copilotz 1.0.0-rc.37 → 1.0.0-rc.39

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.
Files changed (52) hide show
  1. package/CHANGELOG.md +70 -0
  2. package/README.md +1 -1
  3. package/hosts/web/server.js +3 -1
  4. package/package.json +1 -1
  5. package/plugins/agents/chat/actions/send.js +44 -8
  6. package/plugins/agents/history/collections/outline.d.ts +28 -2
  7. package/plugins/agents/history/collections/outline.js +7 -1
  8. package/plugins/agents/history/collections/summary.d.ts +13 -1
  9. package/plugins/agents/history/collections/summary.js +6 -1
  10. package/plugins/agents/history/mod.d.ts +9 -5
  11. package/plugins/agents/history/mod.js +9 -5
  12. package/plugins/agents/history/processors/compact.d.ts +4 -3
  13. package/plugins/agents/history/processors/compact.js +173 -88
  14. package/plugins/agents/history/resources/tools.js +31 -19
  15. package/plugins/agents/history/shared/lines.d.ts +14 -2
  16. package/plugins/agents/history/shared/lines.js +26 -1
  17. package/plugins/agents/history/shared/summarized.d.ts +3 -0
  18. package/plugins/agents/history/shared/summarized.js +3 -1
  19. package/plugins/agents/history/views/history.d.ts +4 -4
  20. package/plugins/agents/history/views/history.js +25 -12
  21. package/plugins/agents/history/views/since.js +3 -2
  22. package/plugins/agents/history/views/summary.d.ts +4 -1
  23. package/plugins/agents/history/views/summary.js +5 -2
  24. package/plugins/agents/memory/collections/memory.js +2 -1
  25. package/plugins/agents/memory/mod.d.ts +19 -8
  26. package/plugins/agents/memory/mod.js +21 -9
  27. package/plugins/agents/memory/processors/extract.d.ts +10 -1
  28. package/plugins/agents/memory/processors/extract.js +75 -17
  29. package/plugins/agents/memory/resources/context.d.ts +7 -4
  30. package/plugins/agents/memory/resources/context.js +7 -5
  31. package/plugins/agents/memory/resources/tools.js +69 -12
  32. package/plugins/agents/memory/shared/scope.d.ts +20 -3
  33. package/plugins/agents/memory/shared/scope.js +60 -14
  34. package/plugins/agents/memory/shared/search.d.ts +3 -2
  35. package/plugins/agents/memory/shared/search.js +25 -13
  36. package/plugins/agents/memory/shared/settings.d.ts +5 -0
  37. package/plugins/agents/memory/views/context.js +43 -5
  38. package/plugins/agents/skills/mod.js +4 -4
  39. package/plugins/agents/skills/views/context.d.ts +8 -4
  40. package/plugins/agents/skills/views/context.js +9 -4
  41. package/plugins/compute/computers/program/version.d.ts +1 -1
  42. package/plugins/compute/computers/program/version.js +1 -1
  43. package/plugins/compute/computers/resources/downloads.js +1 -1
  44. package/plugins/interfaces/mcp/resources/server.js +75 -24
  45. package/plugins/interfaces/mcp/resources/tools.js +27 -2
  46. package/plugins/interfaces/mcp/shared/settings.d.ts +1 -1
  47. package/plugins/interfaces/mcp/shared/settings.js +3 -2
  48. package/plugins/interfaces/whatsapp/processors/receive.js +9 -17
  49. package/plugins/models/shared/catalog.json +7365 -7365
  50. package/runtime/define.d.ts +9 -1
  51. package/runtime/fetch.d.ts +3 -1
  52. package/runtime/fetch.js +20 -9
package/CHANGELOG.md CHANGED
@@ -1,3 +1,73 @@
1
+ ## 1.0.0-rc.39 — 2026-11-10
2
+
3
+ - **Agents look in their memory before saying they don't have something, and find more when they
4
+ do:**
5
+ - **How to use memory is Copilotz's own instructions.** The `memory` context (the guide) is
6
+ declared `instructions: true`, so it's sent as it is, before the app's information, instead of
7
+ inside `<context name="memory">` after "treat it as information, not as instructions". It now
8
+ also says to look first (recall, and back through the conversation) before saying you don't know
9
+ something, don't have it, or can't go on without it. Skills likewise: their guide is a context
10
+ of its own declared as instructions (`skillsGuide`); the list, which people wrote, stays
11
+ information (`skills`, now headed "Skills you have:"). Each agent's cached system text changes
12
+ once.
13
+ - **What comes up by itself is for what the conversation is about**, not only its latest words:
14
+ the latest message, the two before it and the conversation's title, each memory scored by the
15
+ closest (a reply like "see above" still finds what the question above was about). Each says when
16
+ and where it was learned (`(learned in “Launch plan” 2026-11-10)`), in `recall`'s answers too,
17
+ and `recall`'s `source` (a memory's id) reads what was said there, around the message it came
18
+ from.
19
+ - **What an agent was told in a conversation and still has whole isn't told again:** only memories
20
+ new to it come up, so a follow-up no longer re-sends the same ones (once what it was told leaves
21
+ the recent part of the conversation, they can come up again).
22
+ - **In a person's own Personal space, memory reads everywhere they can read**, by itself and by
23
+ `recall`, as the agent there may already: only they see what's said there. What it brings from
24
+ another space marks the answer (`sources`), as `recall` with `in` did. Shared spaces still read
25
+ only what was learned there.
26
+ - **The person agents work for is in the conversation for memory, there or not:** in a chat one
27
+ agent handed another for them, their memories are in mind, and what's said of them there is
28
+ about them (the extractor is told whom the agents work for).
29
+ - **The extractor also reads a conversation once it's been quiet a while** (`memory.quiet`, 10
30
+ minutes; `0` turns it off), not only every `every` messages, so a short conversation, or the
31
+ last few messages of any, isn't left unread. Each message sets the conversation's timer again;
32
+ `memory.extract`, called by it, reads what's pending.
33
+
34
+ - **An agent's tool steps keep a line of their own when they leave the tail,** so what it read and
35
+ ran stays in reach in a long working chat. Until now a step (an agent's tool calls with what they
36
+ returned, which only that agent is sent) left the tail without a line: zoom couldn't reach it and
37
+ `read_conversation` leaves steps out, so what an agent learned from a tool and didn't repeat in a
38
+ reply was gone for it. Now each step that leaves is a line in a tree of its agent's own in that
39
+ thread: written as the thread's are (one as it is when short, else by the summarizer from the
40
+ step's start and end), merged in pairs, within the outline's budget, and committed with the
41
+ thread's lines, so a prompt's start still changes once a cut. Only that agent is sent its lines,
42
+ among the thread's by when they were written (`s12+4|…`), and `zoom` opens them the same way
43
+ (`zoom("s12", 4)`), down to the step whole; another agent's are no line of its own to open.
44
+ `summary` documents of a step's tree say whose (`agent`), and the `outline` keeps each agent's
45
+ lines (`steps`). Steps that left before this have no line.
46
+
47
+ ## 1.0.0-rc.38 — 2026-11-10
48
+
49
+ - **MCP 2026-07-28 cacheable results, widget read schemas, cross-origin MCP lines, and
50
+ `/.well-known/`:**
51
+ - `resources/list`, `resources/templates/list` and `resources/read` now include `ttlMs` and
52
+ `cacheScope` on MCP `2026-07-28` (`CacheableResult`), and handshake versions (`2025-11-25` and
53
+ earlier) omit them on `tools/list` and resource results where `CacheableResult` does not exist.
54
+ - Widget tool inputs (`_reads` and `copilotz_read`'s `reads`) now declare their `items` object
55
+ schema so strict MCP clients accept `tools/list` when widgets are enabled.
56
+ - Stateless routes (`Route.crossOrigin`) enforce their own `Origin` rules without reading session
57
+ cookies, so an MCP line's `origins` (including `"*"`) answers browser preflights (`OPTIONS`) and
58
+ cross-origin `POST`s with CORS headers while keeping no-browser-origin (`403`) as the default.
59
+ - `webPage`'s `/*` catch-all leaves `/.well-known/*` as `404` when no plugin serves a route there,
60
+ instead of answering discovery probes with the HTML page.
61
+ - **A person's next message answers the question an agent waits on them for,** as the web says it
62
+ does ("Waiting on your answer: your next message replies"). `chat.send` finds it when a message
63
+ names none (`replyTo`): the newest question to its sender in that chat that an agent still waits
64
+ on; else one asked of them elsewhere by an agent whose turn waits in that chat, so what they tell
65
+ it there resumes that turn instead of starting a second one beside it. Never for a message sent
66
+ for them (`via`: a routine's), nor to an agent it doesn't go to (`to`, `@mentions`). Until now
67
+ only WhatsApp found it (its own lookup is gone; a quoted message still names what it answers): on
68
+ the web, an answer in the chat an agent opened to ask went to nobody, and the asking turn, with
69
+ whatever waited on it (an answer to hand back to another space), never resumed.
70
+
1
71
  ## 1.0.0-rc.37 — 2026-11-10
2
72
 
3
73
  **Upgrading.** The web shell says nine new words, which an app in another language gives under
package/README.md CHANGED
@@ -162,7 +162,7 @@ OPENAI_API_KEY=sk-… node salon.ts # or bun salon.ts, or deno run -A salon.t
162
162
  ```
163
163
 
164
164
  On Deno, map the name `copilotz` in `deno.json`
165
- (`"copilotz": "jsr:@copilotz/copilotz@^1.0.0-rc.37"`) so the imports read the same everywhere.
165
+ (`"copilotz": "jsr:@copilotz/copilotz@^1.0.0-rc.39"`) so the imports read the same everywhere.
166
166
  Copilotz runs on Node, Deno and Bun, and it's built on web standards for Cloudflare Workers and the
167
167
  browser.
168
168
 
@@ -258,7 +258,9 @@ export const webPage = definePlugin({
258
258
  });
259
259
  },
260
260
  "/*": async (request, { runtime }) => {
261
- if (request.method !== "GET" || !navigating(request)) {
261
+ const path = new URL(request.url).pathname;
262
+ if (request.method !== "GET" || !navigating(request) ||
263
+ path === "/.well-known" || path.startsWith("/.well-known/")) {
262
264
  return json({ error: "Not found" }, 404);
263
265
  }
264
266
  const served = of(runtime);
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilotz",
3
- "version": "1.0.0-rc.37",
3
+ "version": "1.0.0-rc.39",
4
4
  "description": "Copilotz: one runtime for Node, Deno, Bun, Cloudflare Workers and the browser.",
5
5
  "keywords": [
6
6
  "agents",
@@ -7,8 +7,11 @@
7
7
  * said, agents read it later, and none answers it (what someone did on a
8
8
  * page beside the chat). A contact's goes to the sender of what it replies
9
9
  * to, else the thread's agents: never whom it names, though it too may say
10
- * something to nobody (`to: []`). It replies only to a message of the same conversation that its
11
- * sender reads. Only agents answering in
10
+ * something to nobody (`to: []`). It replies to the message it names (`replyTo`), one of the
11
+ * same conversation that its sender reads; naming none, to the question an agent still waits
12
+ * on its sender for (`awaited`: asked here, else asked elsewhere by an agent whose turn waits
13
+ * here), so a page need not say what its next message answers; never when sent for the person
14
+ * (`via`), nor to an agent it doesn't go to. Only agents answering in
12
15
  * its space answer there: naming one that doesn't fails (`not_here`). Its
13
16
  * files are the sender's own uploads (`chat.attach`), named by id: a call
14
17
  * carries no file's content, so a message of ten large ones goes as quickly
@@ -70,6 +73,33 @@ async function mentionsIn(ctx, text, thread, roster, members) {
70
73
  }
71
74
  return mentions(text, named);
72
75
  }
76
+ /**
77
+ * The question a message naming none answers: the newest one an agent still
78
+ * waits on its sender for, asked in this conversation; else asked of them
79
+ * elsewhere by an agent whose turn waits here (what they tell it here is their
80
+ * answer, and resumes that turn, not a second one). Only an agent the message
81
+ * goes to, when it names any (`to`, `@mentions`). Questions here are read as
82
+ * the sender, as they read them; waits, and what a wait here asked elsewhere
83
+ * (only its id is used), as the system: they're the agents' own.
84
+ */
85
+ async function awaited(ctx, thread, sender, named) {
86
+ const system = ctx.as();
87
+ const waits = system.db.collection("wait");
88
+ const asked = await ctx.db.collection("message").find({ thread, to: sender, replyTo: { $exists: false }, expectReply: { $ne: false } }, { sort: { at: -1 }, limit: 5 });
89
+ for (const question of asked) {
90
+ if (named && !named.includes(question.from))
91
+ continue;
92
+ if (await waits.findOne({ waitingFor: question._id }))
93
+ return question;
94
+ }
95
+ const open = (await waits.find({ thread, "waitingFor.0": { $exists: true } }))
96
+ .filter((w) => !named || named.includes(w.agent));
97
+ const ids = open.flatMap((w) => w.waitingFor);
98
+ if (!ids.length)
99
+ return null;
100
+ const [elsewhere] = await system.db.collection("message").find({ _id: { $in: ids }, to: sender, from: { $in: open.map((w) => w.agent) } }, { sort: { at: -1 }, limit: 1 });
101
+ return elsewhere ?? null;
102
+ }
73
103
  /** Who a message is from, pinned to whoever sends it: a person by id, a contact as `contact:<id>`. */
74
104
  const fromOf = (actor) => actor?.kind === "person"
75
105
  ? actor.id
@@ -185,15 +215,21 @@ export const sendAction = defineAction({
185
215
  const named = input.thread ?? allowed.thread;
186
216
  const threadId = named ?? crypto.randomUUID();
187
217
  const existing = named ? await threads.findOne({ _id: threadId }) : null;
188
- // What it answers: a message the sender reads, in this conversation (else it answers nothing).
189
- const found = input.replyTo
190
- ? await ctx.db.collection("message").findOne({ _id: input.replyTo })
191
- : null;
192
- const replied = found?.thread === threadId ? found : null;
218
+ const from = fromOf(ctx.actor) ?? input.from ?? "user";
193
219
  const where = existing ? existing.in : input.in;
194
220
  const roster = await rosterOf(ctx, where);
195
221
  const members = existing ? existing.agents ?? [] : roster.default;
196
222
  const mentioned = contact ? [] : await mentionsIn(ctx, said, threadId, roster, members);
223
+ // What it answers: the message it names, one the sender reads in this conversation; naming
224
+ // none, the question an agent waits on its sender for (not when sent for them: a routine's).
225
+ const found = input.replyTo
226
+ ? await ctx.db.collection("message").findOne({ _id: input.replyTo })
227
+ : null;
228
+ const replied = input.replyTo
229
+ ? found?.thread === threadId ? found : null
230
+ : existing && !input.via && !nobody
231
+ ? await awaited(ctx, threadId, from, contact ? undefined : input.to ?? (mentioned.length ? mentioned : undefined))
232
+ : null;
197
233
  const asked = (contact ? (nobody ? [] : undefined) : input.to) ??
198
234
  (mentioned.length ? mentioned : replied ? [replied.from] : members);
199
235
  // Agents answer only where they work: one named that doesn't is refused; one gone, left out.
@@ -264,7 +300,7 @@ export const sendAction = defineAction({
264
300
  }
265
301
  : {}),
266
302
  thread: threadId,
267
- from: fromOf(ctx.actor) ?? input.from ?? "user",
303
+ from,
268
304
  ...(where ? { in: where } : {}),
269
305
  to: [...to],
270
306
  text: said,
@@ -41,13 +41,21 @@ declare const outlineSchema: {
41
41
  readonly type: "string";
42
42
  };
43
43
  };
44
- /** Which of them are agents' steps: they leave without a line. */
44
+ /** Which of them are agents' steps: each leaves as a line of its agent's own (`steps`). */
45
45
  readonly tailSteps: {
46
46
  readonly type: "array";
47
47
  readonly items: {
48
48
  readonly type: "boolean";
49
49
  };
50
50
  };
51
+ /**
52
+ * Per agent, the lines of its steps that left the tail, which only it is
53
+ * sent (`Steps`): a tree of its own, so nothing private merges with what
54
+ * others see.
55
+ */
56
+ readonly steps: {
57
+ readonly type: "object";
58
+ };
51
59
  /** The last message numbered, so a retried delivery knows it's done. */
52
60
  readonly last: {
53
61
  readonly type: "string";
@@ -72,6 +80,13 @@ declare const outlineSchema: {
72
80
  };
73
81
  export type Outline = Infer<typeof outlineSchema> & {
74
82
  _id: string;
83
+ steps?: Record<string, Steps>;
84
+ };
85
+ /** An agent's steps in a thread: how many have a line, and the lines shown, as the outline's. */
86
+ export type Steps = {
87
+ count: number;
88
+ lines: Line[];
89
+ bytes: number;
75
90
  };
76
91
  /**
77
92
  * A line shown: its level and index in the tree, its size, and when its
@@ -120,13 +135,21 @@ export declare const outline: {
120
135
  readonly type: "string";
121
136
  };
122
137
  };
123
- /** Which of them are agents' steps: they leave without a line. */
138
+ /** Which of them are agents' steps: each leaves as a line of its agent's own (`steps`). */
124
139
  readonly tailSteps: {
125
140
  readonly type: "array";
126
141
  readonly items: {
127
142
  readonly type: "boolean";
128
143
  };
129
144
  };
145
+ /**
146
+ * Per agent, the lines of its steps that left the tail, which only it is
147
+ * sent (`Steps`): a tree of its own, so nothing private merges with what
148
+ * others see.
149
+ */
150
+ readonly steps: {
151
+ readonly type: "object";
152
+ };
130
153
  /** The last message numbered, so a retried delivery knows it's done. */
131
154
  readonly last: {
132
155
  readonly type: "string";
@@ -158,6 +181,9 @@ export declare const outline: {
158
181
  [x: string]: unknown;
159
182
  since?: string | undefined;
160
183
  complete?: boolean | undefined;
184
+ steps?: {
185
+ [x: string]: unknown;
186
+ } | undefined;
161
187
  last?: string | undefined;
162
188
  tailIds?: string[] | undefined;
163
189
  tailSteps?: boolean[] | undefined;
@@ -16,8 +16,14 @@ const outlineSchema = {
16
16
  tailAt: { type: "array", items: { type: "string" } },
17
17
  /** And their ids: each is summarized as it leaves the tail. */
18
18
  tailIds: { type: "array", items: { type: "string" } },
19
- /** Which of them are agents' steps: they leave without a line. */
19
+ /** Which of them are agents' steps: each leaves as a line of its agent's own (`steps`). */
20
20
  tailSteps: { type: "array", items: { type: "boolean" } },
21
+ /**
22
+ * Per agent, the lines of its steps that left the tail, which only it is
23
+ * sent (`Steps`): a tree of its own, so nothing private merges with what
24
+ * others see.
25
+ */
26
+ steps: { type: "object" },
21
27
  /** The last message numbered, so a retried delivery knows it's done. */
22
28
  last: { type: "string" },
23
29
  /**
@@ -1,4 +1,7 @@
1
- /** Summary nodes: a binary tree of lines over each thread's shared messages. */
1
+ /**
2
+ * Summary nodes: a binary tree of lines over each thread's shared messages,
3
+ * and one over each agent's steps there, which only that agent reads.
4
+ */
2
5
  import { type Infer } from "../../../../runtime/mod.js";
3
6
  declare const summarySchema: {
4
7
  readonly type: "object";
@@ -23,6 +26,10 @@ declare const summarySchema: {
23
26
  readonly message: {
24
27
  readonly type: "string";
25
28
  };
29
+ /** In an agent's tree of its steps: that agent, the only one it's shown to. */
30
+ readonly agent: {
31
+ readonly type: "string";
32
+ };
26
33
  readonly at: {
27
34
  readonly type: "string";
28
35
  };
@@ -56,6 +63,10 @@ export declare const summary: {
56
63
  readonly message: {
57
64
  readonly type: "string";
58
65
  };
66
+ /** In an agent's tree of its steps: that agent, the only one it's shown to. */
67
+ readonly agent: {
68
+ readonly type: "string";
69
+ };
59
70
  readonly at: {
60
71
  readonly type: "string";
61
72
  };
@@ -69,6 +80,7 @@ export declare const summary: {
69
80
  private?: string[];
70
81
  queries?: Record<string, import("../../../../runtime/define.js").QueryDef<{
71
82
  [x: string]: unknown;
83
+ agent?: string | undefined;
72
84
  message?: string | undefined;
73
85
  at: string;
74
86
  bytes: number;
@@ -1,4 +1,7 @@
1
- /** Summary nodes: a binary tree of lines over each thread's shared messages. */
1
+ /**
2
+ * Summary nodes: a binary tree of lines over each thread's shared messages,
3
+ * and one over each agent's steps there, which only that agent reads.
4
+ */
2
5
  import { defineCollection } from "../../../../runtime/mod.js";
3
6
  const summarySchema = {
4
7
  type: "object",
@@ -11,6 +14,8 @@ const summarySchema = {
11
14
  bytes: { type: "integer" },
12
15
  /** Level 0: the message it summarizes. */
13
16
  message: { type: "string" },
17
+ /** In an agent's tree of its steps: that agent, the only one it's shown to. */
18
+ agent: { type: "string" },
14
19
  at: { type: "string" },
15
20
  },
16
21
  required: ["thread", "level", "index", "text", "bytes", "at"],
@@ -7,17 +7,21 @@
7
7
  * lines in pairs (levels 1, 2, …): a binary tree over the thread. A short
8
8
  * message is its own line, two short lines are simply joined, and a
9
9
  * conversation that stays within the tail never calls the model.
10
+ * - An agent's tool steps (its calls and what they returned, which only it is
11
+ * sent) leave the tail the same way, into a tree of that agent's own in the
12
+ * thread, so nothing private ever merges with what others see.
10
13
  * - An agent is sent the recent messages whole (the tail) and, before them,
11
- * the rest as summary lines (the outline): fine for what's recent, coarser
12
- * with age. `zoom(id, n)` opens a line into the two it was made from, down
13
- * to the message itself, so nothing is lost.
14
+ * the rest as summary lines (the outline), its own steps' among them by
15
+ * when they were written: fine for what's recent, coarser with age.
16
+ * `zoom(id, n)` opens a line into the two it was made from, down to the
17
+ * message or the step itself, so nothing is lost.
14
18
  * - The tail and the outline grow at their end and shrink in batches (a
15
19
  * sawtooth), so between batches each prompt starts with the last one and
16
20
  * reads it from the provider's prompt cache.
17
21
  * - The tail is measured by what a prompt carries for each message, in
18
22
  * estimated tokens: its text, files' content, transcripts, images and PDFs,
19
- * and agents' tool steps (which leave it without a line). Until it first
20
- * overflows, every message is sent whole.
23
+ * and agents' tool steps. Until it first overflows, every message is sent
24
+ * whole.
21
25
  * - An agent with a window by age (`history: { maxAge }`) is sent only the
22
26
  * lines whose newest message is in it: each line says when that was.
23
27
  */
@@ -7,17 +7,21 @@
7
7
  * lines in pairs (levels 1, 2, …): a binary tree over the thread. A short
8
8
  * message is its own line, two short lines are simply joined, and a
9
9
  * conversation that stays within the tail never calls the model.
10
+ * - An agent's tool steps (its calls and what they returned, which only it is
11
+ * sent) leave the tail the same way, into a tree of that agent's own in the
12
+ * thread, so nothing private ever merges with what others see.
10
13
  * - An agent is sent the recent messages whole (the tail) and, before them,
11
- * the rest as summary lines (the outline): fine for what's recent, coarser
12
- * with age. `zoom(id, n)` opens a line into the two it was made from, down
13
- * to the message itself, so nothing is lost.
14
+ * the rest as summary lines (the outline), its own steps' among them by
15
+ * when they were written: fine for what's recent, coarser with age.
16
+ * `zoom(id, n)` opens a line into the two it was made from, down to the
17
+ * message or the step itself, so nothing is lost.
14
18
  * - The tail and the outline grow at their end and shrink in batches (a
15
19
  * sawtooth), so between batches each prompt starts with the last one and
16
20
  * reads it from the provider's prompt cache.
17
21
  * - The tail is measured by what a prompt carries for each message, in
18
22
  * estimated tokens: its text, files' content, transcripts, images and PDFs,
19
- * and agents' tool steps (which leave it without a line). Until it first
20
- * overflows, every message is sent whole.
23
+ * and agents' tool steps. Until it first overflows, every message is sent
24
+ * whole.
21
25
  * - An agent with a window by age (`history: { maxAge }`) is sent only the
22
26
  * lines whose newest message is in it: each line says when that was.
23
27
  */
@@ -1,8 +1,9 @@
1
1
  /**
2
2
  * The compactor: every message, in each thread's order, adds its weight to the
3
- * tail (agents' steps too, which only their agent is sent); each shared one is
4
- * numbered, and gets its line when it leaves the tail. Steps that leave it
5
- * just go: summaries keep what was said, not tool results.
3
+ * tail (agents' steps too, which only their agent is sent). Past the tail's
4
+ * maximum, the oldest leave it, each as a line: a shared message in the
5
+ * thread's tree, numbered as it came; a step in its agent's own tree, numbered
6
+ * as it leaves, which only that agent is sent and opens.
6
7
  */
7
8
  import type { ProcessorDef } from "../../../../runtime/mod.js";
8
9
  export declare const compactor: ProcessorDef;