eve 0.89.0 → 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.
Files changed (247) hide show
  1. package/CHANGELOG.md +39 -9
  2. package/dist/src/channel/adapter.d.ts +12 -3
  3. package/dist/src/channel/adapter.js +1 -1
  4. package/dist/src/channel/auth/definitions.d.ts +7 -20
  5. package/dist/src/channel/auth/definitions.js +1 -1
  6. package/dist/src/channel/auth/http-basic.js +1 -1
  7. package/dist/src/channel/auth/jwt-ecdsa.js +1 -1
  8. package/dist/src/channel/auth/jwt-hmac.js +1 -1
  9. package/dist/src/channel/auth/oidc.js +1 -1
  10. package/dist/src/channel/auth/result.d.ts +2 -3
  11. package/dist/src/channel/auth/result.js +1 -1
  12. package/dist/src/channel/channel-address.d.ts +1 -1
  13. package/dist/src/channel/channel-address.js +1 -1
  14. package/dist/src/channel/channel-operations.d.ts +1 -1
  15. package/dist/src/channel/schedule.js +1 -1
  16. package/dist/src/channel/types.d.ts +2 -0
  17. package/dist/src/chunks/{use-eve-agent-Bbl4H5aA.js → use-eve-agent-Bwloorf8.js} +77 -63
  18. package/dist/src/chunks/{use-eve-agent-CNpxgKEH.js → use-eve-agent-XCB0-tLX.js} +77 -63
  19. package/dist/src/cli/dev/environment.js +1 -1
  20. package/dist/src/cli/dev/tui/prompt-commands.d.ts +1 -1
  21. package/dist/src/cli/dev/tui/remote-connection-probe.js +1 -1
  22. package/dist/src/cli/dev/tui/remote-connection-types.d.ts +1 -0
  23. package/dist/src/cli/dev/tui/runner.js +2 -2
  24. package/dist/src/cli/dev/tui/status-line.d.ts +2 -2
  25. package/dist/src/cli/dev/tui/status-line.js +1 -1
  26. package/dist/src/client/agent-info-schema.d.ts +341 -326
  27. package/dist/src/client/agent-info-schema.js +1 -1
  28. package/dist/src/client/agent-info-types.d.ts +13 -10
  29. package/dist/src/client/client-error.d.ts +1 -1
  30. package/dist/src/client/client.d.ts +5 -3
  31. package/dist/src/client/client.js +1 -1
  32. package/dist/src/client/session.d.ts +1 -1
  33. package/dist/src/compiled/.vendor-stamp.json +1 -1
  34. package/dist/src/evals/target.js +1 -1
  35. package/dist/src/eve-channel/auth.d.ts +19 -0
  36. package/dist/src/eve-channel/auth.js +1 -0
  37. package/dist/src/eve-channel/index.d.ts +1 -0
  38. package/dist/src/eve-channel/index.js +1 -1
  39. package/dist/src/eve-channel/types.d.ts +23 -4
  40. package/dist/src/execution/catalog/connection-entry.js +1 -1
  41. package/dist/src/execution/coordination-dispatch-shared.js +1 -1
  42. package/dist/src/execution/dynamic-workflow/tool.js +1 -1
  43. package/dist/src/execution/proxied-deliver-step.js +1 -1
  44. package/dist/src/execution/sandbox/bash.js +2 -2
  45. package/dist/src/execution/session/active-turn.js +1 -1
  46. package/dist/src/execution/session/admission.d.ts +6 -0
  47. package/dist/src/execution/session/admission.js +1 -1
  48. package/dist/src/execution/session/delivery-facts.js +1 -1
  49. package/dist/src/execution/session/next-input.d.ts +2 -2
  50. package/dist/src/execution/session/next-input.js +1 -1
  51. package/dist/src/execution/session/program.js +1 -1
  52. package/dist/src/execution/session-inbox/inbox.d.ts +2 -2
  53. package/dist/src/execution/session-inbox/inbox.js +1 -1
  54. package/dist/src/execution/session-inbox/protocol.js +1 -1
  55. package/dist/src/execution/tools/agent-router-workflow.js +1 -1
  56. package/dist/src/harness/compaction/engine.js +2 -2
  57. package/dist/src/harness/current-messages.js +1 -1
  58. package/dist/src/harness/emission.d.ts +3 -0
  59. package/dist/src/harness/emission.js +1 -1
  60. package/dist/src/harness/facts.d.ts +5 -2
  61. package/dist/src/harness/facts.js +1 -1
  62. package/dist/src/harness/model-call/call.d.ts +7 -1
  63. package/dist/src/harness/model-call/call.js +3 -1
  64. package/dist/src/harness/provider-tool-history.d.ts +8 -0
  65. package/dist/src/harness/provider-tool-history.js +1 -1
  66. package/dist/src/harness/session-machine/transitions.d.ts +3 -2
  67. package/dist/src/harness/step/after-model.js +1 -1
  68. package/dist/src/harness/step/context.js +1 -1
  69. package/dist/src/harness/step/intake.js +1 -1
  70. package/dist/src/harness/step/prompt.js +1 -1
  71. package/dist/src/harness/tool-history-repair.d.ts +2 -0
  72. package/dist/src/harness/tool-history-repair.js +1 -1
  73. package/dist/src/harness/tool-loop.js +1 -1
  74. package/dist/src/internal/application/stamped-package-version.js +1 -1
  75. package/dist/src/internal/authored-module-graph.js +1 -1
  76. package/dist/src/internal/nitro/routes/agent-info/build-agent-info-response.d.ts +2 -2
  77. package/dist/src/protocol/routes.d.ts +7 -1
  78. package/dist/src/protocol/routes.js +1 -1
  79. package/dist/src/protocol/session-events/families/delivery.d.ts +5 -3
  80. package/dist/src/protocol/session-events/families/delivery.js +1 -1
  81. package/dist/src/protocol/session-projection/fold.js +1 -1
  82. package/dist/src/public/channels/discord/hitl.js +1 -1
  83. package/dist/src/public/channels/github/githubChannel.js +1 -1
  84. package/dist/src/public/channels/github/state.d.ts +7 -0
  85. package/dist/src/public/channels/github/state.js +1 -1
  86. package/dist/src/public/channels/mcp.js +1 -1
  87. package/dist/src/public/channels/slack/hitl.d.ts +2 -1
  88. package/dist/src/public/channels/slack/hitl.js +3 -3
  89. package/dist/src/public/channels/slack/interaction-cards.js +1 -1
  90. package/dist/src/public/channels/slack/request-card-render.js +1 -1
  91. package/dist/src/public/channels/teams/hitl.js +1 -1
  92. package/dist/src/public/channels/teams/verify.js +1 -1
  93. package/dist/src/public/channels/telegram/telegramChannel.js +1 -1
  94. package/dist/src/public/connections/index.d.ts +1 -1
  95. package/dist/src/public/definitions/channel.js +1 -1
  96. package/dist/src/public/definitions/connections/tool-call.d.ts +2 -2
  97. package/dist/src/public/definitions/hook.d.ts +90 -7
  98. package/dist/src/public/definitions/hook.js +1 -1
  99. package/dist/src/public/hooks/index.d.ts +3 -2
  100. package/dist/src/reactions/continuation.d.ts +19 -0
  101. package/dist/src/reactions/continuation.js +1 -0
  102. package/dist/src/reactions/frame.js +1 -1
  103. package/dist/src/reactions/intents.d.ts +10 -4
  104. package/dist/src/reactions/intents.js +1 -1
  105. package/dist/src/reactions/kinds/hook.js +1 -1
  106. package/dist/src/reactions/runner.js +1 -1
  107. package/dist/src/reactions/state.d.ts +15 -2
  108. package/dist/src/reactions/state.js +1 -1
  109. package/dist/src/runtime/channels/registry.d.ts +2 -2
  110. package/dist/src/runtime/channels/registry.js +1 -1
  111. package/dist/src/runtime/connections/approval-scope.d.ts +9 -0
  112. package/dist/src/runtime/connections/approval-scope.js +1 -0
  113. package/dist/src/runtime/connections/mcp-client.d.ts +1 -1
  114. package/dist/src/runtime/connections/mcp-client.js +1 -1
  115. package/dist/src/runtime/connections/provided-arguments.js +1 -1
  116. package/dist/src/runtime/resolve-connection.js +1 -1
  117. package/dist/src/runtime/subagents/workflow.js +1 -1
  118. package/dist/src/setup/primitives/open-url.js +1 -1
  119. package/dist/src/setup/scaffold/create/project.js +1 -1
  120. package/dist/src/shared/agent-info-access.d.ts +5 -0
  121. package/dist/src/shared/agent-info-access.js +1 -0
  122. package/dist/src/shared/connection-types.d.ts +21 -4
  123. package/dist/src/shared/value-delta.d.ts +5 -4
  124. package/dist/src/shared/value-delta.js +1 -1
  125. package/dist/src/svelte/index.js +1 -1
  126. package/dist/src/svelte/use-eve-agent.js +1 -1
  127. package/dist/src/tools/provided/ask-question-workflow.js +1 -1
  128. package/dist/src/tools/provided/sleep-workflow.js +1 -1
  129. package/dist/src/tools/provided/web-fetch.js +1 -1
  130. package/dist/src/vue/index.js +1 -1
  131. package/dist/src/vue/use-eve-agent.js +1 -1
  132. package/docs/agent-config.md +199 -222
  133. package/docs/channels/chat-sdk.mdx +60 -64
  134. package/docs/channels/custom.mdx +265 -280
  135. package/docs/channels/discord.mdx +176 -123
  136. package/docs/channels/eve.mdx +136 -204
  137. package/docs/channels/github.mdx +24 -22
  138. package/docs/channels/linear.mdx +30 -30
  139. package/docs/channels/linq.mdx +25 -13
  140. package/docs/channels/mcp.mdx +154 -116
  141. package/docs/channels/overview.mdx +31 -32
  142. package/docs/channels/photon.mdx +32 -56
  143. package/docs/channels/slack.mdx +538 -375
  144. package/docs/channels/teams.mdx +40 -26
  145. package/docs/channels/telegram.mdx +13 -13
  146. package/docs/channels/twilio.mdx +11 -11
  147. package/docs/code-extension.mdx +40 -42
  148. package/docs/concepts/built-in-tools.md +89 -57
  149. package/docs/concepts/context-control.md +20 -20
  150. package/docs/concepts/default-harness.md +20 -36
  151. package/docs/concepts/execution-model-and-durability.mdx +96 -160
  152. package/docs/concepts/project-structure.mdx +21 -14
  153. package/docs/concepts/security-model.md +27 -27
  154. package/docs/concepts/sessions-runs-and-streaming.md +184 -194
  155. package/docs/concepts/state.md +7 -15
  156. package/docs/connections/mcp.mdx +109 -93
  157. package/docs/connections/openapi.mdx +57 -59
  158. package/docs/connections/overview.mdx +205 -170
  159. package/docs/evals/assertions.mdx +36 -29
  160. package/docs/evals/cases.mdx +38 -42
  161. package/docs/evals/judge.mdx +21 -29
  162. package/docs/evals/overview.mdx +42 -38
  163. package/docs/evals/reporters.mdx +54 -27
  164. package/docs/evals/running.mdx +15 -8
  165. package/docs/evals/targets.mdx +17 -18
  166. package/docs/evals/tool-stubs.mdx +111 -97
  167. package/docs/experimental/dynamic-schedules.mdx +118 -63
  168. package/docs/extensions.md +58 -65
  169. package/docs/getting-started.mdx +4 -6
  170. package/docs/guides/auth-and-route-protection.md +100 -70
  171. package/docs/guides/client/continuations.mdx +23 -26
  172. package/docs/guides/client/messages.mdx +47 -66
  173. package/docs/guides/client/output-schema.mdx +8 -8
  174. package/docs/guides/client/overview.mdx +47 -41
  175. package/docs/guides/client/streaming.mdx +62 -71
  176. package/docs/guides/decide.md +24 -79
  177. package/docs/guides/deployment/meta.json +1 -1
  178. package/docs/guides/deployment/overview.md +27 -18
  179. package/docs/guides/deployment/self-hosted-operations.md +99 -0
  180. package/docs/guides/deployment/self-hosting.md +63 -80
  181. package/docs/guides/deployment/vercel.mdx +31 -27
  182. package/docs/guides/deployment/workflow-worlds.md +100 -0
  183. package/docs/guides/dev-tui.md +48 -41
  184. package/docs/guides/dynamic-capabilities.md +49 -50
  185. package/docs/guides/frontend/nextjs.mdx +2 -2
  186. package/docs/guides/frontend/nuxt.mdx +11 -11
  187. package/docs/guides/frontend/overview.mdx +1 -1
  188. package/docs/guides/frontend/sveltekit.mdx +11 -11
  189. package/docs/guides/frontend/tanstack.mdx +16 -16
  190. package/docs/guides/frontend/use-eve-agent-svelte.mdx +21 -21
  191. package/docs/guides/frontend/use-eve-agent-vue.mdx +22 -22
  192. package/docs/guides/frontend/use-eve-agent.mdx +25 -25
  193. package/docs/guides/hooks.md +152 -106
  194. package/docs/guides/instrumentation/agent-runs.mdx +26 -30
  195. package/docs/guides/instrumentation/instrumentation.mdx +49 -76
  196. package/docs/guides/instrumentation/meta.json +1 -1
  197. package/docs/guides/instrumentation/otel.mdx +113 -179
  198. package/docs/guides/prepare-for-1-0.md +23 -1
  199. package/docs/guides/remote-agents.md +125 -187
  200. package/docs/guides/self-modification.md +18 -18
  201. package/docs/guides/session-context.md +16 -16
  202. package/docs/install-integrations.mdx +26 -24
  203. package/docs/instructions.mdx +37 -42
  204. package/docs/memory/custom-provider.md +35 -41
  205. package/docs/memory/file.md +93 -76
  206. package/docs/memory/overview.mdx +145 -156
  207. package/docs/patterns/durable-cross-channel-notifications.md +15 -19
  208. package/docs/patterns/dynamic-scheduling.md +19 -23
  209. package/docs/patterns/multi-tenant-approvals.md +17 -22
  210. package/docs/patterns/multi-tenant-auth.md +43 -42
  211. package/docs/patterns/multi-tenant-memory.md +39 -36
  212. package/docs/patterns/voice-notes.md +3 -3
  213. package/docs/protocols/acp.md +13 -13
  214. package/docs/protocols/ucp.mdx +7 -7
  215. package/docs/reference/agent-files.md +6 -6
  216. package/docs/reference/cli.md +99 -98
  217. package/docs/reference/telemetry.md +1 -1
  218. package/docs/reference/typescript-api.md +52 -53
  219. package/docs/responsible-use.md +2 -2
  220. package/docs/sandbox/custom-providers.mdx +60 -56
  221. package/docs/sandbox/default.mdx +23 -24
  222. package/docs/sandbox/docker.mdx +16 -10
  223. package/docs/sandbox/index.mdx +93 -61
  224. package/docs/sandbox/just-bash.mdx +17 -11
  225. package/docs/sandbox/troubleshooting.mdx +29 -23
  226. package/docs/sandbox/vercel.mdx +45 -52
  227. package/docs/schedules.mdx +65 -54
  228. package/docs/skills.mdx +74 -49
  229. package/docs/subagents/index.mdx +97 -136
  230. package/docs/tools/human-in-the-loop.md +160 -90
  231. package/docs/tools/meta.json +1 -1
  232. package/docs/tools/overview.mdx +229 -237
  233. package/docs/tools/tasks.md +118 -117
  234. package/docs/tools/workflows.mdx +447 -543
  235. package/docs/tutorial/connect-a-warehouse.mdx +11 -13
  236. package/docs/tutorial/first-agent.mdx +14 -16
  237. package/docs/tutorial/guard-the-spend.mdx +6 -8
  238. package/docs/tutorial/how-it-runs.mdx +8 -8
  239. package/docs/tutorial/query-sample-data.mdx +8 -8
  240. package/docs/tutorial/remember-definitions.mdx +4 -4
  241. package/docs/tutorial/run-analysis.mdx +20 -22
  242. package/docs/tutorial/ship-it.mdx +19 -19
  243. package/docs/tutorial/team-playbooks.mdx +9 -9
  244. package/docs/use-cases.mdx +13 -11
  245. package/package.json +1 -1
  246. package/docs/guides/instrumentation/migration.md +0 -96
  247. package/docs/tools/tasks-upgrade.md +0 -218
@@ -4,7 +4,9 @@ description: "Reach your agent from GitHub App webhooks, with comment invocation
4
4
  type: integration
5
5
  ---
6
6
 
7
- The GitHub channel lets the agent work directly on a repository. Add its invocation token, such as `@my-agent`, to a new issue, PR, or review comment and the agent answers in that thread, with the PR diff already in context and the repo checked out into the sandbox. The token is an eve convention: GitHub may not autocomplete it or render it as a linked mention. The channel takes GitHub App webhooks at `/eve/v1/github`, checks the signature, derives auth from whoever triggered the event, and replies on the native surface. Credentials can run through [Vercel Connect](../guides/auth-and-route-protection), which manages the GitHub App, the installation token, and inbound webhook verification, so there's no app private key or webhook secret for you to hold. See [Channels](./overview) for the contract this builds on.
7
+ The GitHub channel lets people reach your agent from issues and pull requests. It lives in `agent/channels/github.ts`. Write the agent's invocation token, such as `@my-agent`, in a new issue, PR, or review comment, and the agent replies in that thread. It sees the PR diff and works in a checkout of the repo.
8
+
9
+ [Vercel Connect](../guides/auth-and-route-protection) can manage the GitHub App, its token, and webhook checks, so you hold no private key or webhook secret. See [Channels](./overview) for what all channels share.
8
10
 
9
11
  ## Guided Connect setup
10
12
 
@@ -14,11 +16,7 @@ Run the registry setup from the agent directory:
14
16
  eve add channel/github
15
17
  ```
16
18
 
17
- The flow signs you in to Vercel when needed, creates or links a Vercel project, provisions an app-scoped GitHub Connect client, and registers `/eve/v1/github` as a trigger destination. It then installs `@vercel/connect` and writes `agent/channels/github.ts` with the connector UID.
18
-
19
- Vercel Connect creates the GitHub App, receives and verifies its webhooks, and forwards them to the deployed agent. After deploying, open the GitHub App in the Connect dashboard and install it in the organization or account where you want to use it. Add the generated invocation token (for example, `@my-agent`) to a new issue, pull request, or review comment to start a conversation. GitHub may not autocomplete the token or render it as a linked mention.
20
-
21
- The generated channel uses Connect-managed credentials:
19
+ The command signs you in to Vercel, links a project, and creates an app-scoped GitHub Connect client that sends webhooks to `/eve/v1/github`. It then installs `@vercel/connect` and writes the channel file:
22
20
 
23
21
  ```ts title="agent/channels/github.ts"
24
22
  import { connectGitHubCredentials } from "@vercel/connect/eve";
@@ -30,11 +28,11 @@ export default githubChannel({
30
28
  });
31
29
  ```
32
30
 
33
- `connectGitHubCredentials` returns `{ installationToken, webhookVerifier }`: eve uses the Connect-managed installation token directly for GitHub API calls, skipping its native App JWT exchange, and verifies Connect-forwarded webhooks by their Vercel OIDC signature instead of a GitHub webhook secret. Token rotation, refresh, and multi-installation tenancy stay inside Connect, so there is no `GITHUB_APP_ID`, `GITHUB_APP_PRIVATE_KEY`, or `GITHUB_WEBHOOK_SECRET` to manage.
31
+ Connect creates the GitHub App and forwards its webhooks, and eve checks their Vercel OIDC signature. Connect also handles token rotation and multiple installations. After you deploy, open the GitHub App in the Connect dashboard and install it in your organization or account.
34
32
 
35
33
  ### Bring your own GitHub App
36
34
 
37
- To run a GitHub App you manage yourself, pass its credentials directly instead:
35
+ To run a GitHub App you manage yourself, pass its credentials directly:
38
36
 
39
37
  ```ts title="agent/channels/github.ts"
40
38
  import { githubChannel } from "eve/channels/github";
@@ -49,7 +47,7 @@ export default githubChannel({
49
47
  });
50
48
  ```
51
49
 
52
- Every field falls back to an env var, so you can drop the `credentials` block entirely once these are set:
50
+ Omit any field, or the whole `credentials` block, to read it from these env vars:
53
51
 
54
52
  ```bash
55
53
  GITHUB_APP_ID=... # GitHub App id
@@ -58,17 +56,19 @@ GITHUB_WEBHOOK_SECRET=... # verifies the webhook signature
58
56
  GITHUB_APP_SLUG=... # supplies botName when it is not set in config
59
57
  ```
60
58
 
61
- `appId`/`privateKey`/`webhookSecret` also take a lazy resolver function if you'd rather fetch them on demand, and so does `botName`: it resolves on first use inside request handling, caches on success, and retries on the next event after a failure, so a resolver that depends on request-scoped credentials works in production. When `botName` is not configured, the channel falls back to the credentials' `appSlug`, then to `GITHUB_APP_SLUG`.
59
+ `appId`, `privateKey`, `webhookSecret`, and `botName` also accept a function. A `botName` function runs when a webhook arrives, so it can use that request's credentials. eve keeps its result, or tries again on the next event if it fails. Omit `botName` to use the credentials' `appSlug`, then `GITHUB_APP_SLUG`.
62
60
 
63
- Point the GitHub App webhook URL at `https://<deployment>/eve/v1/github`. For comment-invoked turns, subscribe to `issue_comment` and `pull_request_review_comment`; add `issues`, `pull_request`, `check_suite`, `check_run`, or `workflow_run` if you wire up their opt-in hooks. After installing the App for the repository, a new comment that includes `@botName` starts a turn. This is a text invocation token, not a GitHub-native mention: GitHub may display the App as `botName[bot]`, but it may not autocomplete or link `@botName`.
61
+ Point the GitHub App webhook URL at `https://<deployment>/eve/v1/github`. Subscribe to `issue_comment` and `pull_request_review_comment` so comments reach the agent. Add `issues`, `pull_request`, `check_suite`, `check_run`, or `workflow_run` for their opt-in hooks. Install the App on the repository, and a new comment that includes `@botName` starts a turn.
62
+
63
+ The invocation token is plain text, not a GitHub mention, so GitHub may not autocomplete or link `@botName`. GitHub may show the App as `botName[bot]`.
64
64
 
65
65
  ## How the channel handles messages
66
66
 
67
67
  ### Dispatch
68
68
 
69
- Inbound hooks return `{ auth }` to dispatch, or `null` to ignore. Return `title` alongside `auth` to set the title when the dispatch starts a run. Use `defaultGitHubAuth(ctx)` to derive auth from the actor.
69
+ Each hook returns `{ auth }` to start a turn or `null` to ignore the event. Add `title` to set the run title when the event starts a run. `defaultGitHubAuth(ctx)` builds auth from the person who triggered the event.
70
70
 
71
- The model-visible `<github_context>` includes `sender`, `bot_name` when resolved, and `is_mentioned` for comments. eve computes `is_mentioned` before removing the invocation token.
71
+ The model sees a `<github_context>` block with `sender` and, when known, `bot_name`. For comments it also has `is_mentioned`, which eve sets before it removes the invocation token from the text.
72
72
 
73
73
  ```ts
74
74
  import { defaultGitHubAuth, githubChannel } from "eve/channels/github";
@@ -93,37 +93,39 @@ export default githubChannel({
93
93
  });
94
94
  ```
95
95
 
96
- The CI hooks expose normalized `action`, `status`, `conclusion`, `app.slug`, `headSha`, and `pullRequests` fields, plus `checkSuiteId`, `checkRunId`, or `workflowRunId`. `workflow_run` is a GitHub Actions-only event, so its normalized `app.slug` is `"github-actions"`. A dispatched CI turn is anchored to the first number in `pullRequests`; the hook still runs when the array is empty, but it must return `null` because there is no issue or PR thread for the session.
96
+ The CI hooks expose normalized `action`, `status`, `conclusion`, `app.slug`, `headSha`, and `pullRequests` fields, plus `checkSuiteId`, `checkRunId`, or `workflowRunId`. For `workflow_run`, which only GitHub Actions sends, `app.slug` is `"github-actions"`. A CI turn replies on the first PR in `pullRequests`. When the array is empty, the hook still runs but must return `null`, because there is no thread to reply in.
97
97
 
98
98
  ### Delivery
99
99
 
100
- When a turn starts, the channel adds an `eyes` reaction to the triggering comment (turn this off with `progress: { reactions: false }`). The reply comes back as a comment, on the timeline or in the review thread, and splits across multiple comments when it runs long. If the turn fails, you get a short error comment carrying an error id.
100
+ When a turn starts, the channel adds an `eyes` reaction to the comment that triggered it. Set `progress: { reactions: false }` to skip it. The reply posts as a comment on the timeline or in the review thread, split across several comments when long. A failed turn posts a short error comment with an error id.
101
101
 
102
102
  ### Human-in-the-loop (HITL)
103
103
 
104
- GitHub comments have no interactive button or card affordance. A human-in-the-loop (HITL) request, an `interaction.opened` fact, is posted as a comment prompt, and the user's reply comment maps back to the pending request. Declare an `events["interaction.opened"]` handler to customize the prompt.
104
+ GitHub comments have no buttons or cards, so an approval or question posts as a comment. The user answers it with a reply comment. Declare an `events["interaction.opened"]` handler to change the prompt.
105
105
 
106
106
  ### Proactive sessions
107
107
 
108
- Start a session without an inbound comment invocation through `to(github, target).send(message, { auth })` from a schedule `run` handler, or `ctx.to(github, target).send(message, { auth })` from another channel. The target requires `owner`, `repo`, and exactly one of `issueNumber` or `pullRequestNumber`. This sends turn input to the agent; it is not a direct GitHub comment.
108
+ To start a session without a comment, call `to(github, target).send(message, { auth })` from a schedule's `run` handler. From another channel, call `ctx.to(github, target).send(message, { auth })`. The target needs `owner`, `repo`, and exactly one of `issueNumber` or `pullRequestNumber`. This sends a message to the agent, not a comment to GitHub.
109
109
 
110
- To post without invoking the model, use `ctx.channel.thread.post(...)` inside a GitHub event handler. For application-managed retries and deduplication across providers, see [Durable cross-channel notifications](../patterns/durable-cross-channel-notifications).
110
+ To post without invoking the model, use `ctx.channel.thread.post(...)` inside a GitHub event handler. To retry and deduplicate notifications across providers yourself, see [Durable cross-channel notifications](../patterns/durable-cross-channel-notifications).
111
111
 
112
112
  ### Attachments
113
113
 
114
- Inbound file attachments are not supported on this channel today. Repository contents reach the agent through the sandbox checkout below, not as message attachments.
114
+ The channel doesn't accept inbound file attachments. Repository contents reach the agent through the [sandbox checkout](#sandbox-checkout).
115
115
 
116
116
  ### PR context
117
117
 
118
- Summon the agent on a PR and it always sees the diff. PR metadata and the changed-file patch land in `context`. Large generated files still appear in the list, but their patch body is dropped; add more paths to the skip list with `pullRequestContext.excludedFiles`.
118
+ On a PR, the agent always gets the PR metadata and the patch of each changed file in `context`. Large generated files stay in the file list without their patch. Add more paths to skip with `pullRequestContext.excludedFiles`.
119
119
 
120
120
  ### Sandbox checkout
121
121
 
122
- Before the first model call, every triggered turn checks out the relevant ref into the sandbox, so `read_file`/`glob`/`grep`/`bash` all run against the real tree. The installation token never enters the sandbox. `git` fetches a token-free URL, and the platform injects auth on egress at the firewall. That requires a firewall-capable backend (Vercel); the local backend skips checkout. Within a session, checkout is incremental across turns.
122
+ Before the first model call, each turn checks out the repo into the sandbox. `read_file`, `glob`, `grep`, and `bash` then work on the real files.
123
+
124
+ The installation token never enters the sandbox, because the sandbox firewall adds auth to outbound `git` requests. Checkout needs a sandbox with a firewall (Vercel), so the local sandbox skips it.
123
125
 
124
126
  ### Arbitrary API calls
125
127
 
126
- For anything the channel doesn't wrap, call `ctx.github.request({ method, path, body })`. It carries installation-token auth.
128
+ For any other GitHub API call, use `ctx.github.request({ method, path, body })`. It sends the installation token.
127
129
 
128
130
  ## What to read next
129
131
 
@@ -4,7 +4,9 @@ description: "Reach your agent through Linear Agent Sessions, with native Agent
4
4
  type: integration
5
5
  ---
6
6
 
7
- The Linear channel uses Linear's Agent Session surface rather than ordinary comments. Users delegate work to the agent from Linear, eve receives `AgentSessionEvent` webhooks at `/eve/v1/linear`, and the channel replies with native Agent Activities, including `thought`, `action`, `elicitation`, `response`, and `error`. Credentials can run through [Vercel Connect](../guides/auth-and-route-protection), which manages the Linear app, its access token, and inbound webhook verification, so there's no API key or webhook secret for you to hold. See [Channels](./overview) for the contract this builds on.
7
+ The Linear channel lets people delegate issues to your agent, or mention it, in Linear. It lives in `agent/channels/linear.ts` and uses Linear Agent Sessions. The agent shows its progress and answers as native Agent Activities: `thought`, `action`, `elicitation`, `response`, and `error`.
8
+
9
+ [Vercel Connect](../guides/auth-and-route-protection) can manage the Linear app, its token, and webhook checks, so you hold no API key or webhook secret. See [Channels](./overview) for what all channels share.
8
10
 
9
11
  ## Guided Connect setup
10
12
 
@@ -20,11 +22,7 @@ To let the agent search and update Linear through MCP, install the separate Line
20
22
  eve add connection/linear
21
23
  ```
22
24
 
23
- The channel setup flow signs you in to Vercel when needed, creates or links a Vercel project, reuses a compatible existing connector when available or provisions an app-scoped Linear Connect client, and registers `/eve/v1/linear` as a trigger destination. It then installs `@vercel/connect` and writes `agent/channels/linear.ts` with the connector UID.
24
-
25
- Vercel Connect creates the Linear app with the `app:assignable` and `app:mentionable` scopes required for Agent Sessions, receives and verifies `AgentSessionEvent` webhooks, and forwards them to the deployed agent. After deploying, open the Linear app in the Connect dashboard and install it in the workspace where you want to delegate work. Then delegate an issue or mention the agent in a Linear Agent Session.
26
-
27
- The generated channel uses Connect-managed credentials:
25
+ The channel command signs you in to Vercel, links a project, and reuses or creates an app-scoped Linear Connect client that sends webhooks to `/eve/v1/linear`. It then installs `@vercel/connect` and writes the channel file:
28
26
 
29
27
  ```ts title="agent/channels/linear.ts"
30
28
  import { connectLinearCredentials } from "@vercel/connect/eve";
@@ -35,11 +33,11 @@ export default linearChannel({
35
33
  });
36
34
  ```
37
35
 
38
- `connectLinearCredentials` returns `{ accessToken, webhookVerifier }`: eve uses the Connect-managed app token for Linear GraphQL calls and verifies Connect-forwarded webhooks by their Vercel OIDC signature instead of a Linear webhook secret. Token rotation, refresh, and multi-workspace tenancy stay inside Connect, so there is no `LINEAR_AGENT_ACCESS_TOKEN` or `LINEAR_WEBHOOK_SECRET` to manage.
36
+ Connect creates the Linear app with the `app:assignable` and `app:mentionable` scopes that Agent Sessions require. Connect forwards the app's webhooks, and eve checks their Vercel OIDC signature. Connect also handles token rotation and multiple workspaces. After you deploy, open the Linear app in the Connect dashboard and install it in your workspace. Then delegate an issue or mention the agent.
39
37
 
40
38
  ### Bring your own Linear app
41
39
 
42
- To run a Linear OAuth app you manage yourself, pass its credentials directly instead:
40
+ To run a Linear OAuth app you manage yourself, pass its credentials directly:
43
41
 
44
42
  ```ts title="agent/channels/linear.ts"
45
43
  import { linearChannel } from "eve/channels/linear";
@@ -52,14 +50,12 @@ export default linearChannel({
52
50
  });
53
51
  ```
54
52
 
55
- Direct webhook verification accepts timestamps within 60 seconds by default, as Linear recommends. Set `maxSkewMs` to a larger number of milliseconds only when you intentionally accept delayed retries. Use the narrowest window that fits your retry policy.
56
-
57
53
  ```bash
58
54
  LINEAR_AGENT_ACCESS_TOKEN=lin_api_... # posts Agent Activities and creates proactive sessions
59
55
  LINEAR_WEBHOOK_SECRET=... # verifies Linear-Signature
60
56
  ```
61
57
 
62
- The sample passes credentials explicitly. To rely on env vars instead, drop the `credentials` block: the access token falls back to `LINEAR_AGENT_ACCESS_TOKEN`, `LINEAR_ACCESS_TOKEN`, `LINEAR_API_KEY`, or `LINEAR_API_TOKEN`, and the webhook secret falls back to `LINEAR_WEBHOOK_SECRET`. Both fields also accept lazy resolver functions.
58
+ Omit `credentials` to read the access token from `LINEAR_AGENT_ACCESS_TOKEN`, `LINEAR_ACCESS_TOKEN`, `LINEAR_API_KEY`, or `LINEAR_API_TOKEN`. The webhook secret then comes from `LINEAR_WEBHOOK_SECRET`. Both fields also accept a function.
63
59
 
64
60
  Create the Linear OAuth app, enable Agent Session events, and point the webhook URL at:
65
61
 
@@ -67,39 +63,45 @@ Create the Linear OAuth app, enable Agent Session events, and point the webhook
67
63
  https://<deployment>/eve/v1/linear
68
64
  ```
69
65
 
70
- For Linear's agent surface, configure the OAuth authorize URL with `actor=app` and grant the app scopes that let it appear as an agent in Linear, including `app:assignable` and `app:mentionable`. Subscribe to the `AgentSessionEvent` webhook category so Linear sends `created` events when the agent is delegated or mentioned and `prompted` events when the user continues the session.
66
+ Configure the OAuth authorize URL with `actor=app` and grant the scopes that let the app appear as an agent, including `app:assignable` and `app:mentionable`. Subscribe to the `AgentSessionEvent` webhook category. Linear then sends `created` when someone delegates to or mentions the agent, and `prompted` when the user replies.
67
+
68
+ eve checks the `Linear-Signature` HMAC over the raw body. It rejects a `webhookTimestamp` older than 60 seconds, as Linear recommends. Raise `maxSkewMs` (milliseconds) only to accept delayed retries, and keep it as small as your retry policy allows.
71
69
 
72
- Linear sends webhook signatures in `Linear-Signature`; eve verifies the HMAC over the raw body and rejects stale `webhookTimestamp` values. If a trusted gateway verifies Linear before the request reaches eve, pass `credentials.webhookVerifier` instead of a webhook secret. Your custom verifier must enforce its timestamp policy because `maxSkewMs` does not apply.
70
+ If a trusted gateway verifies Linear webhooks first, pass `credentials.webhookVerifier` instead of a webhook secret. `maxSkewMs` doesn't apply to a verifier, so the verifier must check timestamps itself.
73
71
 
74
72
  ## How the channel handles messages
75
73
 
76
74
  ### Dispatch
77
75
 
78
- The default hook dispatches `created` and `prompted` Agent Session events. The Linear context includes `app_user_id` when available, plus the agent session, issue, comment, and organization identifiers. The session continues with `agent-session:<id>`.
76
+ By default, `created` and `prompted` Agent Session events start a turn. The model sees the agent session, issue, comment, and organization ids, plus `app_user_id` when known. Each Linear Agent Session maps to one eve session, keyed `agent-session:<id>`.
79
77
 
80
78
  ### Delivery
81
79
 
82
- Turn start posts an ephemeral `thought`, tool calls post ephemeral `action` activities, final assistant text posts a durable `response`, and failures post `error` activities. When the model emits text before a tool call, eve buffers the first non-empty line and uses it as the next ephemeral Linear `thought`, mirroring Slack's typing-status behavior.
80
+ | Turn event | Agent Activity |
81
+ | ----------------------- | -------------------------------------------------- |
82
+ | Turn starts | Ephemeral `thought` |
83
+ | Text before a tool call | Ephemeral `thought`, from its first non-empty line |
84
+ | Tool call | Ephemeral `action` |
85
+ | Final assistant text | `response`, not ephemeral |
86
+ | Failure | `error` |
83
87
 
84
88
  ### Human-in-the-loop (HITL)
85
89
 
86
- Human-in-the-loop (HITL) input requests render as Linear `elicitation` activities. When the user replies to the Agent Session, the channel resolves that prompt back to the pending eve input request and resumes with `answers`.
90
+ Approvals and questions post as `elicitation` activities. The user's reply in the Agent Session answers the open one, and the turn continues.
87
91
 
88
92
  ### Connection authorization
89
93
 
90
- When a user-scoped connection needs authorization, the default channel posts Linear's native `auth` elicitation with the provider's sign-in URL, targeted to the Linear user who started the session. URL-less device flows render their instructions and user code as a plain elicitation. After authorization finishes, the channel posts a thought with the outcome; successful authorization indicates that the parked turn is resuming.
91
-
92
- ### Proactive sessions
93
-
94
- Start a session without an inbound webhook with `receive(linear, { target })`. See [Proactive sessions](#proactive-sessions) below for the target shape and examples.
94
+ When a connection needs the user to sign in, the channel posts Linear's native `auth` elicitation with the provider's sign-in URL. It goes to the user who started the session. A device flow without a URL posts its instructions and user code as a plain elicitation. When sign-in ends, the channel posts a `thought` with the result, and a successful sign-in continues the turn.
95
95
 
96
96
  ### Attachments
97
97
 
98
- Files uploaded to Linear and referenced in an Agent Session prompt, whether as markdown images (`![name](url)`) or file links (`[name](url)`) hosted at `https://uploads.linear.app`, are fetched with the resolved Linear access token and included as file parts. eve sends the bearer token only to that exact HTTPS origin; images and links from other hosts remain markdown text. If a Linear upload fails, an image reference returns non-image content, or a file link returns an HTML page, the reference becomes its label in the text, the agent gets a short note that the file couldn't be retrieved, and the text turn continues.
98
+ Markdown images (`![name](url)`) and file links (`[name](url)`) in an Agent Session prompt reach the model as files. This works only for links to `https://uploads.linear.app`, which eve downloads with the Linear access token. eve sends the token only to that exact HTTPS origin, and links to other hosts stay Markdown text.
99
+
100
+ A file fails when the download fails, an image link returns non-image content, or a file link returns an HTML page. The link then becomes its label, and the agent gets a note that the file couldn't be retrieved. The turn continues.
99
101
 
100
102
  ### API handle
101
103
 
102
- Event handlers receive `channel.linear`, which exposes `createActivity`, `listActivities`, and `updateSession` for custom Agent Activity delivery and Agent Session metadata.
104
+ Event handlers receive `channel.linear`. Use its `createActivity`, `listActivities`, and `updateSession` methods to post your own Agent Activities and update the Agent Session.
103
105
 
104
106
  ### Low-level API helpers
105
107
 
@@ -114,7 +116,7 @@ channel context's API handle when it already has the configured credentials.
114
116
 
115
117
  ## Custom hooks
116
118
 
117
- Return `{ auth }` to dispatch, or `null` to acknowledge without waking the agent. Return `title` alongside `auth` to set the title when the dispatch starts a run.
119
+ Return `{ auth }` to start a turn, or `null` to accept the webhook without waking the agent. Add `title` to set the run title when the event starts a run.
118
120
 
119
121
  ```ts
120
122
  import { defaultLinearAuth, linearChannel } from "eve/channels/linear";
@@ -127,7 +129,7 @@ export default linearChannel({
127
129
  });
128
130
  ```
129
131
 
130
- Restrict dispatch to a subset of Linear teams or projects by inspecting `event.agentSession.issue` in `onAgentSession`. Add extra context by returning `context` alongside `auth`.
132
+ To restrict the agent to some Linear teams or projects, inspect `event.agentSession.issue`. Return `context` alongside `auth` to add background:
131
133
 
132
134
  ```ts
133
135
  import { defaultLinearAuth, linearChannel } from "eve/channels/linear";
@@ -143,7 +145,7 @@ export default linearChannel({
143
145
  });
144
146
  ```
145
147
 
146
- Override event delivery when you want more specific Agent Activities.
148
+ Override event handlers to post your own Agent Activities:
147
149
 
148
150
  ```ts
149
151
  import { linearChannel } from "eve/channels/linear";
@@ -167,7 +169,7 @@ export default linearChannel({
167
169
  });
168
170
  ```
169
171
 
170
- Add session-level links when your agent creates an external artifact.
172
+ Add session links when your agent creates an external artifact:
171
173
 
172
174
  ```ts
173
175
  await channel.linear.updateSession({
@@ -177,7 +179,7 @@ await channel.linear.updateSession({
177
179
 
178
180
  ## Proactive sessions
179
181
 
180
- Use the channel's proactive target to continue an existing Agent Session or create one from a Linear issue or root comment. The target accepts an existing `agentSessionId`, or an `issueId` or root `commentId` to create a new session before sending the message. The example below runs from a schedule; a route handler uses the same target shape through `ctx.to(...)`.
182
+ To start a session without a webhook, call `to(linear, target).send(message, { auth })`. The target continues an existing Agent Session by `agentSessionId`, or creates one from an `issueId` or root `commentId`. This example runs from a schedule; a route handler passes the same target to `ctx.to(...)`.
181
183
 
182
184
  ```ts
183
185
  import { defineSchedule } from "eve/schedules";
@@ -199,8 +201,6 @@ export default defineSchedule({
199
201
  });
200
202
  ```
201
203
 
202
- For issue or comment targets, the channel calls Linear's proactive Agent Session mutations before starting the eve turn. For an existing `agentSessionId`, it skips session creation and only seeds the continuation token.
203
-
204
204
  ## What to read next
205
205
 
206
206
  - [Channels overview](./overview): the channel contract and every built-in channel
@@ -3,9 +3,9 @@ title: Linq
3
3
  description: Connect an eve agent to iMessage and SMS through Linq.
4
4
  ---
5
5
 
6
- Use `linqChannel` to receive and reply to iMessage and SMS conversations through Linq.
6
+ The Linq channel connects your agent to iMessage and SMS conversations through `agent/channels/linq.ts`.
7
7
 
8
- Run `eve add channel/linq` to choose Vercel Connect or portable credentials. With Vercel Connect, eve signs you in and creates or links a Vercel project when needed. Then choose whether to create a managed Linq account and line or connect an existing account with its partner API token. eve fetches the phone numbers assigned to that account, and you select the numbers for the agent. eve configures the connector and webhook through Connect:
8
+ Run `eve add channel/linq` and choose Vercel Connect or portable credentials. With Vercel Connect, eve signs you in and links a Vercel project. It then asks whether to create a managed Linq account and line, or connect an existing account with its partner API token. You select the account's phone numbers for the agent, and eve configures the connector and webhook through Connect:
9
9
 
10
10
  ```ts title="agent/channels/linq.ts"
11
11
  import { connectLinqCredentials } from "@vercel/connect/eve";
@@ -16,13 +16,13 @@ export default linqChannel({
16
16
  });
17
17
  ```
18
18
 
19
- The default webhook route is `/eve/v1/linq`. The channel verifies forwarded webhooks with Vercel OIDC from the same project and environment by default, derives user auth from each message author, marks accepted messages as read, and continues the same eve session for every message in a Linq conversation. A new accepted message steers the active turn. Before answer output or local tool execution begins, steering can interrupt pending model generation. Executing tools finish first; after answer output starts, steering waits for the next committed workflow boundary. See [Overlapping messages](./overview#overlapping-messages).
19
+ The channel receives webhooks at `/eve/v1/linq` and, by default, verifies them with Vercel OIDC from the same project and environment. It builds auth from the person who sent each message, marks accepted messages as read, and keeps one eve session per Linq conversation.
20
20
 
21
- Set `turnPolicy: "queue"` when every response should finish before Linq starts the next message.
21
+ A message that arrives during a turn joins that turn, so the agent can take the correction into account. Set `turnPolicy: "queue"` to let every reply finish before the next message starts. See [Overlapping messages](./overview#overlapping-messages) for when a new message can interrupt the model.
22
22
 
23
- Images and other files people send reach the agent as file parts. eve downloads each one from Linq's CDN over HTTPS and passes the bytes. Downloads and redirects must resolve to public network addresses and have a 30-second timeout. A failed download, or a file over 25 MB, reaches the agent as a short note.
23
+ Images and other files people send reach the agent as file parts. eve downloads each one over HTTPS. Downloads and redirects must resolve to public network addresses and time out after 30 seconds. A failed download, or a file over 25 MB, reaches the agent as a short note instead.
24
24
 
25
- Customize inbound dispatch with `onMessage`. Return `null` to ignore a message, or return `title` alongside `auth` to set the title when the dispatch starts a run:
25
+ Customize inbound handling with `onMessage`. Return `null` to ignore a message, or return `title` alongside `auth` to set the run title when the message starts a run:
26
26
 
27
27
  ```ts
28
28
  export default linqChannel({
@@ -37,7 +37,7 @@ export default linqChannel({
37
37
  });
38
38
  ```
39
39
 
40
- Set `route` to override the webhook path or `webhookVerifier` (typed `LinqWebhookVerifier` from `eve/channels/linq`) to use a different trusted-forwarder verifier. A verifier receives the request and its raw body bytes, and rejects a webhook by throwing or returning a falsy value such as `null` or `false`.
40
+ Set `route` to change the webhook path, or `webhookVerifier` (typed `LinqWebhookVerifier` from `eve/channels/linq`) to use a different trusted-forwarder verifier. A verifier receives the request and its raw body bytes. It rejects a webhook by throwing or returning a falsy value such as `null` or `false`.
41
41
 
42
42
  ## Tapbacks
43
43
 
@@ -60,7 +60,15 @@ export default linqChannel({
60
60
  });
61
61
  ```
62
62
 
63
- The agent reads an accepted tapback as a message in the form iMessage uses when it shows a tapback as text, such as `Tapback: Loved “See you at 7”` or `Tapback: Removed a like tapback from a message`. The quoted text appears when Linq can return the message the tapback is on. `tapback.tapback` is `love`, `like`, `dislike`, `laugh`, `emphasize`, or `question`, or the emoji itself for an emoji tapback. `tapback.messageId` and `tapback.author` identify the message and the person. An accepted tapback starts or steers a turn like any other message, following `turnPolicy`. The agent's own tapbacks never reach `onTapback`. `onTapback` runs instead of `onMessage` for tapbacks, so repeat any sender checks from `onMessage` there. Tapbacks arrive through the `reaction.added` and `reaction.removed` webhook events, which `eve add channel/linq` subscribes to.
63
+ | Field | Value |
64
+ | ------------------- | ---------------------------------------------------------------------------------------------- |
65
+ | `tapback.tapback` | `love`, `like`, `dislike`, `laugh`, `emphasize`, `question`, or the emoji for an emoji tapback |
66
+ | `tapback.messageId` | The message the tapback is on |
67
+ | `tapback.author` | The person who sent it |
68
+
69
+ The agent reads an accepted tapback as iMessage's text form, such as `Tapback: Loved “See you at 7”` or `Tapback: Removed a like tapback from a message`. The quoted text appears when Linq can return the original message. An accepted tapback starts or steers a turn like any other message, following `turnPolicy`.
70
+
71
+ `onTapback` runs instead of `onMessage` for tapbacks, so repeat any sender checks from `onMessage` there. The agent's own tapbacks never reach it. Tapbacks arrive as `reaction.added` and `reaction.removed` webhook events, which `eve add channel/linq` subscribes to.
64
72
 
65
73
  To let the agent send tapbacks, export the channel's tapback tool from a file in `agent/tools/`. The file name becomes the tool name:
66
74
 
@@ -70,11 +78,13 @@ import linq from "../channels/linq";
70
78
  export default linq.tapbackTool();
71
79
  ```
72
80
 
73
- The model calls it with a standard tapback, such as `{ "tapback": "love" }`, or any single emoji, such as `{ "tapback": "🎉" }`, and eve reacts to the latest message someone sent in the conversation. A standard tapback's own emoji, such as `👍`, sends that tapback. The model can send a tapback alongside a reply. To let a tapback be the whole answer, also add [`no_reply`](../concepts/built-in-tools#no_reply). The tool is never added on its own, and subagents don't receive it. In a session that didn't come through this channel, such as a web chat, or before anyone has sent a message, the call fails with an error the model reads.
81
+ The model calls it with a standard tapback, such as `{ "tapback": "love" }`, or any single emoji, such as `{ "tapback": "🎉" }`. eve reacts to the latest message someone sent in the conversation. A standard tapback's own emoji, such as `👍`, sends that tapback.
82
+
83
+ The model can send a tapback alongside a reply; to let a tapback be the whole answer, also add [`no_reply`](../concepts/built-in-tools#no_reply). Subagents don't receive the tool. In a session from another channel, such as web chat, or before anyone has sent a message, the call returns an error to the model.
74
84
 
75
85
  ### Answer approvals with a tapback
76
86
 
77
- Return `answer` from `onTapback` to answer the input request eve posted in the message the tapback is on. A [tool approval](/docs/human-in-the-loop#approvals) offers the options `approve` and `cancel`, so a like or dislike on the approval prompt can approve or cancel it:
87
+ Return `answer` from `onTapback` to answer the approval or question in the message the tapback is on. A [tool approval](/docs/human-in-the-loop#approvals) offers the options `approve` and `deny`, so a like or dislike on the approval prompt can approve or deny it:
78
88
 
79
89
  ```ts title="agent/channels/linq.ts"
80
90
  import { connectLinqCredentials } from "@vercel/connect/eve";
@@ -92,11 +102,13 @@ export default linqChannel({
92
102
  });
93
103
  ```
94
104
 
95
- `answer` settles only the request posted in that message, and only while it is still waiting and offers that option. A tapback on any other message, or on a prompt that was already answered, reaches the agent as an ordinary tapback, such as `Tapback: Liked “Got it”`. The approval's response policy still decides whether the person who sent the tapback may answer. For a [question](/docs/human-in-the-loop#questions), return one of its option ids. To replace the text the agent receives for a tapback, return `message`. Don't set `message` to an option's id, label, or number: eve reads that text like a typed reply, which answers the first waiting approval no matter which message the tapback is on.
105
+ `answer` answers only the request posted in that message, and only while that request is still open and offers that option. A tapback on any other message, or on an answered prompt, reaches the agent as an ordinary tapback, such as `Tapback: Liked “Got it”`. The approval's response policy still decides whether the sender may answer. For a [question](/docs/human-in-the-loop#questions), return one of its option ids.
106
+
107
+ Return `message` to replace the text the agent receives for a tapback. Don't set `message` to an option's id, label, or number, because eve reads that text like a typed reply. A typed reply answers the first waiting approval, no matter which message the tapback is on.
96
108
 
97
109
  ## Other hosts
98
110
 
99
- For a host without Vercel Connect, choose **Use portable credentials** during `eve add channel/linq`. eve writes `LINQ_API_KEY` and `LINQ_WEBHOOK_SECRET` to `.env.local`.
111
+ On a host without Vercel Connect, choose **Use portable credentials** during `eve add channel/linq`. eve writes `LINQ_API_KEY` and `LINQ_WEBHOOK_SECRET` to `.env.local`.
100
112
 
101
113
  After deploying the agent:
102
114
 
@@ -116,7 +128,7 @@ export default linqChannel({
116
128
  });
117
129
  ```
118
130
 
119
- For direct Linq webhooks, pass `signingSecret`. A supplied `webhookVerifier` takes precedence over it.
131
+ A supplied `webhookVerifier` takes precedence over `signingSecret`.
120
132
 
121
133
  ## What to read next
122
134