eve 0.90.0 → 0.91.0
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/CHANGELOG.md +34 -23
- package/dist/src/channel/auth/http-basic.js +1 -1
- package/dist/src/channel/channel-operations.d.ts +1 -1
- package/dist/src/channel/types.d.ts +2 -0
- package/dist/src/cli/dev/tui/prompt-commands.d.ts +1 -1
- package/dist/src/client/session.d.ts +1 -1
- package/dist/src/compiled/.vendor-stamp.json +1 -1
- package/dist/src/execution/dynamic-workflow/tool.js +1 -1
- package/dist/src/execution/proxied-deliver-step.js +1 -1
- package/dist/src/execution/sandbox/bash.js +2 -2
- package/dist/src/execution/session/active-turn.js +1 -1
- package/dist/src/execution/session/admission.d.ts +6 -0
- package/dist/src/execution/session/admission.js +1 -1
- package/dist/src/execution/session/delivery-facts.js +1 -1
- package/dist/src/execution/session/next-input.d.ts +2 -2
- package/dist/src/execution/session/next-input.js +1 -1
- package/dist/src/execution/session/program.js +1 -1
- package/dist/src/execution/session-inbox/inbox.d.ts +2 -2
- package/dist/src/execution/session-inbox/inbox.js +1 -1
- package/dist/src/execution/session-inbox/protocol.js +1 -1
- package/dist/src/execution/tools/agent-router-workflow.js +1 -1
- package/dist/src/harness/compaction/engine.js +2 -2
- package/dist/src/harness/current-messages.js +1 -1
- package/dist/src/harness/emission.d.ts +3 -0
- package/dist/src/harness/emission.js +1 -1
- package/dist/src/harness/facts.d.ts +5 -2
- package/dist/src/harness/facts.js +1 -1
- package/dist/src/harness/model-call/call.d.ts +7 -1
- package/dist/src/harness/model-call/call.js +3 -1
- package/dist/src/harness/provider-tool-history.d.ts +8 -0
- package/dist/src/harness/provider-tool-history.js +1 -1
- package/dist/src/harness/session-machine/transitions.d.ts +3 -2
- package/dist/src/harness/step/after-model.js +1 -1
- package/dist/src/harness/step/context.js +1 -1
- package/dist/src/harness/step/intake.js +1 -1
- package/dist/src/harness/step/prompt.js +1 -1
- package/dist/src/harness/tool-history-repair.d.ts +2 -0
- package/dist/src/harness/tool-history-repair.js +1 -1
- package/dist/src/harness/tool-loop.js +1 -1
- package/dist/src/internal/application/stamped-package-version.js +1 -1
- package/dist/src/protocol/session-events/families/delivery.d.ts +5 -3
- package/dist/src/protocol/session-events/families/delivery.js +1 -1
- package/dist/src/protocol/session-projection/fold.js +1 -1
- package/dist/src/public/channels/discord/hitl.js +1 -1
- package/dist/src/public/channels/slack/hitl.d.ts +2 -1
- package/dist/src/public/channels/slack/hitl.js +3 -3
- package/dist/src/public/channels/slack/interaction-cards.js +1 -1
- package/dist/src/public/channels/slack/request-card-render.js +1 -1
- package/dist/src/public/channels/teams/hitl.js +1 -1
- package/dist/src/public/channels/teams/verify.js +1 -1
- package/dist/src/public/definitions/hook.d.ts +90 -7
- package/dist/src/public/definitions/hook.js +1 -1
- package/dist/src/public/hooks/index.d.ts +3 -2
- package/dist/src/reactions/continuation.d.ts +19 -0
- package/dist/src/reactions/continuation.js +1 -0
- package/dist/src/reactions/intents.d.ts +10 -4
- package/dist/src/reactions/intents.js +1 -1
- package/dist/src/reactions/kinds/hook.js +1 -1
- package/dist/src/reactions/runner.js +1 -1
- package/dist/src/reactions/state.d.ts +15 -2
- package/dist/src/reactions/state.js +1 -1
- package/dist/src/runtime/resolve-connection.js +1 -1
- package/dist/src/runtime/subagents/workflow.js +1 -1
- package/dist/src/setup/primitives/open-url.js +1 -1
- package/dist/src/setup/scaffold/create/project.js +1 -1
- package/dist/src/shared/value-delta.d.ts +5 -4
- package/dist/src/shared/value-delta.js +1 -1
- package/dist/src/tools/provided/ask-question-workflow.js +1 -1
- package/dist/src/tools/provided/sleep-workflow.js +1 -1
- package/dist/src/tools/provided/web-fetch.js +1 -1
- package/docs/agent-config.md +199 -222
- package/docs/channels/chat-sdk.mdx +60 -64
- package/docs/channels/custom.mdx +264 -281
- package/docs/channels/discord.mdx +176 -123
- package/docs/channels/eve.mdx +136 -206
- package/docs/channels/github.mdx +24 -22
- package/docs/channels/linear.mdx +30 -30
- package/docs/channels/linq.mdx +25 -13
- package/docs/channels/mcp.mdx +154 -116
- package/docs/channels/overview.mdx +31 -32
- package/docs/channels/photon.mdx +32 -56
- package/docs/channels/slack.mdx +538 -375
- package/docs/channels/teams.mdx +40 -26
- package/docs/channels/telegram.mdx +13 -13
- package/docs/channels/twilio.mdx +11 -11
- package/docs/code-extension.mdx +40 -42
- package/docs/concepts/built-in-tools.md +89 -57
- package/docs/concepts/context-control.md +20 -20
- package/docs/concepts/default-harness.md +20 -36
- package/docs/concepts/execution-model-and-durability.mdx +96 -160
- package/docs/concepts/project-structure.mdx +21 -14
- package/docs/concepts/security-model.md +27 -27
- package/docs/concepts/sessions-runs-and-streaming.md +184 -198
- package/docs/concepts/state.md +7 -15
- package/docs/connections/mcp.mdx +109 -93
- package/docs/connections/openapi.mdx +57 -59
- package/docs/connections/overview.mdx +175 -170
- package/docs/evals/assertions.mdx +36 -29
- package/docs/evals/cases.mdx +38 -42
- package/docs/evals/judge.mdx +21 -29
- package/docs/evals/overview.mdx +42 -38
- package/docs/evals/reporters.mdx +54 -27
- package/docs/evals/running.mdx +15 -8
- package/docs/evals/targets.mdx +16 -19
- package/docs/evals/tool-stubs.mdx +111 -97
- package/docs/experimental/dynamic-schedules.mdx +118 -63
- package/docs/extensions.md +58 -65
- package/docs/getting-started.mdx +4 -6
- package/docs/guides/auth-and-route-protection.md +87 -70
- package/docs/guides/client/continuations.mdx +23 -26
- package/docs/guides/client/messages.mdx +47 -66
- package/docs/guides/client/output-schema.mdx +8 -8
- package/docs/guides/client/overview.mdx +45 -43
- package/docs/guides/client/streaming.mdx +62 -71
- package/docs/guides/decide.md +24 -79
- package/docs/guides/deployment/meta.json +1 -1
- package/docs/guides/deployment/overview.md +27 -18
- package/docs/guides/deployment/self-hosted-operations.md +99 -0
- package/docs/guides/deployment/self-hosting.md +63 -80
- package/docs/guides/deployment/vercel.mdx +31 -27
- package/docs/guides/deployment/workflow-worlds.md +100 -0
- package/docs/guides/dev-tui.md +48 -41
- package/docs/guides/dynamic-capabilities.md +49 -50
- package/docs/guides/frontend/nextjs.mdx +2 -2
- package/docs/guides/frontend/nuxt.mdx +11 -11
- package/docs/guides/frontend/overview.mdx +1 -1
- package/docs/guides/frontend/sveltekit.mdx +11 -11
- package/docs/guides/frontend/tanstack.mdx +16 -16
- package/docs/guides/frontend/use-eve-agent-svelte.mdx +21 -21
- package/docs/guides/frontend/use-eve-agent-vue.mdx +22 -22
- package/docs/guides/frontend/use-eve-agent.mdx +25 -25
- package/docs/guides/hooks.md +152 -106
- package/docs/guides/instrumentation/agent-runs.mdx +26 -30
- package/docs/guides/instrumentation/instrumentation.mdx +49 -76
- package/docs/guides/instrumentation/meta.json +1 -1
- package/docs/guides/instrumentation/otel.mdx +113 -179
- package/docs/guides/remote-agents.md +125 -187
- package/docs/guides/self-modification.md +18 -18
- package/docs/guides/session-context.md +16 -16
- package/docs/install-integrations.mdx +26 -24
- package/docs/instructions.mdx +37 -42
- package/docs/memory/custom-provider.md +35 -41
- package/docs/memory/file.md +93 -76
- package/docs/memory/overview.mdx +145 -156
- package/docs/patterns/durable-cross-channel-notifications.md +15 -19
- package/docs/patterns/dynamic-scheduling.md +19 -23
- package/docs/patterns/multi-tenant-approvals.md +17 -22
- package/docs/patterns/multi-tenant-auth.md +43 -42
- package/docs/patterns/multi-tenant-memory.md +39 -36
- package/docs/patterns/voice-notes.md +3 -3
- package/docs/protocols/acp.md +13 -13
- package/docs/protocols/ucp.mdx +7 -7
- package/docs/reference/agent-files.md +6 -6
- package/docs/reference/cli.md +99 -98
- package/docs/reference/telemetry.md +1 -1
- package/docs/reference/typescript-api.md +52 -53
- package/docs/responsible-use.md +2 -2
- package/docs/sandbox/custom-providers.mdx +60 -56
- package/docs/sandbox/default.mdx +23 -24
- package/docs/sandbox/docker.mdx +16 -10
- package/docs/sandbox/index.mdx +93 -61
- package/docs/sandbox/just-bash.mdx +17 -11
- package/docs/sandbox/troubleshooting.mdx +29 -23
- package/docs/sandbox/vercel.mdx +45 -52
- package/docs/schedules.mdx +65 -54
- package/docs/skills.mdx +74 -49
- package/docs/subagents/index.mdx +97 -136
- package/docs/tools/human-in-the-loop.md +160 -90
- package/docs/tools/meta.json +1 -1
- package/docs/tools/overview.mdx +229 -237
- package/docs/tools/tasks.md +118 -117
- package/docs/tools/workflows.mdx +447 -543
- package/docs/tutorial/connect-a-warehouse.mdx +11 -13
- package/docs/tutorial/first-agent.mdx +14 -16
- package/docs/tutorial/guard-the-spend.mdx +6 -8
- package/docs/tutorial/how-it-runs.mdx +8 -8
- package/docs/tutorial/query-sample-data.mdx +8 -8
- package/docs/tutorial/remember-definitions.mdx +4 -4
- package/docs/tutorial/run-analysis.mdx +20 -22
- package/docs/tutorial/ship-it.mdx +19 -19
- package/docs/tutorial/team-playbooks.mdx +9 -9
- package/docs/use-cases.mdx +13 -11
- package/package.json +1 -1
- package/docs/guides/instrumentation/migration.md +0 -96
- package/docs/tools/tasks-upgrade.md +0 -218
|
@@ -3,11 +3,11 @@ title: "Built-in Tools"
|
|
|
3
3
|
description: "The default and opt-in tools eve provides, including glob, grep, and sleep."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
eve provides a default
|
|
6
|
+
Built-in tools are framework tools eve provides: a default set every agent gets, and opt-in tools you add with one file. Each occupies the same `agent/tools/<name>.ts` slot you would author yourself, so an authored definition replaces it and `disableTool()` removes it. For custom tools, see [Tools](../tools).
|
|
7
7
|
|
|
8
8
|
## Default tools
|
|
9
9
|
|
|
10
|
-
Default tools require no imports. The
|
|
10
|
+
Default tools require no imports. The model sees only the defaults available to the current agent and session.
|
|
11
11
|
|
|
12
12
|
### Disable optional default tools
|
|
13
13
|
|
|
@@ -22,9 +22,7 @@ export default defineAgent({
|
|
|
22
22
|
});
|
|
23
23
|
```
|
|
24
24
|
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
`defaultTools` doesn't affect [the catalog tools](#eve__search-eve__tool-and-eve__skill): eve adds them from what the session can reach, as listed in that section.
|
|
25
|
+
Add back only the tools the agent needs with the command in each tool's section. Files under `agent/tools/` stay available, including same-name replacements such as `agent/tools/bash.ts`. `defaultTools` doesn't affect [the catalog tools](#eve__search-eve__tool-and-eve__skill), which eve adds from what the session can reach.
|
|
28
26
|
|
|
29
27
|
### `bash`
|
|
30
28
|
|
|
@@ -45,7 +43,7 @@ export { default } from "eve/tools/bash";
|
|
|
45
43
|
- `stdout`, `stderr`, and `truncated`: the output so far
|
|
46
44
|
- `message`: instructions for the model
|
|
47
45
|
|
|
48
|
-
The command
|
|
46
|
+
The command writes to `stdout` and `stderr` files in `outputDirectory`, and its exit code to an `exit` file when it finishes. The model checks on or stops it with shell commands in later `bash` calls, so the tool's approval policy applies to them:
|
|
49
47
|
|
|
50
48
|
```sh
|
|
51
49
|
tail /tmp/.eve/jobs/3f9a1c2e/stdout # latest output
|
|
@@ -53,7 +51,7 @@ cat /tmp/.eve/jobs/3f9a1c2e/exit # exit code, once the command has finished
|
|
|
53
51
|
kill -- -4312 # stop the command's whole process group
|
|
54
52
|
```
|
|
55
53
|
|
|
56
|
-
The command
|
|
54
|
+
The command runs across turns until it exits, the model stops it, or the sandbox stops, and its output files last until the sandbox stops. Cancelling a turn stops a command that hasn't yet returned `running`. The `just-bash` provider has no background processes, so it runs every command to completion.
|
|
57
55
|
|
|
58
56
|
Override its description, approval policy, or executor by wrapping the exported definition:
|
|
59
57
|
|
|
@@ -81,7 +79,14 @@ export default disableTool();
|
|
|
81
79
|
|
|
82
80
|
### `read_file`
|
|
83
81
|
|
|
84
|
-
`read_file` reads text files
|
|
82
|
+
`read_file` reads sandbox text files with line-numbered output. It also shows the model images and PDFs as files:
|
|
83
|
+
|
|
84
|
+
- PNG, JPEG, GIF, and WebP images up to 3 MiB and 8000 pixels per side
|
|
85
|
+
- PDFs up to 20 MiB
|
|
86
|
+
|
|
87
|
+
It detects images and PDFs from their bytes, so the filename extension doesn't matter.
|
|
88
|
+
|
|
89
|
+
It accepts absolute paths, paths relative to the workspace root where `bash` commands start, and paths beginning with `$HOME/`. Results and errors name the resolved absolute path.
|
|
85
90
|
|
|
86
91
|
```sh
|
|
87
92
|
eve add tool/read_file
|
|
@@ -195,7 +200,7 @@ export default disableTool();
|
|
|
195
200
|
|
|
196
201
|
### `web_search`
|
|
197
202
|
|
|
198
|
-
`web_search` uses provider-managed web search and appears only for supported model providers. AI Gateway models use Exa
|
|
203
|
+
`web_search` uses provider-managed web search and appears only for supported model providers. AI Gateway models use Exa unless you set `provider`; direct provider models use their native search.
|
|
199
204
|
|
|
200
205
|
```sh
|
|
201
206
|
eve add tool/web_search
|
|
@@ -207,7 +212,7 @@ import { webSearch } from "eve/tools/web_search";
|
|
|
207
212
|
export default webSearch({ provider: "exa" });
|
|
208
213
|
```
|
|
209
214
|
|
|
210
|
-
|
|
215
|
+
Choose another AI Gateway search provider:
|
|
211
216
|
|
|
212
217
|
```ts title="agent/tools/web_search.ts"
|
|
213
218
|
import { webSearch } from "eve/tools/web_search";
|
|
@@ -223,7 +228,7 @@ import { webSearch } from "eve/tools/web_search";
|
|
|
223
228
|
export default webSearch({ provider: "browserbase" });
|
|
224
229
|
```
|
|
225
230
|
|
|
226
|
-
|
|
231
|
+
Browserbase Search requires a [Gateway model ID](../agent-config#set-the-model). AI Gateway runs the search with `AI_GATEWAY_API_KEY` or Vercel project OIDC credentials, so no `BROWSERBASE_API_KEY` is needed. See [Browserbase Search on AI Gateway](https://vercel.com/docs/ai-gateway/models-and-providers/web-search#using-browserbase-search).
|
|
227
232
|
|
|
228
233
|
Select the model vendor's own hosted search for a model routed through AI Gateway:
|
|
229
234
|
|
|
@@ -233,9 +238,19 @@ import { webSearch } from "eve/tools/web_search";
|
|
|
233
238
|
export default webSearch({ provider: "native" });
|
|
234
239
|
```
|
|
235
240
|
|
|
236
|
-
The vendor runs the search server-side and returns citations:
|
|
241
|
+
The vendor runs the search server-side and returns citations:
|
|
242
|
+
|
|
243
|
+
| Model vendor | Search |
|
|
244
|
+
| -------------------------- | ----------------------- |
|
|
245
|
+
| OpenAI | OpenAI web search |
|
|
246
|
+
| Anthropic | Anthropic web search |
|
|
247
|
+
| Google, Gemini 3 and later | Google Search grounding |
|
|
248
|
+
|
|
249
|
+
AI Gateway uses its usual credentials, so no `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or Google key is needed. Every other Gateway model, including one picked by a dynamic model resolver and Gemini models before Gemini 3, doesn't get `web_search`.
|
|
250
|
+
|
|
251
|
+
eve picks the search tool from the requested model. A call that AI Gateway's `models` fallback serves with another vendor's model can therefore run without search.
|
|
237
252
|
|
|
238
|
-
|
|
253
|
+
Anthropic web search runs only on Anthropic's own API. AI Gateway tries another host when Amazon Bedrock or Google Vertex AI rejects the tool. If no host accepts it, eve retries the step without `web_search`.
|
|
239
254
|
|
|
240
255
|
Set `fallback` to give models without native search a provider that works with any Gateway model (`"exa"`, `"parallel"`, or `"browserbase"`):
|
|
241
256
|
|
|
@@ -247,7 +262,7 @@ export default webSearch({ provider: "native", fallback: "exa" });
|
|
|
247
262
|
|
|
248
263
|
The `provider` setting applies only to AI Gateway models. Direct OpenAI, Anthropic, and Gemini 3 and later models always use their native search; other direct models omit `web_search`.
|
|
249
264
|
|
|
250
|
-
eve identifies a direct model's vendor by its AI SDK provider name
|
|
265
|
+
eve identifies a direct model's vendor by its AI SDK provider name. A `createOpenAI()` model pointed at an OpenAI-compatible endpoint, such as Amazon Bedrock's, therefore gets OpenAI web search. When the endpoint rejects it, eve retries the step without `web_search`, so each step makes one rejected call first. To avoid that, give the provider its own name, so the agent gets no `web_search`:
|
|
251
266
|
|
|
252
267
|
```ts title="agent/agent.ts"
|
|
253
268
|
import { createOpenAI } from "@ai-sdk/openai";
|
|
@@ -262,8 +277,6 @@ const mantle = createOpenAI({
|
|
|
262
277
|
export default defineAgent({ model: mantle("openai.gpt-5.6-sol") });
|
|
263
278
|
```
|
|
264
279
|
|
|
265
|
-
The agent then gets no `web_search`, the same as other direct models without native search.
|
|
266
|
-
|
|
267
280
|
Replace provider-managed search with an authored implementation:
|
|
268
281
|
|
|
269
282
|
```ts title="agent/tools/web_search.ts"
|
|
@@ -304,7 +317,7 @@ To let the model choose an AI Gateway model for each root-copy task, export `age
|
|
|
304
317
|
export { agentWithModel as default } from "eve/tools/agent";
|
|
305
318
|
```
|
|
306
319
|
|
|
307
|
-
|
|
320
|
+
`agentWithModel` is a separate workflow tool that calls `ctx.agent("agent", { model })`; the default `agent` tool has no `model` parameter. It accepts:
|
|
308
321
|
|
|
309
322
|
```ts
|
|
310
323
|
{
|
|
@@ -314,9 +327,9 @@ This is a separate workflow tool that calls `ctx.agent("agent", { model })`. The
|
|
|
314
327
|
}
|
|
315
328
|
```
|
|
316
329
|
|
|
317
|
-
It otherwise
|
|
330
|
+
It otherwise behaves like the default tool, and `taskId` continues the same root-copy session. The selected model applies to every turn in that session, so a continuation must repeat the original model; start a new task to use another. Because the parent model picks the value, use this tool only when it may choose any model your AI Gateway credentials and policies allow.
|
|
318
331
|
|
|
319
|
-
An authored
|
|
332
|
+
An authored `agent/tools/agent.ts` replaces the framework tool. Re-export the default definition, export `agentWithModel`, export another tool such as `agentRouter()`, or disable the slot. `agentRouter()` runs each call as a [task](/docs/tools/workflows#run-calls-as-tasks-task), which adds `eve__task_wait` and `eve__task_cancel`:
|
|
320
333
|
|
|
321
334
|
```ts title="agent/tools/agent.ts"
|
|
322
335
|
import { disableTool } from "eve/tools";
|
|
@@ -326,46 +339,77 @@ export default disableTool();
|
|
|
326
339
|
|
|
327
340
|
### `eve__search`, `eve__tool`, and `eve__skill`
|
|
328
341
|
|
|
329
|
-
|
|
342
|
+
The catalog tools let the model reach what isn't in its tool list. `eve__search` finds tools defined with `deferred: true`, agents defined with `tool: "deferred"`, every tool from the agent's [connections](../connections), and deferred [skills](../skills). `eve__tool` calls a deferred tool, agent, or connection tool by name, and `eve__skill` loads a skill, deferred or not. There is no add command; eve adds each one when the session has something it reaches, even when `defaultTools` is `false`:
|
|
330
343
|
|
|
331
344
|
- `eve__tool` comes with anything it can call: a deferred tool or agent, or a connection.
|
|
332
345
|
- `eve__skill` comes with any skill, so an agent whose only catalog entries are listed skills gets `eve__skill` alone.
|
|
333
346
|
- `eve__search` comes with anything it could find: whatever `eve__tool` can call, plus deferred skills.
|
|
334
347
|
- A session with none of these gets no catalog tools.
|
|
335
348
|
|
|
336
|
-
|
|
349
|
+
Declared entries count from the session's first step, and an entry a dynamic resolver returns counts from the step where it first appears. A resolver in `agent/tools/` that returns only non-deferred tools adds no catalog tools. Once a session has a catalog tool, it keeps it, even after a resolver stops returning the entry that brought it.
|
|
350
|
+
|
|
351
|
+
#### `eve__search`
|
|
352
|
+
|
|
353
|
+
`eve__search({ query, limit? })` returns the best matches, up to `limit` (default 10, at most 50). `query` is required and must contain a word. It isn't a regular expression, and eve ignores characters that can't appear in a name, such as a leading `^`.
|
|
354
|
+
|
|
355
|
+
| Match | Fields | Use with |
|
|
356
|
+
| -------------- | ------------------------------------------------------------------------------------------ | ------------ |
|
|
357
|
+
| Tool | `tool` name, `description`, and a TypeScript `signature` rendered from its schemas | `eve__tool` |
|
|
358
|
+
| Deferred skill | `skill` name, `description`, and the `path` of its `SKILL.md` when it has supporting files | `eve__skill` |
|
|
359
|
+
|
|
360
|
+
A very long signature drops its property descriptions before any property name. Next to `results`, `searched` counts the entries the query covered, and `remaining` counts the matches past `limit`. A connection behind sign-in counts as its one sign-in result, and an unavailable connection counts as none.
|
|
361
|
+
|
|
362
|
+
Tools and skills rank together, in tiers:
|
|
337
363
|
|
|
338
|
-
|
|
339
|
-
|
|
340
|
-
|
|
341
|
-
|
|
342
|
-
|
|
343
|
-
- `eve__skill({ name })` loads the named skill, deferred or not, and returns its instructions. An unknown name fails with the closest skill names, a tool's name fails with a reminder to call it with `eve__tool` or directly, and a name that matches a connection says to find its tools with `eve__search({ query: "<connection>__" })`.
|
|
364
|
+
1. An entry whose name is exactly the query.
|
|
365
|
+
2. An entry whose name after its last `__` is the query, such as `linear__create_issue` for `create_issue`.
|
|
366
|
+
3. The tools of a connection named by the query, so `eve__search({ query: "linear" })` lists the `linear` connection's tools first.
|
|
367
|
+
4. Entries whose names, or names after their last `__`, start with the query.
|
|
368
|
+
5. Keyword matches in names, parameters, and descriptions. One-letter and filler words such as `a` and `the` don't count unless the query has nothing else.
|
|
344
369
|
|
|
345
|
-
|
|
370
|
+
A query whose first word contains `__` searches one namespace: everything before its last `__`, without trailing underscores. `eve__search` keeps names under `<namespace>__` and anything named exactly the namespace, such as a connection's sign-in entry, then ranks them by the whole query. `eve__search({ query: "linear__" })` returns only the `linear` connection's tools, or its sign-in result. Connections that can't own names in that namespace don't appear in `unavailable`. A namespace that matches nothing fails with the closest connection names.
|
|
346
371
|
|
|
347
|
-
|
|
372
|
+
`eve__search` never asks the user to sign in. A connection whose server won't list its tools until sign-in appears as one result named after the connection, such as `linear`. A connection whose tools fail to load, or take longer than 10 seconds, appears under `unavailable`. Its `error` reads, for example, `"crm" did not list its tools within 10s. Try again later.` Matches from everything else still return. An `eve__tool` call on that connection's tools fails with the same error.
|
|
348
373
|
|
|
349
|
-
|
|
374
|
+
#### `eve__tool` and `eve__skill`
|
|
375
|
+
|
|
376
|
+
- `eve__tool({ name: "linear" })`, with a connection's own name, asks the user to sign in when the connection's tools need it. It returns once the tools can be listed, so the next `eve__search` finds them. If the server lists its tools without sign-in, it confirms they are available without asking.
|
|
377
|
+
- `eve__tool({ name, input? })` calls the entry named `name` with `input`, which defaults to `{}`. A connection tool's name is `<connection>__<tool>`, such as `linear__list_issues`. A call fails with the entry's signature when the input fails its schema, and with the closest names when the name is unknown. A skill's name fails with a reminder to use `eve__skill`. When the server asks for the user's authorization, the call asks the user to sign in and waits until sign-in completes.
|
|
378
|
+
- eve cancels a connection tool call that the server doesn't answer within 5 minutes. The call fails with an error such as `"linear" did not answer list_issues within 5 minutes. It may still have run, so check before you retry.` A tool that changes data may already have made the change.
|
|
379
|
+
- `eve__skill({ name })` loads the named skill, deferred or not, and returns its instructions. An unknown name fails with the closest skill names. A tool's name fails with a reminder to call it with `eve__tool` or directly. A connection's name says to find its tools with `eve__search({ query: "<connection>__" })`.
|
|
380
|
+
|
|
381
|
+
Once `eve__tool` or `eve__skill` resolves its entry, the call runs like a direct call. Approval policies, workflow tools and tasks, agents, `endsTurn`, `toModelOutput`, hooks, and stream events all see the entry's own name and input, such as `linear__list_issues`. Only model history records `eve__tool` or `eve__skill`. Loading a skill emits `call.requested` with `capability: { kind: "skill", name }`, then `call.settled`.
|
|
382
|
+
|
|
383
|
+
#### What the model is told
|
|
384
|
+
|
|
385
|
+
eve lists what the model can reach in an append-only context message, not the system prompt. The message lists:
|
|
386
|
+
|
|
387
|
+
- which kinds of deferred entries exist
|
|
388
|
+
- up to 20 namespaces, the first `__` segment of deferred names, such as `sre` for `sre__list_alerts`
|
|
389
|
+
- up to 20 connections with their descriptions
|
|
390
|
+
|
|
391
|
+
It never names a deferred entry, so deferred entries stay out of context until `eve__search` finds them. A later step appends the listing again only when it changes.
|
|
392
|
+
|
|
393
|
+
#### Reserved `eve` names
|
|
394
|
+
|
|
395
|
+
The tools eve adds itself live in the `eve` namespace: `eve__search`, `eve__tool`, `eve__skill`, `eve__task_wait`, `eve__task_cancel`, and `eve__reply`. No tool, subagent, skill, connection, or extension mount, static or dynamic, may be named `eve` or start with `eve__`. The compiler rejects an authored tool, skill, connection, or mount with such a name, such as `agent/tools/eve__search.ts`. eve rejects an authored subagent when the agent loads, and a dynamic entry when its resolver returns it. Any other name is free, including `search` and `execute`.
|
|
350
396
|
|
|
351
397
|
### `eve__task_wait` and `eve__task_cancel`
|
|
352
398
|
|
|
353
|
-
eve adds `eve__task_wait` and `eve__task_cancel` when the agent has a tool that runs its calls as [tasks](/docs/tools/tasks)
|
|
399
|
+
eve adds `eve__task_wait` and `eve__task_cancel` when the agent has a tool that runs its calls as [tasks](/docs/tools/tasks). These are the built-in `agent` tool, declared subagents, remote agents, `agentRouter()`, the `workflow` tool, and authored workflow tools that define `task(input, ctx)` or `serve(receive, ctx)`. There is no add command.
|
|
354
400
|
|
|
355
|
-
- `eve__task_wait({ timeoutSeconds? })`
|
|
356
|
-
- `eve__task_cancel({ taskId })` stops a task's current work and says so
|
|
401
|
+
- `eve__task_wait({ timeoutSeconds? })` waits until any task has a result, a new message arrives, or `timeoutSeconds` pass. It returns at once when a result is already waiting. The turn stays running, not paused, because `turn.paused` only reports approvals, questions, and other requests for input. Results arrive in a `<task_result>` message right after it returns. Waiting never stops a task.
|
|
402
|
+
- `eve__task_cancel({ taskId })` stops a task's current work and says so. When the task already finished or is an idle [resumable task](/docs/tools/workflows#resumable-tasks-serve), it says the task had no work to stop. An id that names no task fails with `UNKNOWN_TASK`. Cancelling an agent task ends it; other resumable tasks stay available after a cancel.
|
|
357
403
|
|
|
358
404
|
Review these tools before production use. Disable, wrap, restrict, or require approval for any tool that can access the filesystem, network, shell, or sensitive data.
|
|
359
405
|
|
|
360
|
-
You can also add the opt-in framework tools described below.
|
|
361
|
-
|
|
362
406
|
## Opt-in framework tools
|
|
363
407
|
|
|
364
|
-
These
|
|
408
|
+
These tools are not added by default. Add only the ones the agent needs, and remove the file to remove the tool; `disableTool()` is unnecessary.
|
|
365
409
|
|
|
366
410
|
### `ask_question`
|
|
367
411
|
|
|
368
|
-
`ask_question` lets the model ask the user one question,
|
|
412
|
+
`ask_question` lets the model ask the user one question, optionally with two or three options, and waits for the answer. [Human-in-the-loop](/docs/human-in-the-loop#questions) covers its input, results, and how channels show it. Add it:
|
|
369
413
|
|
|
370
414
|
```sh
|
|
371
415
|
eve add tool/ask_question
|
|
@@ -377,7 +421,7 @@ import { askQuestion } from "eve/tools/ask_question";
|
|
|
377
421
|
export default askQuestion;
|
|
378
422
|
```
|
|
379
423
|
|
|
380
|
-
`ask_question` is a [workflow tool](/docs/tools/workflows) that calls `ctx.ask()`.
|
|
424
|
+
`ask_question` is a [workflow tool](/docs/tools/workflows) that calls `ctx.ask()`. A steering message that doesn't answer the question withdraws it, and the model reads `{ interrupted: true }` as `Stopped early because a new message arrived.`, then the message. In a session that cannot request input, such as a [markdown schedule](/docs/schedules#markdown-form-fire-and-forget), the result is `{ status: "unavailable" }` and the model continues on its own judgment.
|
|
381
425
|
|
|
382
426
|
### `glob`
|
|
383
427
|
|
|
@@ -403,11 +447,9 @@ export default defineTool({
|
|
|
403
447
|
});
|
|
404
448
|
```
|
|
405
449
|
|
|
406
|
-
Remove the file to remove the tool. `disableTool()` is unnecessary because `glob` is not added by default.
|
|
407
|
-
|
|
408
450
|
### `grep`
|
|
409
451
|
|
|
410
|
-
`grep` searches file contents
|
|
452
|
+
`grep` searches sandbox file contents with a regular expression. It searches the workspace root unless the model passes a directory or file inside the workspace. The code extension's `code__grep` tool behaves the same. Add it:
|
|
411
453
|
|
|
412
454
|
```sh
|
|
413
455
|
eve add tool/grep
|
|
@@ -429,21 +471,13 @@ export default defineTool({
|
|
|
429
471
|
});
|
|
430
472
|
```
|
|
431
473
|
|
|
432
|
-
|
|
433
|
-
|
|
434
|
-
Inputs are `pattern`, optional `path`, `glob`, `ignoreCase`, `literal`, `context`, `limit`, and
|
|
435
|
-
`outputMode`. `files_with_matches` is the default and lists paths; `content` returns matching
|
|
436
|
-
lines and `count` returns per-file totals. Identifier-like patterns use literal matching unless
|
|
437
|
-
`literal: false` is explicit. The default limit is 50 rows, capped at 200, with additional byte
|
|
438
|
-
and line bounds. Relative paths resolve against the workspace root; `$HOME` paths, parent traversal, and symlinks
|
|
439
|
-
outside it are rejected. Ripgrep respects `.gitignore`; the POSIX fallback does not.
|
|
474
|
+
Inputs are `pattern`, optional `path`, `glob`, `ignoreCase`, `literal`, `context`, `limit`, and `outputMode`. Omit `outputMode` to list matching paths (`files_with_matches`); `content` returns matching lines and `count` returns per-file totals. Identifier-like patterns match literally unless `literal: false` is explicit. The default limit is 50 rows, capped at 200, with additional byte and line bounds.
|
|
440
475
|
|
|
441
|
-
Results contain `content`, `matchCount`, `outputMode`, `path`, and `truncated`.
|
|
442
|
-
`outputMode: "content"` to return matching lines.
|
|
476
|
+
Relative paths resolve against the workspace root; `$HOME` paths, parent traversal, and symlinks outside it are rejected. When the sandbox has ripgrep, results respect `.gitignore`; otherwise they don't. Results contain `content`, `matchCount`, `outputMode`, `path`, and `truncated`.
|
|
443
477
|
|
|
444
478
|
### `no_reply`
|
|
445
479
|
|
|
446
|
-
`no_reply` ends the turn without a reply.
|
|
480
|
+
`no_reply` ends the turn without a reply. It fits a scheduled check that finds nothing to report, or an action the agent already took is the whole answer. The model calls it with an optional `{ reason }`, which stays in session history and traces and is never sent. Channels and schedule sends post nothing, and later turns see that the agent chose to stay quiet. Add it:
|
|
447
481
|
|
|
448
482
|
```sh
|
|
449
483
|
eve add tool/no_reply
|
|
@@ -455,13 +489,13 @@ import { noReply } from "eve/tools/no_reply";
|
|
|
455
489
|
export default noReply;
|
|
456
490
|
```
|
|
457
491
|
|
|
458
|
-
`no_reply` is a `defineTool` tool with [`endsTurn: true`](/docs/tools#end-the-turn-after-a-tool-call), so the turn ends only when no other tool runs in the same step. Only root sessions receive it. Slack clears the thread status when the turn completes.
|
|
492
|
+
`no_reply` is a `defineTool` tool with [`endsTurn: true`](/docs/tools#end-the-turn-after-a-tool-call), so the turn ends only when no other tool runs in the same step. Only root sessions receive it. Slack clears the thread status when the turn completes.
|
|
459
493
|
|
|
460
|
-
|
|
494
|
+
Without `no_reply`, a root session also accepts an empty model reply with `finishReason: "stop"` and completes the turn without a final message. Use `no_reply` to record an explicit choice to stay quiet, with a reason. Delegated sessions retry an empty reply once and report a failure if it stays empty, so the caller can act on it.
|
|
461
495
|
|
|
462
496
|
### `sleep`
|
|
463
497
|
|
|
464
|
-
`sleep` pauses and
|
|
498
|
+
`sleep` pauses the current turn and resumes it later, without keeping the application runtime running. The wait survives restarts. The model calls it with `{ seconds }`. Concurrent calls run in parallel, and the turn resumes after the longest wait. A steering message, the default for a new message, ends the wait early: the model reads `{ interrupted: true }` as `Stopped early because a new message arrived.`, then the message. Add it:
|
|
465
499
|
|
|
466
500
|
```sh
|
|
467
501
|
eve add tool/sleep
|
|
@@ -485,8 +519,6 @@ export default defineWorkflowTool({
|
|
|
485
519
|
});
|
|
486
520
|
```
|
|
487
521
|
|
|
488
|
-
Remove the file to remove the tool. `disableTool()` is unnecessary because `sleep` is not added by default.
|
|
489
|
-
|
|
490
522
|
## What to read next
|
|
491
523
|
|
|
492
524
|
- [Tools](../tools): define your own tools, gate them on approval, and shape their output with `toModelOutput`
|
|
@@ -3,20 +3,20 @@ title: "Context Control"
|
|
|
3
3
|
description: "Choose what an eve agent's model sees and when, across instructions, skills, tools, the workspace, and subagents."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
Control context by putting information in the narrowest surface that needs it. Keep permanent rules in instructions
|
|
6
|
+
Control context by putting information in the narrowest surface that needs it. Keep permanent rules in instructions and load optional procedures as skills. Let the model inspect runtime files through sandbox tools, and delegate specialist work to a subagent.
|
|
7
7
|
|
|
8
8
|
## Recommended context layout
|
|
9
9
|
|
|
10
|
-
| Need | Use
|
|
11
|
-
| ---------------------------------------------------- |
|
|
12
|
-
| Permanent identity, rules, or constraints | System-role [instructions](../instructions)
|
|
13
|
-
|
|
|
14
|
-
| A procedure needed only for some tasks | A [skill](../skills)
|
|
15
|
-
| A typed action or external operation | A [tool](../tools) or [connection](../connections)
|
|
16
|
-
| Files or command execution | The [sandbox workspace](../sandbox)
|
|
17
|
-
| A specialist with a separate prompt and
|
|
18
|
-
| Instructions or
|
|
19
|
-
|
|
|
10
|
+
| Need | Use | What the model sees |
|
|
11
|
+
| ---------------------------------------------------- | -------------------------------------------------- | -------------------------------------------------------------------------------- |
|
|
12
|
+
| Permanent identity, rules, or constraints | System-role [instructions](../instructions) | System context on every model call |
|
|
13
|
+
| Application or retrieved context kept in history | User-role [instructions](../instructions) | A message in conversation history, added at session start or when it changes |
|
|
14
|
+
| A procedure needed only for some tasks | A [skill](../skills) | Its description until the model loads the full skill |
|
|
15
|
+
| A typed action or external operation | A [tool](../tools) or [connection](../connections) | The callable schema and the result of each call |
|
|
16
|
+
| Files or command execution | The [sandbox workspace](../sandbox) | A workspace hint, then files and command output the model requests through tools |
|
|
17
|
+
| A specialist with a separate prompt and tools | A [subagent](../subagents) | The child's reply as the tool result |
|
|
18
|
+
| Instructions, tools, or skills that vary by caller | A [dynamic value](../guides/dynamic-capabilities) | The values resolved for the active session |
|
|
19
|
+
| Context recalled from storage that outlives sessions | [Memory](../memory) | User-role messages labeled with their memory slot, placed before the turn input |
|
|
20
20
|
|
|
21
21
|
## Base identity with `instructions.md`
|
|
22
22
|
|
|
@@ -24,7 +24,7 @@ Use system-role instructions for stable behavior that should apply throughout a
|
|
|
24
24
|
|
|
25
25
|
### Compose instructions in TypeScript with `instructions.ts`
|
|
26
26
|
|
|
27
|
-
Use `instructions.ts` when you need typed helpers, build-time composition, or a user-role message. User-role instructions become ordinary
|
|
27
|
+
Use `instructions.ts` when you need typed helpers, build-time composition, or a user-role message. User-role instructions become ordinary conversation history rather than system context. See [Instructions](../instructions) for both formats, directory composition, and runtime resolution.
|
|
28
28
|
|
|
29
29
|
## Load procedures on demand with `skills/`
|
|
30
30
|
|
|
@@ -42,7 +42,7 @@ Use a directory with `SKILL.md` when the procedure also needs references, assets
|
|
|
42
42
|
|
|
43
43
|
Do not paste a file tree or large working dataset into the prompt. Seed files into the sandbox workspace and let the model inspect them through `bash`, `read_file`, `glob`, and the other sandbox-backed tools. Skill package files use a separate runtime skill directory.
|
|
44
44
|
|
|
45
|
-
See [Sandbox](../sandbox) for workspace seeding, runtime access, backends, and
|
|
45
|
+
See [Sandbox](../sandbox) for workspace seeding, runtime access, backends, and how long a sandbox lives.
|
|
46
46
|
|
|
47
47
|
## Delegate to a specialist with a subagent
|
|
48
48
|
|
|
@@ -52,19 +52,19 @@ See [Subagents](../subagents) for the distinction between root-agent copies and
|
|
|
52
52
|
|
|
53
53
|
## Dynamic context with `defineDynamic`
|
|
54
54
|
|
|
55
|
-
Use `defineDynamic` when instructions, skills, tools, subagents, or the model depend on the
|
|
55
|
+
Use `defineDynamic` when instructions, skills, tools, subagents, or the model depend on the caller, tenant, channel, conversation, or feature state. The function reads the recorded session and returns the value or `null`. eve evaluates it before each ordinary model call, and `ctx.memo(key, fn)` keeps JSON observations across evaluations.
|
|
56
56
|
|
|
57
57
|
See [Dynamic capabilities](../guides/dynamic-capabilities) for the context, memo rules, supported folders, and evaluation timing.
|
|
58
58
|
|
|
59
59
|
## Compaction and clear
|
|
60
60
|
|
|
61
|
-
Before
|
|
61
|
+
Before each model call, eve measures the history together with the system instructions and advertised tool schemas against the compaction threshold. The measurement starts from the provider's last reported input usage when one exists.
|
|
62
62
|
|
|
63
|
-
Compaction reserves space for those instructions and tools
|
|
63
|
+
Compaction reserves space for those instructions and tools and reduces only conversation history. It can't shrink the instructions or tool catalog, so keep them within the selected model's context window.
|
|
64
64
|
|
|
65
|
-
User-role instructions
|
|
65
|
+
User-role instructions are part of history. Compaction can summarize them, and clear removes them without reinserting unchanged instructions. System-role instructions remain outside history and continue to apply after either operation.
|
|
66
66
|
|
|
67
|
-
Recalled memory stays outside history too. eve recalls before the first model call of each turn, and every later model call reads that turn's recall just ahead of the turn's input. Compaction
|
|
67
|
+
Recalled memory stays outside history too. eve recalls before the first model call of each turn, and every later model call reads that turn's recall just ahead of the turn's input. Compaction doesn't summarize it, and a provider can capture before compaction rewrites history. Clear drops what earlier turns recalled, though not the provider's external data, and the next turn recalls again.
|
|
68
68
|
|
|
69
69
|
## What to read next
|
|
70
70
|
|
|
@@ -72,5 +72,5 @@ Recalled memory stays outside history too. eve recalls before the first model ca
|
|
|
72
72
|
- [Skills](../skills): provide procedures that load on demand.
|
|
73
73
|
- [Sandbox](../sandbox): give the model files and command execution.
|
|
74
74
|
- [Subagents](../subagents): isolate specialist work.
|
|
75
|
-
- [Dynamic capabilities](../guides/dynamic-capabilities): vary
|
|
76
|
-
- [Memory](../memory):
|
|
75
|
+
- [Dynamic capabilities](../guides/dynamic-capabilities): vary instructions, tools, and skills by session.
|
|
76
|
+
- [Memory](../memory): recall context from storage that outlives a session.
|
|
@@ -3,11 +3,11 @@ title: "Default Harness"
|
|
|
3
3
|
description: "How eve manages model context and compaction during an agent turn."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
The default harness is eve's built-in agent loop. It manages model calls, compaction, and tool execution.
|
|
6
|
+
The default harness is eve's built-in agent loop. It manages model calls, compaction, and tool execution. See [Built-in tools](./built-in-tools) for its model-facing defaults and opt-ins, and [Execution model and durability](./execution-model-and-durability) for how turns checkpoint and resume.
|
|
7
7
|
|
|
8
8
|
## Compaction
|
|
9
9
|
|
|
10
|
-
|
|
10
|
+
Compaction keeps a long session from overflowing the model's context window. The harness compacts when the conversation, plus the compaction prompt's estimated size, reaches `compaction.threshold` of the window. It then summarizes the older turns into a checkpoint and keeps going. Omit `compaction.threshold` to compact at `0.9`. Tune it under [`compaction`](../agent-config#compaction) in `agent.ts`:
|
|
11
11
|
|
|
12
12
|
```ts title="agent/agent.ts"
|
|
13
13
|
export default defineAgent({
|
|
@@ -18,43 +18,27 @@ export default defineAgent({
|
|
|
18
18
|
});
|
|
19
19
|
```
|
|
20
20
|
|
|
21
|
-
Before summarizing, eve tries to shorten oversized tool results in older history.
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
`ClientSession.compact()`, a channel route's `compact(address)`, or
|
|
39
|
-
`attachSession(sessionId).compact()`. The request does not append a user message;
|
|
40
|
-
if a turn is running, eve queues it until that turn settles. A manual compaction is
|
|
41
|
-
the same context change as automatic compaction: `context.started` and
|
|
42
|
-
`context.settled` with `kind: "compaction"`.
|
|
43
|
-
|
|
44
|
-
After either kind of compaction, eve moves the idle session to a fresh workflow
|
|
45
|
-
run on the same deployment, so a long session's run history does not keep
|
|
46
|
-
growing. See [Execution model and durability](./execution-model-and-durability#compaction-handoff).
|
|
47
|
-
|
|
48
|
-
To discard model-message history instead of summarizing it, call the corresponding
|
|
49
|
-
`clear()` method on any of those handles. Clearing preserves the session identity,
|
|
50
|
-
system prompt, configured tools and skills, durable state, limits, and sandbox.
|
|
51
|
-
It removes recalled memory records and framework memory bookkeeping, but it
|
|
52
|
-
does not delete data from a memory provider's external store.
|
|
53
|
-
On the stream it is a context change with `kind: "clear"`: `context.started`, then `context.settled`.
|
|
21
|
+
Before summarizing, eve tries to shorten oversized tool results in older history. If that can't free enough space, eve summarizes. eve measures the space against the provider's last reported input token count, plus an estimate for new messages.
|
|
22
|
+
|
|
23
|
+
The summary prompt asks the compaction model to separate completed progress and decisions from remaining work. It also asks the model to keep the constraints, preferences, data, and references needed to continue. A later compaction passes the previous summary in full and replaces it with an updated one. Omit `compaction.model` to summarize with the active turn model.
|
|
24
|
+
|
|
25
|
+
After compacting, the harness keeps the most recent messages word for word next to the summary. It keeps up to 20,000 tokens or half the threshold, whichever is smaller, and shortens their tool results to 2,000 characters. The current user message is always kept. When that message alone exceeds the budget, the harness keeps its start and end with a note at the cut. It summarizes the middle with the older turns.
|
|
26
|
+
|
|
27
|
+
If compaction can't bring the history under the threshold, the session fails with an error instead of compacting again, and the step isn't retried. Start a new session or send a smaller message.
|
|
28
|
+
|
|
29
|
+
The summary call retries transient provider errors like any model call. If it fails for another reason, the turn fails with `MODEL_CALL_FAILED` and the history stays uncompacted. After a transient error such as a 429, the session waits for the next message.
|
|
30
|
+
|
|
31
|
+
[Memory](../memory) stays outside history, so the summarizer never sees it. eve asks providers to capture before compaction rewrites history, and what earlier turns recalled follows the checkpoint.
|
|
32
|
+
|
|
33
|
+
Clients and channels can request compaction between turns with `ClientSession.compact()`, a channel route's `compact(address)`, or `attachSession(sessionId).compact()`. The request doesn't append a user message. If a turn is running, eve queues the request until that turn ends. On the stream, manual and automatic compaction are the same context change: `context.started` and `context.settled` with `kind: "compaction"`.
|
|
34
|
+
|
|
35
|
+
After either kind of compaction, eve moves the idle session to a fresh workflow run on the same deployment. This keeps a long session's run history from growing. See [Execution model and durability](./execution-model-and-durability#compaction-handoff).
|
|
36
|
+
|
|
37
|
+
To discard model-message history instead of summarizing it, call `clear()` on any of those handles. Clearing keeps the session identity, system prompt, configured tools and skills, [`defineState`](./state) values, limits, and sandbox. It removes recalled memory, but doesn't delete data from a memory provider's external store. On the stream, clear is a context change with `kind: "clear"`: `context.started`, then `context.settled`.
|
|
54
38
|
|
|
55
39
|
## What to read next
|
|
56
40
|
|
|
57
41
|
- [Built-in tools](./built-in-tools): review the default and opt-in framework tools and configure the model-facing tool set
|
|
58
42
|
- [Execution model and durability](./execution-model-and-durability): understand how turns checkpoint and resume
|
|
59
43
|
- [Context control](./context-control): choose what the model sees and when
|
|
60
|
-
- [Memory](../memory):
|
|
44
|
+
- [Memory](../memory): recall context from earlier sessions on every turn
|