herdr-gentle-shell 1.5.0 → 1.5.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/DESIGN.md +4 -0
- package/README.md +15 -5
- package/extensions/gentle-herdr-state.ts +65 -25
- package/package.json +1 -1
package/DESIGN.md
CHANGED
|
@@ -804,6 +804,10 @@ gentle-ai concern and explicitly out of scope for this plugin.
|
|
|
804
804
|
the poll after the native one for the same question, a systematic
|
|
805
805
|
duplication. The ask token still drives the sidebar ask display; sounds,
|
|
806
806
|
suppression, and delay stay Herdr's.
|
|
807
|
+
- Herdr's own done/ask attention — the finished and needs-attention pop-ups and
|
|
808
|
+
their sound — is Herdr's native behavior, configured in Herdr itself (its
|
|
809
|
+
config and its settings). This package deliberately offers no switch for it;
|
|
810
|
+
its only notification surface is the optional Moshi channel.
|
|
807
811
|
- `review` and `error` never emit a plugin notification: `review` attention
|
|
808
812
|
stays in-flow/native; `error` is sidebar state only — our own `error:` label
|
|
809
813
|
with the pane left on native `working`, so neither the `NeedsAttention`
|
package/README.md
CHANGED
|
@@ -269,7 +269,10 @@ The one exception is a blocking synchronous subagent call: while a task-mode
|
|
|
269
269
|
`subagent_run`/`subagent_continue` is in flight the principal's own turn is
|
|
270
270
|
blocked on the child, so the producer publishes that child's role in
|
|
271
271
|
`gentle_pending_v1` and it renders instead of `gentle`, for as long as the
|
|
272
|
-
call lasts.
|
|
272
|
+
call lasts. A resume (`subagent_continue`) carries no agent, so its role is
|
|
273
|
+
the tracked task record's agent for its `task_id`; when neither the input nor
|
|
274
|
+
a record names one, the call publishes no role and the row keeps its generic
|
|
275
|
+
display. Background launches resolve their tool call immediately, so a
|
|
273
276
|
queued or running background delegate publishes no such marker and leaves
|
|
274
277
|
the principal's own display untouched. These yield to `ask`/`rdd`/`blocked`
|
|
275
278
|
and terminal `done` — where `done` needs
|
|
@@ -281,15 +284,17 @@ work total is a direct projection of the
|
|
|
281
284
|
Gentle Shell TaskStore `running` records (only `running` counts as
|
|
282
285
|
executing; queued/waiting never count), never a calculated
|
|
283
286
|
pending-call estimate: pending tool calls are role-only display hints (exact
|
|
284
|
-
in-flight subagent agent -> role slug,
|
|
287
|
+
in-flight subagent agent -> role slug, resolved from the tool input or, for a
|
|
288
|
+
resume, from the tracked task record, so task-mode launches show the active
|
|
285
289
|
role even at count 0) plus label correlation, and
|
|
286
290
|
true concurrent tasks all count. A live `running` record is never regressed
|
|
287
291
|
by a racy non-final status read (only the authoritative launch outcomes,
|
|
288
292
|
completions, and presence terminals move it), so principal activity with
|
|
289
293
|
live delegates keeps `gentle` while an idle principal keeps the role word; a
|
|
290
294
|
sanitized unknown slug exactly
|
|
291
|
-
equal to `working` degrades to `gentle` (
|
|
292
|
-
renders
|
|
295
|
+
equal to `working` or `subagent` degrades to `gentle` (neither bare word ever
|
|
296
|
+
renders; `subagent` is the producer's launch-correlation placeholder, never
|
|
297
|
+
an agent name).
|
|
293
298
|
Background launches (`subagent_run` with `mode: background`) announce
|
|
294
299
|
lifecycle over `message_end` custom results: an ACTIVE status promotes the
|
|
295
300
|
start into the tasks map like a task-mode record, so an active background
|
|
@@ -449,7 +454,12 @@ See [DESIGN.md](DESIGN.md) §4 (producer) and §5 (consumer), and
|
|
|
449
454
|
shows the single `Sidebar agent rows` row, and the only Moshi switch is the
|
|
450
455
|
`Notifications` row under `Moshi notifications`. The two are never mixed —
|
|
451
456
|
`Sidebar agent rows` neither reads nor writes `gentle-moshi.json`, so turning
|
|
452
|
-
the agent rows off never turns the notification channel off.
|
|
457
|
+
the agent rows off never turns the notification channel off. Herdr's own
|
|
458
|
+
done/ask attention (the finished and needs-attention pop-ups and their
|
|
459
|
+
sound) is Herdr's native behavior, configured in Herdr itself — its config
|
|
460
|
+
and its settings — and this package deliberately offers no switch for it:
|
|
461
|
+
the optional Moshi channel below is the only notification surface the
|
|
462
|
+
package owns. The plain
|
|
453
463
|
two-step menu stays as the fallback
|
|
454
464
|
when the TUI helpers or `ctx.ui.custom` are unavailable.
|
|
455
465
|
`Sidebar agent rows` drives the Herdr plugin's own `bin/configure.js`
|
|
@@ -73,10 +73,13 @@
|
|
|
73
73
|
// gentle_names_v1 = CSV of TaskRecord.label/agent (sanitized, ≤64 chars
|
|
74
74
|
// each, oldest-first, total ≤ 512 UTF-8 BYTES; excess
|
|
75
75
|
// advisory names are dropped whole, never chunked — the
|
|
76
|
-
// §4.5 #p= overflow form never triggers by construction
|
|
76
|
+
// §4.5 #p= overflow form never triggers by construction;
|
|
77
|
+
// a record whose label and agent are both absent has no
|
|
78
|
+
// identity to publish and is skipped, never replaced by a
|
|
79
|
+
// placeholder or a stringified absent value)
|
|
77
80
|
// Compatibility transport only: the consumer renders
|
|
78
81
|
// roles, never names. Null (clear) when the active
|
|
79
|
-
// TaskStore list has no
|
|
82
|
+
// TaskStore list has no names; null change tokens when the session model has
|
|
80
83
|
// zero changed files — refreshed/cleared from the live
|
|
81
84
|
// session model, never carried across sessions.
|
|
82
85
|
// gentle_ask_v1 = <hash>:<intentId>:<expiry>
|
|
@@ -2438,17 +2441,21 @@ async function applyCustomizeSwitch(id, value, ctx) {
|
|
|
2438
2441
|
if (result.needsReload && typeof ctx?.reload === "function") await ctx.reload();
|
|
2439
2442
|
}
|
|
2440
2443
|
|
|
2441
|
-
// The single apply path shared by the overlay and the menu fallback.
|
|
2442
|
-
//
|
|
2443
|
-
//
|
|
2444
|
-
//
|
|
2445
|
-
//
|
|
2446
|
-
//
|
|
2447
|
-
|
|
2448
|
-
|
|
2449
|
-
|
|
2444
|
+
// The single apply path shared by the overlay and the menu fallback. The choice
|
|
2445
|
+
// the panel resolves names the switch it drives (`switchId`) and the value to
|
|
2446
|
+
// apply; that switch id is the only thing read here, so a row can never apply a
|
|
2447
|
+
// switch its category does not own. An inconclusive sidebar verdict is never a
|
|
2448
|
+
// refusal: choosing On still attempts the repair and reports the apply step's
|
|
2449
|
+
// own error, exactly like the baseline menu did.
|
|
2450
|
+
const CUSTOMIZE_SWITCH_IDS = ["sidebar", "moshi"];
|
|
2451
|
+
|
|
2452
|
+
async function applyCustomizeChoice(choice, ctx) {
|
|
2453
|
+
if (!isRecord(choice)) return;
|
|
2454
|
+
const switchId = choice.switchId;
|
|
2455
|
+
const valueId = choice.valueId;
|
|
2456
|
+
if (!CUSTOMIZE_SWITCH_IDS.includes(switchId)) return;
|
|
2450
2457
|
if (valueId !== "on" && valueId !== "off") return;
|
|
2451
|
-
await applyCustomizeSwitch(
|
|
2458
|
+
await applyCustomizeSwitch(switchId, valueId, ctx);
|
|
2452
2459
|
}
|
|
2453
2460
|
|
|
2454
2461
|
// The former plain menu, kept as the fallback when the TUI helpers or
|
|
@@ -2477,7 +2484,7 @@ async function runCustomizeFallback(ctx) {
|
|
|
2477
2484
|
choice = undefined;
|
|
2478
2485
|
}
|
|
2479
2486
|
if (choice !== CUSTOMIZE_ON && choice !== CUSTOMIZE_OFF) return;
|
|
2480
|
-
await applyCustomizeChoice(id, choice === CUSTOMIZE_ON ? "on" : "off", ctx);
|
|
2487
|
+
await applyCustomizeChoice({ switchId: id, valueId: choice === CUSTOMIZE_ON ? "on" : "off" }, ctx);
|
|
2481
2488
|
}
|
|
2482
2489
|
|
|
2483
2490
|
async function executeCustomize(rawArgs, ctx) {
|
|
@@ -2548,7 +2555,7 @@ async function executeCustomize(rawArgs, ctx) {
|
|
|
2548
2555
|
// Esc (null) does nothing at all: no notification, no write, no reload.
|
|
2549
2556
|
// Anything else runs the single apply path once the overlay is disposed.
|
|
2550
2557
|
if (!choice || typeof choice !== "object") return;
|
|
2551
|
-
await applyCustomizeChoice(choice
|
|
2558
|
+
await applyCustomizeChoice(choice, ctx);
|
|
2552
2559
|
return;
|
|
2553
2560
|
}
|
|
2554
2561
|
await runCustomizeFallback(ctx);
|
|
@@ -2590,7 +2597,7 @@ export default function (pi) {
|
|
|
2590
2597
|
// Finished/failed/cancelled/waiting entries may linger in the map but
|
|
2591
2598
|
// never count; the map is cleared only on session reset (plus the
|
|
2592
2599
|
// bounded-map guard) — never by a local staleness timeout.
|
|
2593
|
-
const pendingCalls = new Map(); // toolCallId -> { agent, label, at }
|
|
2600
|
+
const pendingCalls = new Map(); // toolCallId -> { agent, label, at }; agent/label are undefined when no agent is resolvable
|
|
2594
2601
|
const tasks = new Map(); // taskId -> { agent, label, status, at }
|
|
2595
2602
|
|
|
2596
2603
|
// Blocker legs. ask combines choice + native questionnaire + legacy
|
|
@@ -3082,7 +3089,20 @@ export default function (pi) {
|
|
|
3082
3089
|
const parts = [];
|
|
3083
3090
|
let length = 0;
|
|
3084
3091
|
for (const sub of subs) {
|
|
3085
|
-
|
|
3092
|
+
// An entry whose label and agent are both absent has no name to publish:
|
|
3093
|
+
// a record can carry no identity at all (an observation without an agent
|
|
3094
|
+
// and no previous record), and `sanitizeLabel` stringifies whatever
|
|
3095
|
+
// fallback it is handed, so passing the absence through would put the
|
|
3096
|
+
// literal `undefined` on the wire as a name.
|
|
3097
|
+
const label =
|
|
3098
|
+
typeof sub.label === "string" && sub.label.length > 0 ? sub.label : undefined;
|
|
3099
|
+
const subAgent =
|
|
3100
|
+
typeof sub.agent === "string" && sub.agent.length > 0 ? sub.agent : undefined;
|
|
3101
|
+
if (label === undefined && subAgent === undefined) continue;
|
|
3102
|
+
// Label first, agent as fallback, unchanged for every entry that has
|
|
3103
|
+
// either; the fallback is never absent here, so the sanitizer always has
|
|
3104
|
+
// a real string to fall back to.
|
|
3105
|
+
const name = sanitizeLabel(label, subAgent ?? label);
|
|
3086
3106
|
if (parts.includes(name)) continue;
|
|
3087
3107
|
const add = (parts.length === 0 ? 0 : 1) + utf8Bytes(name);
|
|
3088
3108
|
if (length + add > MAX_TOKEN_BYTES) break;
|
|
@@ -3130,11 +3150,13 @@ export default function (pi) {
|
|
|
3130
3150
|
) {
|
|
3131
3151
|
return "rdd";
|
|
3132
3152
|
}
|
|
3133
|
-
// The bare visible
|
|
3134
|
-
// exactly equal to
|
|
3135
|
-
// in metadata roles and the native message alike.
|
|
3153
|
+
// The bare visible words `working` and `subagent` are banned: a sanitized
|
|
3154
|
+
// unknown slug exactly equal to either degrades to no role (generic
|
|
3155
|
+
// `gentle`) in metadata roles and the native message alike. `subagent` is
|
|
3156
|
+
// the launch-correlation placeholder, never an agent name, so it must
|
|
3157
|
+
// never reach the wire as a role word.
|
|
3136
3158
|
const slug = sanitizeAgentSlug(agent);
|
|
3137
|
-
return slug === "working" ? undefined : slug;
|
|
3159
|
+
return slug === "working" || slug === "subagent" ? undefined : slug;
|
|
3138
3160
|
}
|
|
3139
3161
|
|
|
3140
3162
|
// Bounded CSV of role words, oldest-first (subs already arrive
|
|
@@ -3923,11 +3945,23 @@ export default function (pi) {
|
|
|
3923
3945
|
|
|
3924
3946
|
// -- subagent activity -----------------------------------------------------
|
|
3925
3947
|
|
|
3948
|
+
// `subagent_run` carries the agent in its input, but `subagent_continue`
|
|
3949
|
+
// carries only `task_id`/`prompt`/`label`/`mode`: a resume names the task
|
|
3950
|
+
// whose record already holds the child's agent. Neither source means no
|
|
3951
|
+
// role evidence at all — the pending call still covers the blocking/
|
|
3952
|
+
// orchestrating marker, but it contributes no role and no name, and it
|
|
3953
|
+
// must never publish the launch-correlation placeholder as a role word.
|
|
3926
3954
|
function launchInput(input) {
|
|
3927
3955
|
if (!isRecord(input)) return undefined;
|
|
3928
|
-
const
|
|
3929
|
-
const
|
|
3930
|
-
|
|
3956
|
+
const taskId = typeof input.task_id === "string" ? input.task_id : undefined;
|
|
3957
|
+
const inputAgent =
|
|
3958
|
+
typeof input.agent === "string" && input.agent.length > 0 ? input.agent : undefined;
|
|
3959
|
+
const agent =
|
|
3960
|
+
inputAgent ?? (taskId !== undefined ? tasks.get(taskId)?.agent : undefined);
|
|
3961
|
+
const labelSource =
|
|
3962
|
+
typeof input.label === "string" && input.label.length > 0 ? input.label : agent;
|
|
3963
|
+
const label = labelSource === undefined ? undefined : sanitizeLabel(labelSource, labelSource);
|
|
3964
|
+
return { agent: agent === undefined ? undefined : truncateChars(agent, MAX_LABEL_CHARS), label };
|
|
3931
3965
|
}
|
|
3932
3966
|
|
|
3933
3967
|
pi.on("tool_call", (event) => {
|
|
@@ -4051,10 +4085,13 @@ export default function (pi) {
|
|
|
4051
4085
|
: undefined;
|
|
4052
4086
|
// A stale read's agent is distrusted with its status, and a missing
|
|
4053
4087
|
// agent keeps the previous record's agent (never reset to a guess).
|
|
4088
|
+
// With neither source the record has no agent at all: `subagent` is the
|
|
4089
|
+
// launch-correlation placeholder, never an identity, so inventing it here
|
|
4090
|
+
// would publish that word as the record's name.
|
|
4054
4091
|
const agent =
|
|
4055
4092
|
staleRead && previous?.agent
|
|
4056
4093
|
? previous.agent
|
|
4057
|
-
: (incomingAgent ?? previous?.agent
|
|
4094
|
+
: (incomingAgent ?? previous?.agent);
|
|
4058
4095
|
const now = Date.now();
|
|
4059
4096
|
tasks.set(details.taskId, {
|
|
4060
4097
|
agent,
|
|
@@ -4105,10 +4142,13 @@ export default function (pi) {
|
|
|
4105
4142
|
if (typeof details.status !== "string") return;
|
|
4106
4143
|
if (!FINAL_TASK.has(details.status) && !ACTIVE_TASK.has(details.status)) return;
|
|
4107
4144
|
const previous = tasks.get(details.taskId);
|
|
4145
|
+
// Same rule as the tool_result path: an observation without an agent keeps
|
|
4146
|
+
// the previous record's agent, and with neither there is no agent at all —
|
|
4147
|
+
// the launch-correlation placeholder must never become a record identity.
|
|
4108
4148
|
const agent =
|
|
4109
4149
|
typeof details.agent === "string" && details.agent.length > 0
|
|
4110
4150
|
? truncateChars(details.agent, MAX_LABEL_CHARS)
|
|
4111
|
-
:
|
|
4151
|
+
: previous?.agent;
|
|
4112
4152
|
// Record identity is immutable per taskId: firstSeen never moves (T2b
|
|
4113
4153
|
// ordering only) whether this observation promotes a background start
|
|
4114
4154
|
// or replaces the record with its terminal status; completion still
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "herdr-gentle-shell",
|
|
3
|
-
"version": "1.5.
|
|
3
|
+
"version": "1.5.1",
|
|
4
4
|
"description": "Pi package for Herdr sidebar states: the Pi extension sidecar that publishes session facts as Herdr pane-metadata tokens, the optional Moshi notification channel, and the Pi-side helpers the Herdr Gentle Shell plugin drives.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"pi-package",
|