Skip to content

refactor(api)!: unify naming and validate packed public types - #5007

Draft
OwenKephart wants to merge 4 commits into
api-cleanup/context-vocabularyfrom
api-cleanup/naming-conventions
Draft

OwenKephart wants to merge 4 commits into
api-cleanup/context-vocabularyfrom
api-cleanup/naming-conventions

Conversation

@OwenKephart

@OwenKephart OwenKephart commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

Summary

Inconsistent names and dependency-controlled declarations make the pre-1.0 surface harder to use and review. Align tool values, reporters, prompts, credentials, cancellation options, extension paths, and experimental APIs. Add per-entry declaration closures and isolated packed-consumer checks with no diagnostic baseline. This assembles #4999 with the cleanup stack without merging unrelated changes from newer main. Related to #4930; stacked on #5006.

Scope and boundaries

  • sleep, noReply, and askQuestion are values; webSearch is a named factory only. Reporter factories use camelCase, and React returns UseEveAgentReturn.
  • Computer use and explicit self-modification mounts live under eve/extensions/*. The router entry is eve/tools/agent_router. Package extension metadata, fixtures, and templates follow the paths.
  • Prompt definitions use content. Channel configs and credentials have one spelling. Continuation helpers accept objects; GitHub exports its helper. Redundant promise aliases are inlined.
  • Sandbox operation options use signal; eval and memory-backend contexts use abortSignal. Linear's activity signal remains domain data, not cancellation.
  • Connection callbacks use experimental: { events } and types from eve/experimental/connections. Connect's bridge metadata remains compatible with the installed SDK.
  • Next helpers preserve the app's generic config. Nuxt exports an opaque setup entry. Neither imports an entire framework declaration graph into eve's public signature.
  • The default sandbox exposes portable fallback options; advanced just-bash customization uses its explicit provider. just-bash 3.6 supplies declarations missing from 3.1. Linq declares its SDK peer; SDK-backed handles keep real class identity.
  • Reports cover every typed public entry, including ambient Workflow modules. Reviewed reachability/orphan allowlists retain intentional brands, helpers, and standalone authoring types. The immediate-any allowlist is empty, not a recursive proof about all generic instantiations.

This PR remains draft with its parent. The coordinated principal rename is not enabled without a compatible Connect release. Recompute the assembled contracts and reports after that change; no published contract history is rewritten.

Validation

  • All 59 workspace typecheck tasks passed on the assembled tree.
  • 14 packed-consumer cases passed with strict library checking: every typed entry, integration-specific peer groups, and standalone client inspection contracts. Consumers have no workspace dependency links and no diagnostic baseline.
  • 265 focused units passed for naming, prompts, reporters, channel APIs, and memory. Cancellation, connection-event, provider, and tool boundaries also passed focused tests; the default-provider migration case also passes.
  • Two real just-bash filesystem scenarios passed on 3.6 after the cancellation migration.
  • All docs checks, the invariant guard, focused lint, formatting, and diff checks passed before final report refreshes. Follow-up commits record reruns when needed.
  • The shape guard rejected a temporary optional field added behind the unchanged HealthResult export, then passed after restoration.
  • Full eve integration/scenario tiers and e2e were not run locally. Required CI checks remain the merge gate.

Review follow-through

The assembled reviewed tree passes all 59 workspace typecheck tasks, 15 packed/declaration-copy cases, 202 focused review units, 68 scoped integration cases, and the 23-case native grep suite. The packed matrix has no diagnostic baseline and covers every typed entry with its explicit peer group. Docs checks, declaration-shape checks, and the invariant guard pass. The default-provider migration contract also passes. No full eve test tier or local e2e run is claimed. The parent principal migration remains gated on Connect coordination.

External benchmark coordination

The benchmark bot reports an incomplete run: its external runner still generates connections/task-mcp.ts with the retired session.started resolver key. That template is outside this checkout. It needs a coordinated runner migration and a fresh benchmark; this PR does not restore legacy framework keys or disable the workflow. No green benchmark result is claimed.

Checklist

  • I added tests and documentation where relevant
  • I added a changeset if this touches the published eve package
  • DCO sign-off passes for every commit (git commit --signoff)

@vercel

vercel Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated
eve-docs Ready Ready Preview, v0 Oct 18, 2026 2:05am UTC
eve-pkg Ready Ready Preview, v0 Oct 18, 2026 2:05am UTC

@socket-security

socket-security Bot commented Oct 18, 2026 •

Copy link
Copy Markdown

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff Package Supply Chain
Security
Vulnerability Quality Maintenance License
Addednpm/​just-bash@​3.6.0941009995100

View full report

@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

Bundle + Package Summary: apps/fixtures/weather-agent

Key takeaways

  • Dependency delta: 9 peer deps added; 1 peer dep changed.

Delta vs api-cleanup/context-vocabulary (e00c7b5)

Area Metric Baseline Current Delta
Package Packed tarball 7.68 MB 7.69 MB +10.9 kB ⚠️
Package Unpacked publish size 26.98 MB 26.97 MB -5.5 kB ✅
Package Installed footprint 75.12 MB 75.11 MB -4.7 kB ✅
Package Published files 4280 4299 +19
Package Installed files 8291 8310 +19
Package Installed package instances 34 34 0
Package Distinct installed package names 32 32 0
Package Installed dependency edges 51 51 0
Package Installed optional peer edges 9 18 +9
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 21.05 MB 21.05 MB -50 B ✅
Runtime Public routes 17 17 0
Dependency manifest changes vs api-cleanup/context-vocabulary (e00c7b5)

Peer dependencies

  • Added: @linqapp/sdk@^0.47.1 (optional), @nuxt/kit@^4.0.0 (optional), @nuxt/schema@^4.0.0 (optional), @vercel/connect@^2.5.2 (optional), next@^16.0.0 (optional), react@^19.0.0 (optional), svelte@^5.0.0 (optional), vite@^8.3.1 (optional), vue@^3.5.0 (optional)
  • Changed: just-bash@^3.1.0 (optional) -> just-bash@^3.6.0 (optional)
Changed function payloads vs api-cleanup/context-vocabulary (e00c7b5) (2)
Function Status Baseline Current Delta Route changes
functions/__server.func changed 10.52 MB 10.52 MB -25 B ✅ none
functions/.well-known/workflow/v1/flow.func changed 10.52 MB 10.52 MB -25 B ✅ none

eve init install

Metric Baseline Current Delta
Installed footprint 113.50 MB 113.49 MB -4.7 kB ✅
Installed packages 97 97 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 45.25 MB 45.25 MB -5.5 kB ✅
devDependency package bytes 5.11 MB 5.11 MB 0 B ➖
Build Metadata
  • Preset: vercel
  • Nitro: nitro@3.0.260903-beta
  • Output directory: apps/fixtures/weather-agent/.vercel/output
  • Build metadata timestamp: 2026-10-18T02:06:09.424Z
  • Route aliases: 17 public, 1 internal (18 total aliases)
  • Vercel routes in config: 20
  • Severity legend: 🔴 dominant/large, 🟠 notable, 🟡 watch, ⚪ small
Package Drill-Down

Package Details

  • Package: eve@0.79.2
  • Package directory: packages/eve
  • Tarball: 7.69 MB (eve-0.79.2.tgz)
  • Unpacked payload: 26.97 MB across 4299 published files
  • Installed footprint: 75.11 MB across 8310 installed files
  • Installed root package: 26.97 MB
  • Installed dependencies: 48.14 MB
  • Installed package instances: 34
  • Distinct installed package names: 32
  • Installed dependency edges: 51
  • Installed optional peer edges: 18
  • Runtime dependencies: 2
  • Peer dependencies: 16 (15 optional)

Installed footprint is measured from an isolated temporary npm install of the packed tarball.
Graph metrics read only package.json files in package directories directly beneath a node_modules boundary, including nested boundaries. Each directory is one package instance; distinct names come from those manifests. Dependency edges count each unique name in dependencies or optionalDependencies per instance; optional peer edges count peerDependencies marked optional.

Heavy installed dependencies

  • eve: 26.97 MB (35.9%)
  • @rolldown/binding-linux-x64-gnu: 19.81 MB (26.4%)
  • ai: 8.24 MB (11.0%)
  • zod: 6.15 MB (8.2%)
  • undici: 3.58 MB (4.8%)
Publish payload breakdown
Published file size
🟠 dist/src/compiled/shadcn-registry/index.js       [#####...................] 3.85 MB 14.3%
🟠 dist/src/compiled/@photon-ai/chat-adapter-ime... [###.....................] 2.29 MB 8.5%
🟠 dist/src/compiled/@ai-sdk/code-mode/index.js     [#.......................] 1.03 MB 3.8%
🟡 dist/src/compiled/@vercel/blob/index.js          [#.......................] 604.9 kB 2.2%
🟡 dist/src/compiled/_chunks/workflow/undici-D-I... [#.......................] 521.9 kB 1.9%
🔴 Other published files                            [########################] 18.68 MB 69.3%
Installed footprint breakdown
Installed package size
🔴 eve                             [########################] 26.97 MB 35.9%
🔴 @rolldown/binding-linux-x64-gnu [##################......] 19.81 MB 26.4%
🔴 ai                              [#######.................] 8.24 MB 11.0%
🔴 zod                             [#####...................] 6.15 MB 8.2%
🟠 undici                          [###.....................] 3.58 MB 4.8%
🟠 nitro                           [##......................] 1.89 MB 2.5%
🔴 Other installed packages        [########................] 8.46 MB 11.3%
Runtime dependencies (2)
Package Range Notes
nitro 3.0.260903-beta
undici 8.10.2
Peer dependencies (16)
Package Range Notes
@linqapp/sdk ^0.47.1 optional peer
@nuxt/kit ^4.0.0 optional peer
@nuxt/schema ^4.0.0 optional peer
@opentelemetry/api ^1.0.0 optional peer
@vercel/connect ^2.5.2 optional peer
ai catalog:
braintrust ^3.0.0 optional peer
chat ^4.42.0 optional peer
dd-trace ^6.13.0 optional peer
just-bash ^3.6.0 optional peer
microsandbox ^0.5.0 optional peer
next ^16.0.0 optional peer
react ^19.0.0 optional peer
svelte ^5.0.0 optional peer
vite ^8.3.1 optional peer
vue ^3.5.0 optional peer
eve init install drill-down

eve init install details

  • Command: eve init my-agent
  • Package manager: npm
  • Installed footprint: 113.49 MB across 10227 installed files
  • Installed packages: 97 total (91 transitive-only)
  • dependencies: 4 direct packages totaling 45.25 MB
  • devDependencies: 2 direct packages totaling 5.11 MB
  • Other transitive package files: 63.14 MB

Installed footprint is measured from an isolated temporary eve init my-agent using the current packed eve tarball.

Heavy installed dependencies

  • @typescript/typescript-linux-x64: 27.95 MB (24.6%)
  • eve: 26.97 MB (23.8%)
  • @rolldown/binding-linux-x64-gnu: 19.81 MB (17.5%)
  • zod: 9.76 MB (8.6%)
  • ai: 8.24 MB (7.3%)
Installed footprint breakdown
Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 24.6%
🔴 eve                              [#######################.] 26.97 MB 23.8%
🔴 @rolldown/binding-linux-x64-gnu  [#################.......] 19.81 MB 17.5%
🔴 zod                              [########................] 9.76 MB 8.6%
🔴 ai                               [#######.................] 8.24 MB 7.3%
🟠 undici                           [###.....................] 3.58 MB 3.1%
🔴 Other installed packages         [###############.........] 17.19 MB 15.1%
dependencies (4)
Package Range Installed size Share
@vercel/connect 2.5.2 276.3 kB 0.2%
ai ^7.0.137 8.24 MB 7.3%
eve file:eve-0.79.2.tgz 26.97 MB 23.8%
zod 4.5.4 9.76 MB 8.6%
devDependencies (2)
Package Range Installed size Share
@types/node 24.x 2.61 MB 2.3%
typescript 7.0.2 2.50 MB 2.2%
Function Drill-Down

Payload Size Graph

Unique function payload size and share of total
🔴 functions/.well-known/workflow/v1/flow.func     [########################] 10.52 MB 50.0%
🔴 functions/__server.func                         [########################] 10.52 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 10.52 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 10.52 MB
Function files 10.52 MB across 126 files
Traced dependencies 0 B
Signal 🟠 Bundled file _chunks/vercel.web.mjs is 2.48 MB (23.5%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 _chunks/vercel.web.mjs                         [############............] 2.48 MB 23.5%
🟠 _libs/undici.mjs                               [#####...................] 1.01 MB 9.6%
🟡 _chunks/sandbox3.mjs                           [####....................] 815.4 kB 7.7%
🟡 _chunks/compiled-artifacts-instrumentation.mjs [####....................] 732.7 kB 7.0%
🟡 _chunks/token-util-Bla5Z0G9.mjs                [####....................] 704.7 kB 6.7%
🔴 Other bundled files                            [########################] 4.79 MB 45.5%

🧾 Vercel Config

{
  "handler": "index.mjs",
  "launcherType": "Nodejs",
  "shouldAddHelpers": false,
  "supportsResponseStreaming": true,
  "runtime": "nodejs24.x",
  "maxDuration": "max",
  "experimentalTriggers": [
    {
      "type": "queue/v2beta",
      "topic": "__eve776561746865722d6167656e74_wkf_workflow_*",
      "consumer": "default",
      "retryAfterSeconds": 5,
      "initialDelaySeconds": 0
    }
  ],
  "environment": {
    "WORKFLOW_PRECONDITION_GUARD": "1"
  }
}

🟠 functions/__server.func • 16 public routes, 1 internal alias • 10.52 MB
Metric Value
Public routes /
/.well-known/workflow/v1/webhook/[token]
/eve/v1/callback/[token]
/eve/v1/connections/[name]/callback/[attemptId]/[token]
/eve/v1/connections/[name]/callback/[token]
/eve/v1/health
/eve/v1/info
/eve/v1/session
/eve/v1/session/[parentSessionId]/subagents/[callId]/[childSessionId]/stream
/eve/v1/session/[sessionId]
/eve/v1/session/[sessionId]/cancel
/eve/v1/session/[sessionId]/clear
/eve/v1/session/[sessionId]/compact
/eve/v1/session/[sessionId]/reset
/eve/v1/session/[sessionId]/stream
/eve/v1/session/[sessionId]/stubs
Internal aliases /__server
Runtime nodejs24.x
Handler index.mjs
Payload 10.52 MB
Function files 10.52 MB across 126 files
Traced dependencies 0 B
Signal 🟠 Bundled file _chunks/vercel.web.mjs is 2.48 MB (23.6%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 _chunks/vercel.web.mjs                         [############............] 2.48 MB 23.6%
🟠 _libs/undici.mjs                               [#####...................] 1.01 MB 9.6%
🟡 _chunks/sandbox3.mjs                           [####....................] 815.4 kB 7.7%
🟡 _chunks/compiled-artifacts-instrumentation.mjs [####....................] 732.7 kB 7.0%
🟡 _chunks/token-util-Bla5Z0G9.mjs                [####....................] 704.7 kB 6.7%
🔴 Other bundled files                            [########################] 4.79 MB 45.5%

🧾 Vercel Config

{
  "handler": "index.mjs",
  "launcherType": "Nodejs",
  "shouldAddHelpers": false,
  "supportsResponseStreaming": true,
  "runtime": "nodejs24.x"
}

Build Timing: e2e/fixtures/agent-tools-sandbox

This is an informational timing measurement inside eve build, from preflight through publication. Output-size measurement and profile writing are excluded.

Build mode: deployable Vercel build with sandbox template prewarm included.

  • Build pipeline: 3.71 s -> 3.78 s (+71.6 ms) vs api-cleanup/context-vocabulary (e00c7b5).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `api-cleanup/context-vocabulary (e00c7b5)`
Phase Baseline Current Delta
extension.check 0.4 ms 0.5 ms +0.1 ms
project.resolve 0.3 ms 0.4 ms +0.1 ms
workspace.create 0.6 ms 0.6 ms 0.0 ms
host.prepare 792.0 ms 818.2 ms +26.2 ms
vercel.service-prefix.resolve 2.3 ms 2.0 ms -0.3 ms
nitro.create 679.4 ms 687.3 ms +7.9 ms
sandbox.prewarm 283.5 ms 279.4 ms -4.1 ms
nitro.cache.prepare 0.2 ms 0.2 ms 0.0 ms
nitro.prepare 0.7 ms 0.7 ms 0.0 ms
nitro.public-assets 0.8 ms 0.8 ms 0.0 ms
nitro.prerender 0.5 ms 0.6 ms +0.1 ms
nitro.bundle 1.81 s 1.85 s +42.0 ms
nitro.cache.write 0.5 ms 0.4 ms -0.1 ms
vercel.workflow-function.materialize 56.0 ms 56.0 ms 0.0 ms
agent-summary.emit 0.6 ms 0.7 ms +0.1 ms
connect-manifest.emit 0.3 ms 0.3 ms 0.0 ms
nitro.close 0.1 ms 0.1 ms 0.0 ms
output.publish 3.4 ms 3.6 ms +0.2 ms
workspace.remove 2.6 ms 2.9 ms +0.3 ms

@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

eve benchmark

Model Dataset Harnesses Source
anthropic/claude-sonnet-5.5 (released 2026-09-28, knowledge 2026-06) swe-lean@v3 eve-code@6e6f496, opencode, pi, opencode@2cc43ca, pi@2cc43ca Run

⚠️ Incomplete: eve-code: prepare benchmark harness bundle: node exited 1: node:internal: eve build failed: Expected the connection export "default" from "connections/task-mcp.ts" to match the public eve shape. Dynamic connection resolvers support only "beforeSession" and "beforeTurn" handlers. Unsupported event: "session.started".

Results

Correctness

Harness Position Score pass^5 Δ 95% CI
opencode (Winner) 1st 32/35 (91%) 71% ±0 —

eve-code@baseline: not in this run

All harnesses and tasks
Task eve-code@6e6f496 opencode pi opencode@2cc43ca pi@2cc43ca
cancel-async-tasks — 3/5 5/5 2/5 5/5
customer-health-dossier — 5/5 3/5 5/5 0/5
customer-sku-breakdown — 4/5 1/5 5/5 2/5
git-multibranch — 5/5 5/5 5/5 5/5
growth-driver-diagnosis — 5/5 5/5 5/5 5/5
log-summary-date-ranges — 5/5 5/5 5/5 5/5
sanitize-git-repo — 5/5 3/5 3/5 3/5
Total — 32/35 27/35 30/35 25/35

Latency

Harness Position Score Δ 95% CI
pi (Winner) 1st 15s ±0 —

eve-code@6e6f496 reports no latency; eve-code@baseline: not in this run

All harnesses and tasks
Task eve-code@6e6f496 opencode pi opencode@2cc43ca pi@2cc43ca
cancel-async-tasks — 11s 12s 12s 14s
customer-health-dossier — 15s 17s 21s 15s
customer-sku-breakdown — 17s 11s 18s 11s
git-multibranch — 25s 23s 31s 16s
growth-driver-diagnosis — 18s 20s 18s 21s
log-summary-date-ranges — 13s 12s 13s 10s
sanitize-git-repo — 17s 15s 21s 17s
Median — 17s 15s 18s 15s

Token usage

Harness Position Score Δ 95% CI
pi (Winner) 1st 896K↑ 52K↓ ±0 —

eve-code@6e6f496 reports no tokens; eve-code@baseline: not in this run

All harnesses and tasks
Task eve-code@6e6f496 opencode pi opencode@2cc43ca pi@2cc43ca
cancel-async-tasks — 21K↑ 948↓ 6K↑ 1K↓ 21K↑ 946↓ 6K↑ 1K↓
customer-health-dossier — 81K↑ 1K↓ 36K↑ 2K↓ 101K↑ 1K↓ 33K↑ 2K↓
customer-sku-breakdown — 114K↑ 949↓ 30K↑ 770↓ 115K↑ 934↓ 30K↑ 773↓
git-multibranch — 56K↑ 2K↓ 25K↑ 2K↓ 80K↑ 2K↓ 10K↑ 1K↓
growth-driver-diagnosis — 112K↑ 1K↓ 50K↑ 3K↓ 110K↑ 1K↓ 50K↑ 3K↓
log-summary-date-ranges — 46K↑ 939↓ 16K↑ 1K↓ 35K↑ 961↓ 10K↑ 888↓
sanitize-git-repo — 46K↑ 1K↓ 19K↑ 1K↓ 94K↑ 2K↓ 17K↑ 1K↓
Total — 2.5M↑ 45K↓ 896K↑ 52K↓ 2.8M↑ 48K↓ 906K↑ 51K↓

Compared inputs

  • live harnesses only

Diagnostics

11 trials to inspect
  • opencode/cancel-async-tasks#1 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness opencode --task cancel-async-tasks
    
  • opencode/cancel-async-tasks#3 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness opencode --task cancel-async-tasks --attempt 3
    
  • opencode/customer-sku-breakdown#3 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness opencode --task customer-sku-breakdown --attempt 3
    
  • pi/customer-health-dossier#1 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-health-dossier
    
  • pi/customer-health-dossier#2 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-health-dossier --attempt 2
    
  • pi/customer-sku-breakdown#1 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-sku-breakdown
    
  • pi/customer-sku-breakdown#2 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-sku-breakdown --attempt 2
    
  • pi/customer-sku-breakdown#3 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-sku-breakdown --attempt 3
    
  • pi/customer-sku-breakdown#5 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task customer-sku-breakdown --attempt 5
    
  • pi/sanitize-git-repo#1 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task sanitize-git-repo
    
  • pi/sanitize-git-repo#4 (reward 0):
    eve-bench trials logs https://github.com/vercel/eve/actions/runs/39088716503 --harness pi --task sanitize-git-repo --attempt 4
    

More details on the workflow run

@vercel vercel Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Additional Suggestions:

  1. JSDoc usage examples for noReply, sleep, and askQuestion still call them as factory functions (export default noReply();) even though they are now exported as plain tool-definition values, so following the docs produces a "not callable" type error.
  1. The web_search scaffold and doc snippet still re-export a default binding from eve/tools/web_search that no longer exists, producing a broken generated agent tool file.
  1. Schedule JSDoc prose still instructs authors to pass the removed markdown key instead of content, so following the docs produces a compile-time and normalize-time error.

Fix on Vercel

@roboeve

roboeve Bot commented Oct 18, 2026

Copy link
Copy Markdown
Contributor

This session has hit the input-token limit (19.8M) per session. This is a guardrail against defective long-running sessions. If session activity looks fine, just approve to keep going.

  1. Approve - Grant a fresh token budget
  2. Stop - Stop now

Answer by mentioning me in a reply, e.g. @roboeve Approve.

@OwenKephart
OwenKephart force-pushed the api-cleanup/context-vocabulary branch from 88eb98b to e00c7b5 Compare October 18, 2026 01:53
vercel Bot and others added 4 commits October 18, 2026 02:03
Signed-off-by: owenkephart <owen.kephart@vercel.com>

Co-Authored-By: owenkephart <owen.kephart@vercel.com>
(cherry picked from commit 5d5d64a)
Signed-off-by: owenkephart <owen.kephart@vercel.com>
Signed-off-by: owenkephart <owen.kephart@vercel.com>

Co-Authored-By: owenkephart <owen.kephart@vercel.com>
Signed-off-by: owenkephart <owen.kephart@vercel.com>

Co-Authored-By: owenkephart <owen.kephart@vercel.com>
(cherry picked from commit 863da68)
Signed-off-by: owenkephart <owen.kephart@vercel.com>
Signed-off-by: owenkephart <owen.kephart@vercel.com>

Co-Authored-By: owenkephart <owen.kephart@vercel.com>
@OwenKephart

Copy link
Copy Markdown
Contributor Author

Reviewed the dependency-bot summary. The just-bash change is an optional-peer/dev dependency update to a release that ships the declaration files missing from 3.1; no runtime dependency was added to eve. The lockfile supply-chain checks and strict packed-consumer case pass. The benchmark-bot bootstrap error is tracked in the PR body as external runner coordination, not treated as a passing benchmark.

This branch was successfully deployed

2 active deployments
Preview – eve-pkg — 6e6f4963 Deployed Oct 18, 2026 by vercel[bot]
Preview – eve-docs — 6e6f4963 Deployed Oct 18, 2026 by vercel[bot]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant