf("On %s, %s failed. No module manages them, so the mesh does not repair them: mend or "+ - "remove them on %s.", node, namesWords(plain, 3), node) + o.Needs = fmt.Sprintf("mend or remove them on %s, or silence this if they do not matter.", node) + o.Explanation = fmt.Sprintf("On %s, %s failed. No module manages them, so the mesh does not repair them.", + node, namesWords(plain, 3)) + o.Actions = []conditions.Action{conditions.SilenceAction(o.Key())} o.Resolved = "No failed services on " + node + " any more" return o, true } diff --git a/cmd/mesh-controller/module_health.go b/cmd/mesh-controller/module_health.go index d03d7138..d402c94a 100644 --- a/cmd/mesh-controller/module_health.go +++ b/cmd/mesh-controller/module_health.go @@ -167,7 +167,7 @@ func judgeModuleHealth(ctx context.Context, inv *inventory.Inventory, k *conditi o.Severity = conditions.Urgent o.Said += "; " + waitingWords(waiters) o.Summary += fmt.Sprintf("; %d consumer(s) wait on it", len(waiters)) - o.Explanation += fmt.Sprintf(" %d module(s) that depend on it wait for it, so this is urgent.", len(waiters)) + o.Explanation += fmt.Sprintf(" %d module(s) that depend on it wait for it.", len(waiters)) } } seen[o.Key()] = true @@ -243,6 +243,7 @@ func sayWaiters(ctx context.Context, k *conditions.Keeper, hold *holding, p cata // the machine and what is wrong with each resource; the detail — targets, streaks, since — is evidence. func moduleUnhealthyObservation(module, node string, rs []inventory.ResourceHealth) conditions.Observation { var words, said, plain []string + needs, actions := moduleNeeds(node, rs) for _, r := range rs { plain = append(plain, resourcePlainWords(r)) if r.Kind == link.KindUnit { @@ -263,8 +264,10 @@ func moduleUnhealthyObservation(module, node string, rs []inventory.ResourceHeal Summary: fmt.Sprintf("%s on %s is not healthy: %s", module, node, strings.Join(words, "; ")), Said: strings.Join(said, "; "), Headline: fmt.Sprintf("%s not working on %s", module, node), - Explanation: fmt.Sprintf("%s on %s is not healthy: %s. It clears as soon as it runs again; if it stays, it "+ - "needs a look at why it fails.", module, node, namesWords(plain, 3)), + Explanation: fmt.Sprintf("%s on %s is not healthy: %s. It clears as soon as it runs again.", module, node, + namesWords(plain, 3)), + Needs: needs, + Actions: actions, Resolved: fmt.Sprintf("%s works again on %s", module, node)} } diff --git a/cmd/mesh-controller/plain_words.go b/cmd/mesh-controller/plain_words.go index c118f12f..edd6a849 100644 --- a/cmd/mesh-controller/plain_words.go +++ b/cmd/mesh-controller/plain_words.go @@ -63,71 +63,80 @@ var plainWordings = map[string]func(conditions.Observation) words{ // Machines and their node-engine. "silent": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") - return words{Headline: m + " is not answering", + w := words{Headline: m + " is not answering", Explanation: fmt.Sprintf("The mesh has not heard from %s for several minutes. A machine asleep or away is "+ - "normal; if %s should be on, check that it is powered and online.", m, m), + "normal.", m), Resolved: m + " answers again"} + if o.Severity == conditions.Urgent { + w.Needs = fmt.Sprintf("check that %s is on and online.", m) + w.Explanation = fmt.Sprintf("The mesh has not heard from %s for half an hour, and the mesh is run from it: "+ + "nothing changes anywhere until it is back.", m) + } + return w }), "sent-not-reported": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: m + " has not confirmed a change", - Explanation: fmt.Sprintf("The mesh sent %s new instructions and %s has not said it applied them. It "+ - "usually catches up by itself; if it stays, %s may be stuck.", m, m, m), + Explanation: fmt.Sprintf("The mesh sent %s new instructions and %s has not said it applied them yet. "+ + "It usually catches up by itself.", m, m), Resolved: m + " applied the change"} }), "tools-silent": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "Tools on " + m + " are not answering", Explanation: fmt.Sprintf("The tool runner on %s has not checked in, so nothing can be done on %s through "+ - "the mesh. A machine asleep is normal.", m, m), + "the mesh until it does. A machine asleep is normal.", m, m), Resolved: "Tools on " + m + " answer again"} }), kindAwaitingPush: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: m + " waits for new instructions", - Explanation: fmt.Sprintf("%s's instructions only work once the next push is made, and none has been made "+ - "for a while. Nothing is broken; an agent can push to %s.", conditions.Capital(m), m), + Explanation: fmt.Sprintf("%s's new instructions go out with the next push. Nothing is broken meanwhile.", + conditions.Capital(m)), Resolved: m + " got its new instructions"} }), "declaration-refused": worded(func(o conditions.Observation) words { if o.Scope == conditions.ScopeMesh { return words{Headline: "No machine can get new instructions", + Needs: "decide whether to undo the last catalogue change; the details say what fails.", Explanation: "The mesh cannot work out its private network, so no machine's instructions can be " + - "made. Machines keep running what they have. It needs a look now.", + "made. Machines keep running what they have.", Resolved: "Machines can get new instructions again"} } m := machineOr(o, "a machine") return words{Headline: m + " cannot get new instructions", - Explanation: fmt.Sprintf("What the mesh would send %s is wrong and would be refused, so nothing new reaches "+ - "%s. It keeps running what it has. It needs a fix in the catalogue.", m, m), + Needs: "decide whether to undo the last catalogue change; the details say what fails.", + Explanation: fmt.Sprintf("What the mesh would send %s is wrong and would be refused, so nothing new "+ + "reaches it. It keeps running what it has.", m), Resolved: m + " can get new instructions again"} }), "own-address-banned": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: m + " has banned the mesh", + Needs: fmt.Sprintf("lift the ban on %s, or wait for it to expire.", m), Explanation: fmt.Sprintf("The intrusion protection on %s banned one of the mesh's own addresses, so the "+ - "mesh is locked out of %s. It needs the ban lifted.", m, m), + "mesh is locked out of it.", m), Resolved: m + " no longer bans the mesh"} }), "core-behind": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: m + " runs an old node-engine", - Explanation: fmt.Sprintf("%s runs an older build of the mesh's own software than the mesh holds, and no "+ - "delivery is bringing it up to date. It works, but misses the newest fixes.", conditions.Capital(m)), + Explanation: fmt.Sprintf("%s runs an older build of the mesh's own software than the mesh holds. It "+ + "works, and gets the newer one with a later delivery.", conditions.Capital(m)), Resolved: m + " runs the current node-engine"} }), kindMachineUnits: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "Failed services on " + m, - Explanation: fmt.Sprintf("Services on %s that no module manages have failed. They are %s's own, so the "+ - "mesh does not repair them: mend or remove them there.", m, m), - Resolved: "No failed services on " + m + " any more"} + Needs: fmt.Sprintf("mend or remove them on %s, or silence this if they do not matter.", m), + Explanation: "No module manages them, so the mesh does not repair them.", + Resolved: "No failed services on " + m + " any more", Actions: []conditions.Action{conditions.SilenceAction(o.Key())}} }), kindMachineNetwork: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: m + " has a network problem", Explanation: fmt.Sprintf("%s's own network check failed: its name lookups, tunnel, bus connection or "+ - "route. Other machines may not reach it, or it them.", conditions.Capital(m)), + "route. It often passes again once a network change settles.", conditions.Capital(m)), Resolved: m + "'s network is fine again"} }), kindNetworkRewritten: worded(func(o conditions.Observation) words { @@ -141,38 +150,38 @@ var plainWordings = map[string]func(conditions.Observation) words{ m := machineOr(o, "a machine") return words{Headline: m + " cannot be reached", Explanation: fmt.Sprintf("Other machines cannot reach %s over the mesh's network. A machine away or "+ - "asleep is normal; otherwise its tunnel needs a look.", m), + "asleep is normal.", m), Resolved: m + " can be reached again"} }), kindBindingKept: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "A module's data source is held on " + m, + Needs: "decide where its data lives; the details name both places.", Explanation: fmt.Sprintf("A module on %s should switch to another provider of its data, and the mesh "+ - "kept the old one because switching would leave the data behind. It needs you to decide.", m), + "kept the old one because switching would leave the data behind.", m), Resolved: "Resolved: the data source on " + m + " is decided"} }), kindBindingMoving: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "A module's data source moves on " + m, - Explanation: fmt.Sprintf("At the next push a module on %s switches to another provider, and its data is "+ - "still with the old one. Move the data first.", m), - Resolved: "Resolved: the data source move on " + m + " is settled"} + Needs: "move its data to the new provider before the next push.", + Explanation: fmt.Sprintf("At the next push a module on %s switches to another provider of its data.", m), + Resolved: "Resolved: the data source move on " + m + " is settled"} }), kindBindingMoved: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "A module's data source moved on " + m, - Explanation: fmt.Sprintf("A module on %s switched to another provider of its data, and its data may "+ - "still be with the old one. Check it found its data.", m), - Resolved: "Resolved: the data source move on " + m + " is settled"} + Needs: "check that it found its data.", + Explanation: fmt.Sprintf("A module on %s switched to another provider, and its data may still be with the old one.", m), + Resolved: "Resolved: the data source move on " + m + " is settled"} }), // Modules and providers. kindModuleUnhealthy: worded(func(o conditions.Observation) words { thing := conditions.ThingWords(o) return words{Headline: conditions.Capital(thing) + " is not working", - Explanation: fmt.Sprintf("%s is not healthy. It clears as soon as it runs again; if it stays, "+ - "look at why it fails.", conditions.Capital(thing)), - Resolved: conditions.Capital(thing) + " works again"} + Explanation: fmt.Sprintf("%s is not healthy. It clears as soon as it runs again.", conditions.Capital(thing)), + Resolved: conditions.Capital(thing) + " works again"} }), kindProviderFailing: worded(func(o conditions.Observation) words { thing, consumer := conditions.ThingWords(o), idPart(o, 2) @@ -181,29 +190,29 @@ var plainWordings = map[string]func(conditions.Observation) words{ } return words{Headline: conditions.Capital(thing) + " keeps failing " + consumer, Explanation: fmt.Sprintf("%s provides something %s needs, such as a database, and keeps failing to set "+ - "it up. %s may not work until it does.", conditions.Capital(thing), consumer, conditions.Capital(consumer)), + "it up. It tries again by itself.", conditions.Capital(thing), consumer), Resolved: conditions.Capital(thing) + " serves " + consumer + " again"} }), kindProviderSilent: worded(func(o conditions.Observation) words { thing := conditions.ThingWords(o) return words{Headline: conditions.Capital(thing) + " went quiet", Explanation: fmt.Sprintf("%s said it keeps failing a module that depends on it, and then stopped "+ - "reporting. Whether it still fails is not known.", conditions.Capital(thing)), + "reporting.", conditions.Capital(thing)), Resolved: conditions.Capital(thing) + " reports again"} }), kindRetireWaiting: worded(func(o conditions.Observation) words { thing := conditions.ThingWords(o) return words{Headline: "Retiring data on " + thing + " waits for you", - Explanation: fmt.Sprintf("%s keeps data the mesh no longer asks for, too much to retire on its own. It "+ - "needs you to approve or reject retiring it.", conditions.Capital(thing)), + Needs: "approve or reject retiring it; the details list what would go.", + Explanation: fmt.Sprintf("%s keeps data the mesh no longer asks for, too much to retire on its own.", + conditions.Capital(thing)), Resolved: "Resolved: the retirement on " + thing + " is decided"} }), kindRetireRejected: worded(func(o conditions.Observation) words { thing := conditions.ThingWords(o) return words{Headline: "Unused data kept on " + thing, - Explanation: fmt.Sprintf("You chose to keep data on %s that the mesh no longer asks for. Nothing to do; "+ - "this is a reminder that it is still there.", thing), - Resolved: "Resolved: the unused data on " + thing + " is gone"} + Explanation: fmt.Sprintf("You chose to keep data on %s that the mesh no longer asks for; it is still there.", thing), + Resolved: "Resolved: the unused data on " + thing + " is gone"} }), kindCleanupWaiting: worded(func(o conditions.Observation) words { var where string @@ -214,9 +223,9 @@ var plainWordings = map[string]func(conditions.Observation) words{ where = what + " on " + machineOr(o, "a machine") } return words{Headline: "Retired data waits for cleanup", - Explanation: fmt.Sprintf("Retired data of %s has been kept for over thirty days. It needs you to delete "+ - "it or keep it.", where), - Resolved: "Resolved: the retired data is dealt with"} + Needs: "delete it or keep it; nothing is deleted without your word.", + Explanation: fmt.Sprintf("Retired data of %s has been kept for over thirty days.", where), + Resolved: "Resolved: the retired data is dealt with"} }), // Data. @@ -224,22 +233,23 @@ var plainWordings = map[string]func(conditions.Observation) words{ m := machineOr(o, "a machine") return words{Headline: "Data on " + m + " could not be measured", Explanation: fmt.Sprintf("The backup holder on %s did not say what it measured, so nothing is known about "+ - "the data there: not that it is safe either.", m), + "the data there. The next measurement may settle it.", m), Resolved: "Data on " + m + " is measured again"} }), kindProtectionMissing: worded(func(o conditions.Observation) words { what, _ := dataWords(o) return words{Headline: conditions.Capital(what) + " is unprotected", + Needs: "check the storage it is on.", Explanation: fmt.Sprintf("%s on %s is said to be protected by redundant storage, and it is not on any "+ - "the mesh can see. It needs you to check its storage.", conditions.Capital(what), machineOr(o, "its machine")), + "the mesh can see.", conditions.Capital(what), machineOr(o, "its machine")), Resolved: conditions.Capital(what) + " is protected again"} }), kindDataMissing: worded(func(o conditions.Observation) words { what, _ := dataWords(o) return words{Headline: conditions.Capital(what) + " is gone", - Explanation: fmt.Sprintf("Where %s is kept on %s, nothing exists any more. If that was not meant, it needs "+ - "restoring from a backup.", what, machineOr(o, "its machine")), - Resolved: conditions.Capital(what) + " is back"} + Needs: "restore it from a backup, or silence this if you removed it.", + Explanation: fmt.Sprintf("Where %s is kept on %s, nothing exists any more.", what, machineOr(o, "its machine")), + Resolved: conditions.Capital(what) + " is back", Actions: []conditions.Action{conditions.SilenceAction(o.Key())}} }), kindDataShrank: worded(func(o conditions.Observation) words { what, _ := dataWords(o) @@ -248,30 +258,33 @@ var plainWordings = map[string]func(conditions.Observation) words{ what = "a dataset" } return words{Headline: conditions.Capital(what) + " shrank on " + m, - Explanation: "More than half of what it held is gone within a week. If you meant that, silence it; if " + - "not, restore the last good copy from a backup.", - Resolved: "Resolved: the shrinking on " + m + " is explained"} + Needs: "if you meant it, silence this; if not, restore the last good copy from a backup.", + Explanation: "More than half of what it held is gone within a week.", + Resolved: "Resolved: the shrinking on " + m + " is explained", Actions: []conditions.Action{conditions.SilenceAction(o.Key())}} }), kindDataQuiet: worded(func(o conditions.Observation) words { what, _ := dataWords(o) return words{Headline: conditions.Capital(what) + " stopped changing", + Needs: "check that what writes it still runs.", Explanation: fmt.Sprintf("%s on %s is normally written all the time and has not been for longer than "+ - "usual: whatever writes it has stopped.", conditions.Capital(what), machineOr(o, "its machine")), + "usual.", conditions.Capital(what), machineOr(o, "its machine")), Resolved: conditions.Capital(what) + " is written again"} }), kindBackupStale: worded(func(o conditions.Observation) words { what, _ := dataWords(o) + m := machineOr(o, "its machine") return words{Headline: "No recent backup of " + what, + Needs: fmt.Sprintf("check that backups run on %s.", m), Explanation: fmt.Sprintf("%s on %s has no good backup recent enough. If the machine failed now, what "+ - "changed since would be lost.", conditions.Capital(what), machineOr(o, "its machine")), + "changed since would be lost.", conditions.Capital(what), m), Resolved: conditions.Capital(what) + " is backed up again"} }), kindArrayDegraded: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "Storage on " + m + " is degraded", - Explanation: fmt.Sprintf("The redundant storage on %s lost a disk or is rebuilding. The data on it is "+ - "less protected until it is whole again.", m), - Resolved: "Storage on " + m + " is whole again"} + Needs: fmt.Sprintf("check the disks of %s.", m), + Explanation: "Its redundant storage lost a disk or is rebuilding; the data on it is less protected until it is whole.", + Resolved: "Storage on " + m + " is whole again"} }), kindEmptyReplacement: worded(func(o conditions.Observation) words { module := idPart(o, 1) @@ -282,8 +295,9 @@ var plainWordings = map[string]func(conditions.Observation) words{ module = "a module" } return words{Headline: conditions.Capital(module) + " runs on empty data", + Needs: "decide where its data lives: move the data, or move it back.", Explanation: fmt.Sprintf("%s on %s is using an empty copy of its data while the full copy is kept "+ - "elsewhere. It needs you: move the data, or move it back.", conditions.Capital(module), machineOr(o, "its machine")), + "elsewhere.", conditions.Capital(module), machineOr(o, "its machine")), Resolved: conditions.Capital(module) + " has its data again"} }), kindDataHeldTwice: worded(func(o conditions.Observation) words { @@ -292,40 +306,38 @@ var plainWordings = map[string]func(conditions.Observation) words{ consumer = "a module" } return words{Headline: conditions.Capital(consumer) + "'s data is on several machines", - Explanation: fmt.Sprintf("%s has live data on more than one machine and uses only one. It needs you to "+ - "decide which to keep.", conditions.Capital(consumer)), - Resolved: conditions.Capital(consumer) + "'s data is in one place again"} + Needs: "decide which copy to keep.", + Explanation: fmt.Sprintf("%s has live data on more than one machine and uses only one.", conditions.Capital(consumer)), + Resolved: conditions.Capital(consumer) + "'s data is in one place again"} }), // Deliveries and walks. "stalled": worded(func(o conditions.Observation) words { if o.Scope == conditions.ScopeDelivery { return words{Headline: "A delivery is held too long", - Explanation: "A delivery has been held past its time limit. " + conditions.ResolverWords(o), - Resolved: "Resolved: the delivery moves again"} + Explanation: "A delivery has been held past its time limit.", Needs: conditions.ResolverNeeds(o), + Resolved: "Resolved: the delivery moves again"} } return words{Headline: "A delivery is stuck halfway", - Explanation: "Its walk across the machines has not moved for longer than usual. Nothing is lost; if it " + - "stays, an agent can look at why.", - Resolved: "Resolved: the delivery moves again"} + Explanation: "Its walk across the machines has not moved for longer than usual. Nothing is lost.", + Resolved: "Resolved: the delivery moves again"} }), kindWalkWaiting: worded(func(o conditions.Observation) words { return words{Headline: "A delivery is waiting to start", Explanation: "A merged change is built, and mesh-delivery (the module that decides when a delivery goes " + - "out) has not said it may start. Nothing to do yet; an agent can start it by hand.", + "out) has not let it start yet.", Resolved: "Resolved: the delivery is no longer waiting"} }), "merge-not-acted": worded(func(o conditions.Observation) words { return words{Headline: "A merge was never picked up", Explanation: "A pull request was merged, and the controller never heard of it, so nothing was built or " + - "sent. An agent can hand it over again.", + "sent. The mesh catches up on missed merges by itself.", Resolved: "Resolved: the merge was picked up"} }), "ask-lost": worded(func(o conditions.Observation) words { return words{Headline: "A build has no result", - Explanation: "A build was asked for and never answered. What it was for is not delivered until it is " + - "built again.", - Resolved: "Resolved: the build has its result"} + Explanation: "A build was asked for and never answered. It is asked again with the next delivery.", + Resolved: "Resolved: the build has its result"} }), kindRolledBack: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") @@ -336,68 +348,73 @@ var plainWordings = map[string]func(conditions.Observation) words{ if o.Scope == conditions.ScopeCore { return words{Headline: "A core update was put back on " + m, Explanation: fmt.Sprintf("A new build of the mesh's own %s did not become healthy on %s, so the build "+ - "before was put back. It needs a look now.", module, m), + "before was put back and runs.", module, m), Resolved: "Resolved: the core on " + m + " is healthy"} } return words{Headline: conditions.Capital(module) + " update put back on " + m, Explanation: fmt.Sprintf("The new build of %s did not become healthy on %s, so the mesh put back the one "+ - "before. The change is not delivered; it needs a fix in its code.", module, m), + "before, which runs. The change is not delivered until it is fixed.", module, m), Resolved: "Resolved: " + module + " on " + m + " is settled"} }), kindRollbackFailed: worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "Putting back an update failed on " + m, - Explanation: fmt.Sprintf("A build that failed on %s could not be put back to the one before. What runs "+ - "there may be broken; it needs you now.", m), - Resolved: "Resolved: " + m + " runs a good build again"} + Needs: fmt.Sprintf("check what runs on %s; the details say which build.", m), + Explanation: fmt.Sprintf("A build that failed on %s could not be put back to the one before.", m), + Resolved: "Resolved: " + m + " runs a good build again"} }), "release-held": worded(func(o conditions.Observation) words { return words{Headline: "Updates wait for your release", - Explanation: "Some module updates wait for a person to release them. They are not delivered until you do.", + Needs: "release them, or leave them held.", + Explanation: "Some module updates wait for a person to release them, and are not delivered until then.", Resolved: "Resolved: the held updates are released"} }), "facts-stale": worded(func(o conditions.Observation) words { return words{Headline: "Merge checks use outdated facts", - Explanation: "The facts a merge check judges a change against are out of date, so a check may pass or " + - "fail for the wrong reason.", + Explanation: "The facts a merge check judges a change against are out of date; they are gathered again " + + "by themselves.", Resolved: "Merge checks use current facts again"} }), // The controller and the core. "controller-deaf": worded(func(o conditions.Observation) words { return words{Headline: "The controller stopped listening", + Needs: "restart the controller if this stays.", Explanation: "The controller, which coordinates the mesh, has taken no messages for minutes while some " + "wait. Changes and repairs do not happen until it recovers.", Resolved: "The controller listens again"} }), "self-check-silent": worded(func(o conditions.Observation) words { return words{Headline: "The mesh's self-check stopped", + Needs: "restart the controller if this stays.", Explanation: "The self-check, which looks over the whole mesh every few minutes, has not finished a run. " + "Problems may go unnoticed until it runs again.", Resolved: "The self-check runs again"} }), "watchdogs-silent": worded(func(o conditions.Observation) words { return words{Headline: "The mesh's watchdogs stopped", - Explanation: "The watchdogs, which notice when something expected does not happen, have not run. Missed " + - "signals are not being noticed.", + Needs: "restart the controller if this stays.", + Explanation: "The watchdogs, which notice when something expected does not happen, have not run, so " + + "missed signals are not noticed.", Resolved: "The watchdogs run again"} }), "lease-lost": worded(func(o conditions.Observation) words { return words{Headline: "The controller lost its lease", + Needs: "make sure only one controller runs; the details say which machines claim it.", Explanation: "The controller holds a lease so that only one copy of it acts at a time. It lost or could " + - "not renew it, so two could act at once, or none. It needs a look now.", + "not renew it, so two could act at once, or none.", Resolved: "The controller holds its lease again"} }), "lease-split": worded(func(o conditions.Observation) words { return words{Headline: "Two controllers may be acting", - Explanation: "The lease that lets one controller act at a time does not agree with its record, so two " + - "could act at once. It needs a look now.", - Resolved: "One controller acts again"} + Needs: "make sure only one controller runs; the details say which machines claim it.", + Explanation: "The lease that lets one controller act at a time does not agree with its record.", + Resolved: "One controller acts again"} }), "stale-writer": worded(func(o conditions.Observation) words { return words{Headline: "Outdated instructions are being sent", Explanation: "Something kept sending instructions older than what the machines already hold, and they " + - "were refused. It is harmless if it stops.", + "were refused, which is harmless.", Resolved: "Resolved: no more outdated instructions"} }), "status-slow": worded(func(o conditions.Observation) words { @@ -408,32 +425,32 @@ var plainWordings = map[string]func(conditions.Observation) words{ kindCoreUnhealthy: worded(func(o conditions.Observation) words { if o.Scope == conditions.ScopeBus { return words{Headline: "The bus is not healthy", + Needs: "check the machine the bus runs on; the details say what fails.", Explanation: "The bus, which carries every message in the mesh, is not healthy. Instructions, builds " + "and tool calls may fail until it recovers.", Resolved: "The bus is healthy again"} } m := machineOr(o, "its machine") return words{Headline: "The mesh's own software fails on " + m, - Explanation: fmt.Sprintf("A part of the mesh's own software on %s is not healthy. What it does there may "+ - "not happen until it recovers.", m), - Resolved: "The mesh's own software on " + m + " is healthy again"} + Explanation: fmt.Sprintf("A part of the mesh's own software on %s is not healthy; it is restarted by itself.", m), + Resolved: "The mesh's own software on " + m + " is healthy again"} }), "call-hung": worded(func(o conditions.Observation) words { return words{Headline: "A tool call is hanging", - Explanation: "A call to one of the mesh's tools has run far past its time limit. Whatever waits on it is " + - "stuck.", - Resolved: "Resolved: the tool call ended"} + Explanation: "A call to one of the mesh's tools has run far past its time limit; it is ended by itself.", + Resolved: "Resolved: the tool call ended"} }), "probe-failed": worded(func(o conditions.Observation) words { return words{Headline: "A check of the mesh could not run", - Explanation: "One of the mesh's own checks could not run, so what it watches is unknown, which is not " + - "the same as fine.", + Explanation: "One of the mesh's own checks could not run, so what it watches is unknown for now. It runs " + + "again every few minutes.", Resolved: "The check runs again"} }), kindHealersBraked: worded(func(o conditions.Observation) words { return words{Headline: "All automatic repairs stopped", + Needs: "read the details and decide whether the repairs may run again.", Explanation: "The healers (the mesh's automatic repairs) acted more often in an hour than allowed, which " + - "looks like a loop, so all of them stopped. Nothing repairs itself until this is looked at.", + "looks like a loop, so all of them stopped.", Resolved: "Automatic repairs run again"} }), "healer-wanted": worded(func(o conditions.Observation) words { @@ -442,8 +459,8 @@ var plainWordings = map[string]func(conditions.Observation) words{ cause = "something" } return words{Headline: conditions.Capital(strings.ReplaceAll(cause, ".", " ")) + " keeps being fixed by hand", - Explanation: "A person keeps repairing this by hand. A healer (an automatic repair) is wanted for it; " + - "nothing is broken now.", + Explanation: "A person keeps repairing this by hand, and an automatic repair is wanted for it. Nothing is " + + "broken now.", Resolved: "Resolved: no more hand repairs of " + strings.ReplaceAll(cause, ".", " ")} }), @@ -451,8 +468,9 @@ var plainWordings = map[string]func(conditions.Observation) words{ "resolver-wrong": worded(func(o conditions.Observation) words { m := machineOr(o, "a machine") return words{Headline: "Name lookups fail on " + m, - Explanation: fmt.Sprintf("The mesh's name resolver on %s does not answer machine names correctly. "+ - "Machines that rely on it may not find each other.", m), + Needs: fmt.Sprintf("check that %s is on and online.", m), + Explanation: fmt.Sprintf("The mesh's name resolver on %s does not answer machine names correctly, so "+ + "machines that rely on it may not find each other.", m), Resolved: "Name lookups work on " + m + " again"} }), "holder-silent": worded(func(o conditions.Observation) words { @@ -468,50 +486,47 @@ var plainWordings = map[string]func(conditions.Observation) words{ }), kindBusObjectsUnasserted: worded(func(o conditions.Observation) words { return words{Headline: "The bus could not be fully set up", - Explanation: "When instructions were sent, the bus's queues could not all be checked, so a module may " + - "not get its messages.", + Explanation: "When instructions were sent, the bus's queues could not all be checked; they are checked " + + "again with the next send.", Resolved: "The bus is fully set up again"} }), kindBusMaintenance: worded(func(o conditions.Observation) words { return words{Headline: "The bus is being upgraded", - Explanation: "The mesh's message system is being upgraded; some things pause until it is done. Nothing " + - "to do.", - Resolved: "The bus upgrade is done"} + Explanation: "The mesh's message system is being upgraded; some things pause until it is done.", + Resolved: "The bus upgrade is done"} }), kindBusUpgradeFailed: worded(func(o conditions.Observation) words { return words{Headline: "The bus upgrade failed", - Explanation: "The upgrade of the mesh's message system did not end healthy in time. It needs you: it can " + - "be put back to the version before.", - Resolved: "Resolved: the bus is healthy after its upgrade"} + Needs: "decide whether to put the bus back to the version before; the details say how.", + Explanation: "The upgrade of the mesh's message system did not end healthy in time.", + Resolved: "Resolved: the bus is healthy after its upgrade"} }), kindConsumerBehind: worded(func(o conditions.Observation) words { return words{Headline: "Messages pile up for a listener", Explanation: "One of the mesh's listeners on the bus is far behind, so what it handles happens late. A " + - "healer may restart it.", + "healer restarts it if it stays.", Resolved: "The listener caught up"} }), "consumer-wrong": worded(func(o conditions.Observation) words { return words{Headline: "A listener on the bus is set up wrong", - Explanation: "One of the mesh's listeners on the bus is missing or not as the controller defines it, so " + - "some messages may reach nobody.", + Explanation: "One of the mesh's listeners on the bus is missing or not as defined; the next send sets " + + "it up again.", Resolved: "The listener is set up right again"} }), "consumer-lost": worded(func(o conditions.Observation) words { return words{Headline: "A listener on the bus is gone", - Explanation: "One of the mesh's listeners is no longer on the bus, so what it should receive reaches " + - "nobody.", - Resolved: "The listener is back"} + Explanation: "One of the mesh's listeners is no longer on the bus; the next send sets it up again.", + Resolved: "The listener is back"} }), "slow-consumer": worded(func(o conditions.Observation) words { return words{Headline: "A listener on the bus is too slow", - Explanation: "The bus reports a listener too slow to keep up, so messages to it are dropped or late.", + Explanation: "The bus reports a listener too slow to keep up, so messages to it are late.", Resolved: "The listener keeps up again"} }), "max-deliveries": worded(func(o conditions.Observation) words { return words{Headline: "A message could not be handled", - Explanation: "The bus gave up on a message after trying to hand it over too many times. What it carried " + - "did not happen.", - Resolved: "Resolved: messages are handled again"} + Explanation: "The bus gave up on a message after trying to hand it over too many times.", + Resolved: "Resolved: messages are handled again"} }), "refused": worded(func(o conditions.Observation) words { return words{Headline: "The bus refuses some messages", @@ -520,21 +535,19 @@ var plainWordings = map[string]func(conditions.Observation) words{ }), "stream-wrong": worded(func(o conditions.Observation) words { return words{Headline: "Part of the bus's storage is wrong", - Explanation: "A store the controller keeps on the bus is missing or not as defined, so what it keeps " + - "there may be lost.", - Resolved: "The bus's storage is right again"} + Needs: "check the machine the bus runs on; the details say what is missing.", + Explanation: "A store the controller keeps on the bus is missing or not as defined, so what it keeps there may be lost.", + Resolved: "The bus's storage is right again"} }), "archives-unheld": worded(func(o conditions.Observation) words { return words{Headline: "Kept builds are about to be cleaned up", - Explanation: "Some kept builds are not claimed by any module, so the store's cleanup would delete them. " + - "Nothing to do unless one is still needed.", - Resolved: "Resolved: every kept build is claimed"} + Explanation: "Some kept builds are not claimed by any module, so the store's cleanup would delete them.", + Resolved: "Resolved: every kept build is claimed"} }), "archives-missing": worded(func(o conditions.Observation) words { return words{Headline: "Kept builds are missing", - Explanation: "Some builds the mesh relies on are no longer in the store. A machine that needs one cannot " + - "get it until it is built again.", - Resolved: "Resolved: the kept builds are back"} + Explanation: "Some builds the mesh relies on are no longer in the store; they are built again when needed.", + Resolved: "Resolved: the kept builds are back"} }), } @@ -602,18 +615,68 @@ func deliveryName(modules []string, repository string) string { return repoName(repository) + " delivery" } -// waitingAct is what the operator does about a walk waiting for its delivery's word. -func waitingAct(severity conditions.Severity) string { +// walkWaitingWords explains a walk waiting for its delivery's word. +func walkWaitingWords(w waitFacts, in time.Duration, severity conditions.Severity) string { + what := deliveryWhat(w.modules, w.repository) if severity == conditions.Urgent { - return "Mesh-delivery may be broken. It needs you: have an agent look at mesh-delivery, or start the " + - "delivery by hand." + return fmt.Sprintf("The change to %s is merged and built, and mesh-delivery (the module that decides when a "+ + "delivery goes out) has not let it start for %s, so mesh-delivery may be stuck.", what, humanDuration(in)) } - return fmt.Sprintf("Nothing to do yet; it becomes urgent after %s. To start it now, have an agent start it by hand.", - humanDuration(waitUrgentAfter)) + return fmt.Sprintf("The change to %s is merged and built, and has waited %s for mesh-delivery (the module that "+ + "decides when a delivery goes out) to let it start. It becomes a question for you if it still waits after %s.", + what, humanDuration(in), humanDuration(waitUrgentAfter)) +} + +// waitingNeeds is what the operator does about a walk waiting past its urgent bound: nothing before it. +func waitingNeeds(severity conditions.Severity) string { + if severity == conditions.Urgent { + return "start it, or stop it." + } + return "" +} + +// waitingActions are the answers to a walk waiting past its urgent bound: the controller's own verb, since +// the module that should have said go is the one not answering. +func waitingActions(w waitFacts, severity conditions.Severity) []conditions.Action { + if severity != conditions.Urgent { + return nil + } + return []conditions.Action{ + {Label: "Start", Verb: "mesh-controller.plans", Arguments: map[string]string{"go": w.id, "why": ""}}, + {Label: "Stop", Verb: "mesh-controller.plans", Arguments: map[string]string{"stop": w.id, "why": ""}}, + } +} + +// moduleNeeds is what the operator can do about a module unhealthy on a machine: log in again where its +// account's groups wait for it (ADR 0252), restart a failed service, or nothing where the mesh restarts it. +func moduleNeeds(node string, rs []inventory.ResourceHealth) (string, []conditions.Action) { + var actions []conditions.Action + for _, r := range rs { + if strings.Contains(r.Reason, "relogin needed") { + return fmt.Sprintf("log out of every session on %s and log in again.", node), nil + } + if r.Kind == link.KindUnit && len(actions) < 2 { + scope := "system" + if strings.Contains(r.Reason, "account's own") { + scope = "user" + } + label := "Restart" + if len(actions) > 0 { + label = "Restart " + unitPlainWords(r.Target) + } + actions = append(actions, conditions.Action{Label: label, Verb: "node-service-manager.restart", + Machine: node, Arguments: map[string]string{"unit": r.Target, "scope": scope}}) + } + } + if len(actions) > 0 { + return "restart it; if it fails again, the details say why.", actions + } + return "", nil } // stalledWords are the plain words of a delivery held past its bound, as mesh-delivery says it. -func stalledWords(l stalledLine, o conditions.Observation) (string, string, string) { +func stalledWords(l stalledLine, o conditions.Observation) (headline, explanation, resolved, needs string, + actions []conditions.Action) { repository, _, _ := strings.Cut(l.ID, "@") name := repoName(repository) held := l.State @@ -624,13 +687,24 @@ func stalledWords(l stalledLine, o conditions.Observation) (string, string, stri if d, err := time.ParseDuration(l.For); err == nil { long = "for " + humanDuration(d) } - act := conditions.ResolverWords(o) if o.Resolver == conditions.ResolverOperator { - act = "It waits for you: release it, or stop it." + switch held { + case "held": + needs = "release it, or stop it." + actions = []conditions.Action{ + {Label: "Release", Verb: "mesh-delivery.release", Arguments: map[string]string{"id": l.ID, "why": ""}}, + {Label: "Stop", Verb: "mesh-delivery.stop", Arguments: map[string]string{"id": l.ID, "why": ""}}, + } + case "ready", "checked": + needs = "merge its pull request, or close it." + default: + needs = "stop it, or read the details to see what it waits for." + actions = []conditions.Action{{Label: "Stop", Verb: "mesh-delivery.stop", Arguments: map[string]string{"id": l.ID, "why": ""}}} + } } return fmt.Sprintf("Delivery of %s %s %s", name, held, long), - fmt.Sprintf("A delivery of %s has been %s %s, past its limit. %s", name, held, long, act), - fmt.Sprintf("Delivery of %s is no longer %s", name, held) + fmt.Sprintf("A delivery of %s has been %s %s, past its limit.", name, held, long), + fmt.Sprintf("Delivery of %s is no longer %s", name, held), needs, actions } // causeWords is a hand-act's cause as a person says it. diff --git a/cmd/mesh-controller/plain_words_test.go b/cmd/mesh-controller/plain_words_test.go index 8c73ba59..8a2c653a 100644 --- a/cmd/mesh-controller/plain_words_test.go +++ b/cmd/mesh-controller/plain_words_test.go @@ -14,29 +14,40 @@ import ( // each keeps its summary for whoever looks closer, and now carries a headline, an explanation and a // resolved line the operator reads at a glance — no plan id, commit, key, verb or clock time in them. -// plainExample checks one finding's words: plain, within their bounds, and saying what the operator needs. -func plainExample(t *testing.T, o conditions.Observation, headline string, says ...string) { +// plainExample checks one finding's words as the keeper will keep them: plain, within their bounds, +// opened by the verdict, and saying what the operator needs; and its actions by label. +func plainExample(t *testing.T, o conditions.Observation, headline, explanation string, actions ...string) { t.Helper() machines := append([]string{o.Machine}, o.Also...) - w := conditions.Words{Headline: o.Headline, Explanation: o.Explanation, Resolved: o.Resolved} + w := conditions.Words{Headline: o.Headline, Explanation: o.Explanation, Resolved: o.Resolved, Needs: o.Needs, + Actions: o.Actions} if why, ok := conditions.PlainWords(w, machines...); !ok { t.Errorf("%s: not plain: %s\n %+v", o.Key(), why, w) } - if o.Headline != headline { - t.Errorf("%s: headline %q, want %q", o.Key(), o.Headline, headline) + said := conditions.Verdict(o.Needs, o.Explanation) + if o.Headline != headline || said != explanation { + t.Errorf("%s: says\n %q\n %q\nwant\n %q\n %q", o.Key(), o.Headline, said, headline, explanation) } - for _, s := range says { - if !strings.Contains(o.Explanation+" | "+o.Resolved, s) { - t.Errorf("%s: the words do not say %q:\n %s | %s", o.Key(), s, o.Explanation, o.Resolved) - } + var labels []string + for _, a := range o.Actions { + labels = append(labels, a.Label) } - t.Logf("\nBEFORE: %s\nAFTER: %s\n %s\nCLEARS: %s", o.Summary, o.Headline, o.Explanation, o.Resolved) + if strings.Join(labels, ",") != strings.Join(actions, ",") { + t.Errorf("%s: actions %v, want %v", o.Key(), labels, actions) + } + quiet := "" + if o.Needs == "" && o.Severity == conditions.Warning { + quiet = " (needs nothing and is a warning: no popup; it stays in conditions and the history)" + } + t.Logf("\nBEFORE: %s\nAFTER: %s%s\n %s\n actions %v\nCLEARS: %s", o.Summary, o.Headline, quiet, + said, labels, o.Resolved) } // **A delivery waiting**: the popup read "the walk of novox/mesh-catalog a6385479 has waited 56m0s for // mesh-delivery's word to start: `mesh-delivery.show` for the delivery that landed as a6385479 says why; -// `plans go plan-1791454185265004861 --why …` starts it by hand". -func TestADeliveryWaitingIsSaidByItsModulesAndWhatToDo(t *testing.T) { +// `plans go plan-1791454185265004861 --why …` starts it by hand". Under four hours it needs nothing — no +// popup; past them, the operator starts or stops it from the notification. +func TestADeliveryWaitingNeedsNothingUntilItsBoundThenOffersStartAndStop(t *testing.T) { now := time.Date(2026, 10, 8, 11, 36, 0, 0, time.UTC) f := calm(now) f.waits = []waitFacts{{id: "plan-1791454185265004861", repository: "novox/mesh-catalog", commit: "a6385479c0ffee", @@ -45,36 +56,59 @@ func TestADeliveryWaitingIsSaidByItsModulesAndWhatToDo(t *testing.T) { if len(got) != 1 { t.Fatalf("%+v", got) } - plainExample(t, got[0], "openrazer delivery waiting to start", "56 minutes", "mesh-delivery (the module that decides", - "Nothing to do yet", "openrazer delivery no longer waiting") + plainExample(t, got[0], "openrazer delivery waiting to start", + "Nothing for you to do. The change to openrazer is merged and built, and has waited 56 minutes for "+ + "mesh-delivery (the module that decides when a delivery goes out) to let it start. It becomes a question "+ + "for you if it still waits after 4 hours.") if !strings.Contains(got[0].Summary, "plans go plan-1791454185265004861") { t.Errorf("the summary lost the way on for whoever looks closer: %q", got[0].Summary) } - // Past four hours it is urgent, and says it needs the operator. + // Past four hours it is urgent, and offers the controller's own answers. f.waits[0].since = now.Add(-5 * time.Hour) got = watchWaits(f) - plainExample(t, got[0], "openrazer delivery waiting to start", "It needs you") + plainExample(t, got[0], "openrazer delivery waiting to start", + "Needs you: start it, or stop it. The change to openrazer is merged and built, and mesh-delivery (the "+ + "module that decides when a delivery goes out) has not let it start for 5 hours, so mesh-delivery may "+ + "be stuck.", "Start", "Stop") + if a := got[0].Actions[0]; a.Verb != "mesh-controller.plans" || a.Arguments["go"] != "plan-1791454185265004861" { + t.Errorf("start: %+v", a) + } + if a := got[0].Actions[1]; a.Verb != "mesh-controller.plans" || a.Arguments["stop"] != "plan-1791454185265004861" { + t.Errorf("stop: %+v", a) + } // Many modules are counted, not listed in the headline. f.waits[0].modules = []string{"a", "b", "c", "d"} got = watchWaits(f) - plainExample(t, got[0], "mesh-catalog delivery waiting to start", "4 modules of mesh-catalog") + if got[0].Headline != "mesh-catalog delivery waiting to start" || !strings.Contains(got[0].Explanation, "4 modules of mesh-catalog") { + t.Errorf("%+v", got[0]) + } } // **A module unhealthy**: "openrazer on g14 is not healthy: its unit openrazer-daemon.service failed in the -// account's own service manager (exit-code)". -func TestAModuleUnhealthyNamesItsServiceInWords(t *testing.T) { +// account's own service manager (exit-code)". The operator restarts it from the notification. +func TestAModuleUnhealthyOffersARestartOfItsService(t *testing.T) { o := moduleUnhealthyObservation("openrazer", "g14", []inventory.ResourceHealth{{Kind: link.KindUnit, Resource: "openrazer-daemon", Target: "openrazer-daemon.service", Reason: "failed in the account's own service manager (exit-code)", Since: time.Now()}}) - plainExample(t, o, "openrazer not working on g14", "is not healthy: its service openrazer-daemon stopped with an error", - "openrazer works again on g14") + plainExample(t, o, "openrazer not working on g14", + "Needs you: restart it; if it fails again, the details say why. openrazer on g14 is not healthy: its "+ + "service openrazer-daemon stopped with an error. It clears as soon as it runs again.", "Restart") + if a := o.Actions[0]; a.Verb != "node-service-manager.restart" || a.Machine != "g14" || + a.Arguments["unit"] != "openrazer-daemon.service" || a.Arguments["scope"] != "user" { + t.Errorf("restart: %+v", a) + } + // An account waiting for a new login (ADR 0252) asks for the login, which no button can give. + o = moduleUnhealthyObservation("openrazer", "g14", []inventory.ResourceHealth{{Kind: "account", + Resource: "operator-in-group", Target: "jochen", Reason: "relogin needed: the account is in the group"}}) + if o.Needs != "log out of every session on g14 and log in again." || len(o.Actions) != 0 { + t.Errorf("relogin: %q %+v", o.Needs, o.Actions) + } } // **Failed units on a machine**: "shanks's service manager is degraded: 3 failed unit(s) no module places — -// mnt-recalbox.mount, storage-media.mount, greenclip.service (the account's own manager). Each is the -// machine's own: mend or remove it there, or have a module place it". +// mnt-recalbox.mount, storage-media.mount, greenclip.service (the account's own manager). …" func TestFailedUnitsOnAMachineAreNamedWithoutTheirSuffixes(t *testing.T) { o, raise := machineUnitsObservation("shanks", &link.UnitsHealth{State: "degraded", Failed: []link.FailedUnit{ {Unit: "mnt-recalbox.mount", Result: "exit-code"}, {Unit: "storage-media.mount", Result: "exit-code"}, @@ -83,12 +117,14 @@ func TestFailedUnitsOnAMachineAreNamedWithoutTheirSuffixes(t *testing.T) { t.Fatal("not raised") } plainExample(t, o, "3 failed services on shanks", - "mnt-recalbox (a mount), storage-media (a mount) and greenclip failed", "mend or remove them on shanks") + "Needs you: mend or remove them on shanks, or silence this if they do not matter. On shanks, "+ + "mnt-recalbox (a mount), storage-media (a mount) and greenclip failed. No module manages them, so the "+ + "mesh does not repair them.", "Silence for a week") } -// **A healer wanted**: "\"push\" was repaired by hand 35 times in 14 days, the last by g14.node-tools, -// through the mesh-controller seat: a healer is wanted for it". -func TestAHealerWantedSaysNothingIsBroken(t *testing.T) { +// **A healer wanted**: "\"push\" was repaired by hand 35 times in 14 days, the last by g14.node-tools, through +// the mesh-controller seat: a healer is wanted for it". Nothing is broken: no popup. +func TestAHealerWantedNeedsNothingFromTheOperator(t *testing.T) { now := time.Date(2026, 10, 8, 12, 0, 0, 0, time.UTC) f := calm(now) for i := 0; i < 35; i++ { @@ -100,15 +136,22 @@ func TestAHealerWantedSaysNothingIsBroken(t *testing.T) { if len(got) != 1 { t.Fatalf("%+v", got) } - plainExample(t, got[0], "Push keeps being fixed by hand", "35 times in 14 days", "nothing is broken now") + plainExample(t, got[0], "Push keeps being fixed by hand", + "Nothing for you to do. A person repaired push by hand 35 times in 14 days, so an automatic repair is "+ + "wanted for it. Nothing is broken now.") } // **A delivery held past its bound**, as mesh-delivery says it: "the delivery novox/hq@055550802096 has been // held for 36h2m6s, past its bound of 24h0m0s (it waits for the operator): healer H2 may none: …". -func TestADeliveryHeldSaysItWaitsForTheOperator(t *testing.T) { +func TestADeliveryHeldOffersReleaseAndStop(t *testing.T) { got := stalledObservations([]stalledLine{{ID: "novox/hq@055550802096", State: "held", For: "36h2m6s", Bound: "24h0m0s", H2: "none: the state is the operator's", Says: "it waits for the operator"}}) - plainExample(t, got[0], "Delivery of hq held for 36 hours", "It waits for you: release it, or stop it.") + plainExample(t, got[0], "Delivery of hq held for 36 hours", + "Needs you: release it, or stop it. A delivery of hq has been held for 36 hours, past its limit.", + "Release", "Stop") + if a := got[0].Actions[0]; a.Verb != "mesh-delivery.release" || a.Arguments["id"] != "novox/hq@055550802096" { + t.Errorf("release: %+v", a) + } } // **Every kind the controller raises has plain words**, and its words are plain for a subject of every @@ -134,6 +177,7 @@ func TestEveryWordingIsPlain(t *testing.T) { for _, s := range subjects { s.Kind = kind w := fn(s) + w.Explanation = conditions.Verdict(w.Needs, w.Explanation) if why, ok := conditions.PlainWords(w, s.Machine); !ok { t.Errorf("%s about %s %s: %s\n %+v", kind, s.Scope, s.ID, why, w) } diff --git a/cmd/mesh-controller/signals.go b/cmd/mesh-controller/signals.go index 64805f2d..1ea068d3 100644 --- a/cmd/mesh-controller/signals.go +++ b/cmd/mesh-controller/signals.go @@ -324,7 +324,7 @@ func watchPlans(f *signalFacts) []conditions.Observation { out = append(out, conditions.Observation{Scope: conditions.ScopePlan, ID: p.id, Kind: "stalled", Headline: "Delivery of " + repoName(p.repository) + " is stuck halfway", Explanation: fmt.Sprintf("Its walk across the machines has been at the same step for %s, longer than "+ - "usual. Nothing is lost; if it stays, an agent can look at why.", humanDuration(f.now.Sub(p.entered))), + "usual. Nothing is lost, and the mesh keeps it where it is.", humanDuration(f.now.Sub(p.entered))), Resolved: "Delivery of " + repoName(p.repository) + " moves again", Severity: conditions.Warning, Summary: fmt.Sprintf("the plan for %s %s has been at tier %d of %d since %s (bound %s): %s", @@ -357,12 +357,12 @@ func watchWaits(f *signalFacts) []conditions.Observation { Summary: fmt.Sprintf("the walk of %s %s has waited %s for %s's word to start: `mesh-delivery.show` for the "+ "delivery that landed as %s says why; `plans go %s --why …` starts it by hand", w.repository, short(w.commit), ago(in), w.awaits, short(w.commit), w.id), - Said: fmt.Sprintf("waiting since %s for %s", w.since.UTC().Format(time.RFC3339), w.awaits), - Headline: deliveryName(w.modules, w.repository) + " waiting to start", - Explanation: fmt.Sprintf("The change to %s is merged and built, and has waited %s for mesh-delivery (the "+ - "module that decides when a delivery goes out) to let it start. %s", deliveryWhat(w.modules, w.repository), - humanDuration(in), waitingAct(severity)), - Resolved: deliveryName(w.modules, w.repository) + " no longer waiting"}) + Said: fmt.Sprintf("waiting since %s for %s", w.since.UTC().Format(time.RFC3339), w.awaits), + Headline: deliveryName(w.modules, w.repository) + " waiting to start", + Explanation: walkWaitingWords(w, in, severity), + Needs: waitingNeeds(severity), + Actions: waitingActions(w, severity), + Resolved: deliveryName(w.modules, w.repository) + " no longer waiting"}) } return out } @@ -692,8 +692,8 @@ func watchHandActs(f *signalFacts) []conditions.Observation { repeated[cause], int(handActsWithin.Hours()/24), newest.By, wanted), Said: strings.Join(acts, "; "), Headline: conditions.Capital(causeWords(cause)) + " keeps being fixed by hand", - Explanation: fmt.Sprintf("A person repaired %s by hand %d times in %d days. A healer (an automatic repair) "+ - "is wanted for it; nothing is broken now.", causeWords(cause), repeated[cause], + Explanation: fmt.Sprintf("A person repaired %s by hand %d times in %d days, so an automatic repair is "+ + "wanted for it. Nothing is broken now.", causeWords(cause), repeated[cause], int(handActsWithin.Hours()/24)), Resolved: "Resolved: no more hand repairs of " + causeWords(cause)}) } diff --git a/internal/conditions/condition.go b/internal/conditions/condition.go index dff6e9b0..cc253a6a 100644 --- a/internal/conditions/condition.go +++ b/internal/conditions/condition.go @@ -134,6 +134,10 @@ type Condition struct { Headline string `json:"headline"` Explanation string `json:"explanation"` Resolved string `json:"resolved"` + // Needs is what the operator does about it, one sentence; empty when nothing (the explanation then + // opens "Nothing for you to do."). Actions are the answers a notification offers (plain.go). + Needs string `json:"needs"` + Actions []Action `json:"actions"` // Evidence is the newest observations, at most KeptEvidence, newest first. Evidence []Evidence `json:"evidence"` // Source is the signals-table row, probe or event that raised it: `S1`, `D3`, `provisioner.failing`. @@ -187,6 +191,8 @@ type Observation struct { Headline string Explanation string Resolved string + Needs string + Actions []Action // Said is this observation's evidence, in the mesh's words; Summary when empty. **Detail goes // here, never in Summary**: an address, a socket's error, a path or a name with its domain is // kept in the condition's evidence, which stays inside the mesh. The summary leaves it — to the diff --git a/internal/conditions/plain.go b/internal/conditions/plain.go index fa48800a..19ce4ee0 100644 --- a/internal/conditions/plain.go +++ b/internal/conditions/plain.go @@ -11,7 +11,12 @@ package conditions // g14"), the title of every message about it; // - an **explanation**: one or two plain sentences — what happened, what it means for the operator, // and whether they need to do anything; -// - a **resolved line**: the one short line said when it clears ("openrazer runs again on g14"). +// - a **resolved line**: the one short line said when it clears ("openrazer runs again on g14"); +// - a **verdict**, which every explanation opens with: "Nothing for you to do." or "Needs you:" and one +// concrete thing the operator can do themselves (needs). Never "have an agent …": the operator is not +// asked to open a session to understand or answer a notification; +// - **actions**: what the operator may answer from the notification itself (Release, Stop, Restart, +// Silence), each the seat verb the operator channel calls when it is chosen, naming the operator. // // They are made here, where the condition is made, so every channel gets them — the desktop today, // others later — and none has to guess what a key means. A producer may say them itself; otherwise the @@ -29,17 +34,45 @@ import ( "github.com/novox/mesh-controller/internal/outward" ) -// Words are what the operator reads of a condition. +// Words are what the operator reads of a condition. Explanation is said after the verdict, which +// plainly writes from Needs: empty is "Nothing for you to do.", else "Needs you: " and Needs. type Words struct { Headline string Explanation string Resolved string + Needs string + Actions []Action +} + +// Action is one answer the operator may give from a notification: a label, and the seat verb the +// operator channel calls with these arguments (and a why naming the operator and the label) when it is +// chosen. Machine is set for a seat every machine holds. An argument "why" given empty is the operator +// channel's to fill: it names the operator, the channel and the label chosen. +type Action struct { + Label string `json:"label"` + Verb string `json:"verb"` + Machine string `json:"machine,omitempty"` + Arguments map[string]string `json:"arguments,omitempty"` +} + +// The two verdicts an explanation opens with. +const ( + NothingToDo = "Nothing for you to do." + NeedsYou = "Needs you:" +) + +// SilenceAction is the action that stops a condition's messages for a week, with the operator's why: the +// answer to a condition the operator decided to live with. +func SilenceAction(key string) Action { + return Action{Label: "Silence for a week", Verb: "mesh-controller.conditions", + Arguments: map[string]string{"silence": key, "for": "7d", "why": ""}} } // Bounds of the plain words: a headline fits a notification's title line, an explanation two sentences. const ( HeadlineMax = 60 - ExplanationMax = 360 + ExplanationMax = 420 + NeedsMax = 120 ) var ( @@ -75,6 +108,7 @@ var ( goDuration = regexp.MustCompile(`\b[0-9]+(h[0-9]+m|m[0-9]+s|h[0-9]+m[0-9]+s)\b|\b[0-9]+(\.[0-9]+)?(ns|ms|µs)\b`) clockTime = regexp.MustCompile(`\b[0-9]{1,2}:[0-9]{2}\b|\b[0-9]{4}-[0-9]{2}-[0-9]{2}\b|\bUTC\b`) flag = regexp.MustCompile(`(^|\s)--?[a-z]`) + agentWord = regexp.MustCompile(`(?i)\bagents?\b|\bby hand\b|\bsession\b`) markup = regexp.MustCompile("[`*<>{}\\[\\]|#]|(^|\\s)_|_(\\s|$)") ) @@ -124,6 +158,27 @@ func PlainWords(w Words, machines ...string) (string, bool) { if len(w.Explanation) > ExplanationMax { return fmt.Sprintf("explanation: longer than %d characters", ExplanationMax), false } + for _, m := range agentWord.FindAllString(w.Explanation, -1) { + if !strings.EqualFold(m, "by hand") { // "repaired by hand" is a fact; telling to act by hand is not + return "explanation: sends the operator elsewhere (" + m + ")", false + } + } + if w.Needs != "" { + if why, ok := Plain(w.Needs, machines...); !ok { + return "needs: " + why, false + } + if m := agentWord.FindString(w.Needs); m != "" { + return "needs: not something the operator does themselves (" + m + ")", false + } + if len(w.Needs) > NeedsMax || !strings.HasSuffix(w.Needs, ".") { + return fmt.Sprintf("needs: one sentence of at most %d characters, ending in a full stop", NeedsMax), false + } + } + for _, a := range w.Actions { + if a.Label == "" || len(a.Label) > 24 || a.Verb == "" { + return fmt.Sprintf("action %q: a short label and a verb", a.Label), false + } + } if why, ok := Plain(w.Resolved, machines...); !ok { return "resolved: " + why, false } @@ -136,7 +191,8 @@ func PlainWords(w Words, machines ...string) (string, bool) { // plainly gives an observation its plain words: its own, its kind's, or its scope's. func plainly(o Observation) Observation { machines := append([]string{o.Machine}, o.Also...) - given := Words{o.Headline, o.Explanation, o.Resolved} + given := Words{Headline: o.Headline, Explanation: o.Explanation, Resolved: o.Resolved, Needs: o.Needs, + Actions: o.Actions} var w Words from := "" switch { @@ -154,6 +210,12 @@ func plainly(o Observation) Observation { if given.Resolved != "" { w.Resolved = given.Resolved } + if given.Needs != "" { + w.Needs = given.Needs + } + if len(given.Actions) > 0 { + w.Actions = given.Actions + } } } if w.Headline != "" && w.Resolved == "" { @@ -170,17 +232,27 @@ func plainly(o Observation) Observation { } w = scopeWords(o) } - o.Headline, o.Explanation, o.Resolved = w.Headline, w.Explanation, w.Resolved + o.Headline, o.Resolved, o.Needs, o.Actions = w.Headline, w.Resolved, w.Needs, w.Actions + o.Explanation = Verdict(w.Needs, w.Explanation) return o } -// Escalated is the sentence a condition's explanation ends with once a healer gave up on it. -const Escalated = "The mesh tried to repair it and could not: it needs you now." +// Verdict is an explanation opened by its verdict. +func Verdict(needs, explanation string) string { + if needs == "" { + return strings.TrimSpace(NothingToDo + " " + explanation) + } + return strings.TrimSpace(NeedsYou + " " + needs + " " + explanation) +} -// escalatedWords says in the explanation that a healer gave up, whatever the words said before. +// Escalated is what a condition needs once a healer gave up on it, where its words needed nothing. +const Escalated = "the mesh tried to repair this and could not; read the details to decide what to do." + +// escalatedWords turns "Nothing for you to do." into "Needs you:" once a healer gave up. func escalatedWords(c *Condition) { - if c.Escalated() && !strings.HasSuffix(c.Explanation, Escalated) { - c.Explanation = strings.TrimSpace(c.Explanation + " " + Escalated) + if c.Escalated() && c.Needs == "" { + c.Needs = Escalated + c.Explanation = Verdict(c.Needs, strings.TrimSpace(strings.TrimPrefix(c.Explanation, NothingToDo))) } } @@ -191,13 +263,14 @@ func scopeWords(o Observation) Words { what := strings.ReplaceAll(o.Kind, "-", " ") w := Words{ Headline: Capital(thing) + " needs a look", - Explanation: fmt.Sprintf("The mesh noticed a problem it calls %q with %s. %s", what, thing, ResolverWords(o)), + Explanation: fmt.Sprintf("The mesh noticed a problem it calls %q with %s.", what, thing), Resolved: "Resolved: " + thing + " is fine again", + Needs: ResolverNeeds(o), } if _, ok := PlainWords(w, append([]string{o.Machine}, o.Also...)...); !ok { w = Words{Headline: "Something in the mesh needs a look", - Explanation: "The mesh noticed a problem it has no plain words for yet. " + ResolverWords(o), - Resolved: "Resolved: the mesh is fine again"} + Explanation: "The mesh noticed a problem it has no plain words for yet.", + Resolved: "Resolved: the mesh is fine again", Needs: ResolverNeeds(o)} } return w } @@ -244,17 +317,12 @@ func ThingWords(o Observation) string { return "the mesh" } -// ResolverWords says whether the operator needs to act, from who resolves it. -func ResolverWords(o Observation) string { - switch { - case o.Resolver == ResolverOperator: - return "It needs you: the mesh does not repair this by itself." - case strings.HasPrefix(o.Resolver, "healer:"): - return "A healer is working on it; nothing to do unless it stays." - case o.Severity == Urgent: - return "It clears by itself once it is fixed, but needs a look now." +// ResolverNeeds is what the operator needs to do, from who resolves it: nothing, unless only a person can. +func ResolverNeeds(o Observation) string { + if o.Resolver == ResolverOperator { + return "the mesh does not repair this by itself; read the details to decide what to do." } - return "Nothing to do yet: it clears by itself once it is fixed." + return "" } // Capital is s with its first letter upper case. diff --git a/internal/conditions/plain_test.go b/internal/conditions/plain_test.go index 674187e4..9a129c67 100644 --- a/internal/conditions/plain_test.go +++ b/internal/conditions/plain_test.go @@ -79,7 +79,7 @@ func TestAConditionCarriesItsPlainWords(t *testing.T) { } said := settled(t, told, 1) body, _ := json.Marshal(said[0]) - for _, field := range []string{`"headline":"ace is not answering"`, `"explanation":"The mesh has not heard from it."`, + for _, field := range []string{`"headline":"ace is not answering"`, `"explanation":"Nothing for you to do. The mesh has not heard from it."`, `"resolved":"ace answers again"`} { if !strings.Contains(string(body), field) { t.Errorf("the event does not carry %s: %s", field, body) @@ -100,7 +100,7 @@ func TestAConditionCarriesItsPlainWords(t *testing.T) { // Words that are not plain, and a kind with none, are said from the scope — and reported. c, _ = k.Observe(t.Context(), Observation{Scope: ScopeModule, ID: "openrazer.g14", Token: "x", Kind: "test-unworded", Machine: "g14", Severity: Warning, Source: "health", Summary: "openrazer on g14 is not healthy"}) - if c.Headline != "Openrazer on g14 needs a look" || !strings.Contains(c.Explanation, "Nothing to do yet") { + if c.Headline != "Openrazer on g14 needs a look" || !strings.HasPrefix(c.Explanation, NothingToDo) { t.Errorf("the scope's words: %+v", c) } c, _ = k.Observe(t.Context(), Observation{Scope: ScopePlan, ID: "plan-1791454185265004861", Kind: "test-silent", @@ -113,13 +113,39 @@ func TestAConditionCarriesItsPlainWords(t *testing.T) { } } +// **An explanation opens with its verdict, and never sends the operator to an agent.** +func TestEveryExplanationOpensWithItsVerdict(t *testing.T) { + if got := Verdict("", "It may be asleep."); got != "Nothing for you to do. It may be asleep." { + t.Errorf("%q", got) + } + if got := Verdict("release it, or stop it.", "It is held."); got != "Needs you: release it, or stop it. It is held." { + t.Errorf("%q", got) + } + for _, w := range []Words{ + {Headline: "x waits", Explanation: "Have an agent start it.", Resolved: "x started"}, + {Headline: "x waits", Explanation: "It waits.", Needs: "start it by hand.", Resolved: "x started"}, + {Headline: "x waits", Explanation: "It waits.", Needs: "open a session and start it.", Resolved: "x started"}, + {Headline: "x waits", Explanation: "It waits.", Needs: "start it", Resolved: "x started"}, + {Headline: "x waits", Explanation: "It waits.", Resolved: "x started", Actions: []Action{{Label: "Start"}}}, + } { + if _, ok := PlainWords(w); ok { + t.Errorf("passed: %+v", w) + } + } + if why, ok := PlainWords(Words{Headline: "push keeps being fixed by hand", Explanation: "A person repaired " + + "push by hand 35 times.", Resolved: "Resolved", Needs: "release it, or stop it.", + Actions: []Action{{Label: "Release", Verb: "mesh-delivery.release"}}}); !ok { + t.Errorf("refused: %s", why) + } +} + // **A healer that gave up says so in the explanation**: the words of the kind said "nothing to do"; once the // budget is spent, the operator is needed. func TestAnEscalatedConditionSaysItNeedsTheOperator(t *testing.T) { k, _, _, _ := keeper(t) ctx := t.Context() o := Observation{Scope: ScopeMachine, ID: "ace", Kind: "silent", Machine: "ace", Severity: Warning, Source: "S1", - Summary: "ace is silent", Headline: "ace is not answering", Explanation: "Nothing to do yet."} + Summary: "ace is silent", Headline: "ace is not answering", Explanation: "It may be asleep."} if _, err := k.Observe(ctx, o); err != nil { t.Fatal(err) } @@ -127,11 +153,11 @@ func TestAnEscalatedConditionSaysItNeedsTheOperator(t *testing.T) { if err != nil { t.Fatal(err) } - if !strings.HasSuffix(c.Explanation, Escalated) { - t.Fatalf("escalated: %q", c.Explanation) + if want := "Needs you: " + Escalated + " It may be asleep."; c.Explanation != want || c.Needs != Escalated { + t.Fatalf("escalated: %q, want %q", c.Explanation, want) } c, _ = k.Observe(ctx, o) - if strings.Count(c.Explanation, Escalated) != 1 { + if strings.Count(c.Explanation, Escalated) != 1 || strings.Contains(c.Explanation, NothingToDo) { t.Errorf("seen again after escalation: %q", c.Explanation) } } diff --git a/internal/conditions/store.go b/internal/conditions/store.go index 9bcedc7e..ebecde5b 100644 --- a/internal/conditions/store.go +++ b/internal/conditions/store.go @@ -190,7 +190,7 @@ func (k *Keeper) Observe(ctx context.Context, o Observation) (Condition, error) if !found { c := Condition{Key: key, Kind: o.Kind, Subject: Subject{Scope: o.Scope, ID: o.ID, Machine: o.Machine, Also: o.Also}, Severity: o.Severity, Summary: o.Summary, Headline: o.Headline, Explanation: o.Explanation, - Resolved: o.Resolved, Evidence: []Evidence{{At: now, Said: said}}, + Resolved: o.Resolved, Needs: o.Needs, Actions: o.Actions, Evidence: []Evidence{{At: now, Said: said}}, Source: o.Source, Raised: now, LastObserved: now, Observations: 1, Count: 1, Resolver: orSelf(o.Resolver)} change := ChangeRaised @@ -240,7 +240,7 @@ func (k *Keeper) Observe(ctx context.Context, o Observation) (Condition, error) // The kind as the source says it now: a source that gave the same key a kind of its own since // (a probe's finding split out for a healer) is read by that kind from its next observation. c.Kind, c.Summary, c.Source, c.LastObserved = o.Kind, o.Summary, o.Source, now - c.Headline, c.Explanation, c.Resolved = o.Headline, o.Explanation, o.Resolved + c.Headline, c.Explanation, c.Resolved, c.Needs, c.Actions = o.Headline, o.Explanation, o.Resolved, o.Needs, o.Actions escalatedWords(&c) if o.Machine != "" { c.Subject.Machine = o.Machine