refactor(eve): unify durable HITL request lifecycle - #2822
Draft
ruiconti wants to merge 12 commits into
Draft
Conversation
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Bundle + Package Summary:
|
| Area | Metric | Baseline | Current | Delta |
|---|---|---|---|---|
| Package | Packed tarball | 8.54 MB | 8.54 MB | -30 B ✅ |
| Package | Unpacked publish size | 32.19 MB | 32.19 MB | +412 B |
| Package | Installed footprint | 77.21 MB | 77.21 MB | +412 B |
| Package | Published files | 3672 | 3672 | 0 |
| Package | Installed files | 7507 | 7507 | 0 |
| Package | Installed package instances | 35 | 35 | 0 |
| Package | Distinct installed package names | 34 | 34 | 0 |
| Package | Installed dependency edges | 53 | 53 | 0 |
| Package | Installed optional peer edges | 47 | 47 | 0 |
| Runtime | Unique function payloads | 2 | 2 | 0 |
| Runtime | Total function bytes | 19.87 MB | 19.87 MB | +254 B |
| Runtime | Public routes | 17 | 17 | 0 |
Changed function payloads vs rui/hitl-authorization-interpreter (de7c03d) (2)
| Function | Status | Baseline | Current | Delta | Route changes |
|---|---|---|---|---|---|
functions/__server.func |
changed | 9.93 MB | 9.93 MB | +127 B |
none |
functions/.well-known/workflow/v1/flow.func |
changed | 9.93 MB | 9.93 MB | +127 B |
none |
eve init install
| Metric | Baseline | Current | Delta |
|---|---|---|---|
| Installed footprint | 115.65 MB | 115.65 MB | +412 B |
| Installed packages | 120 | 120 | 0 |
| dependencies | 4 | 4 | 0 |
| devDependencies | 2 | 2 | 0 |
| Dependency package bytes | 48.16 MB | 48.16 MB | +412 B |
| devDependency package bytes | 5.04 MB | 5.04 MB | 0 B ➖ |
Build Metadata
- Preset:
vercel - Nitro:
nitro@3.0.260610-beta - Output directory:
apps/fixtures/weather-agent/.vercel/output - Build metadata timestamp: 2026-09-01T04:43:24.409Z
- 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@0.47.6 - Package directory:
packages/eve - Tarball: 8.54 MB (
eve-0.47.6.tgz) - Unpacked payload: 32.19 MB across 3672 published files
- Installed footprint: 77.21 MB across 7507 installed files
- Installed root package: 30.73 MB
- Installed dependencies: 46.48 MB
- Installed package instances: 35
- Distinct installed package names: 34
- Installed dependency edges: 53
- Installed optional peer edges: 47
- Runtime dependencies: 2
- Peer dependencies: 5 (4 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: 30.73 MB (39.8%)@rolldown/binding-linux-x64-gnu: 19.33 MB (25.0%)ai: 6.89 MB (8.9%)zod: 6.41 MB (8.3%)undici: 3.50 MB (4.5%)
Publish payload breakdown
Published file size
🔴 dist/src/compiled/shadcn-registry/index.js [#############...........] 9.76 MB 30.3%
🟠 dist/src/compiled/@photon-ai/chat-adapter-ime... [###.....................] 2.27 MB 7.1%
🟠 dist/src/compiled/@ai-sdk/code-mode/index.js [#.......................] 1.03 MB 3.2%
🟡 dist/src/compiled/@vercel/blob/index.js [#.......................] 901.8 kB 2.8%
🟡 dist/src/compiled/_chunks/workflow/undici-Dzn... [#.......................] 512.7 kB 1.6%
🔴 Other published files [########################] 17.72 MB 55.0%
Installed footprint breakdown
Installed package size
🔴 eve [########################] 30.73 MB 39.8%
🔴 @rolldown/binding-linux-x64-gnu [###############.........] 19.33 MB 25.0%
🔴 ai [#####...................] 6.89 MB 8.9%
🔴 zod [#####...................] 6.41 MB 8.3%
🟠 undici [###.....................] 3.50 MB 4.5%
🟠 nitro [##......................] 2.41 MB 3.1%
🔴 Other installed packages [######..................] 7.94 MB 10.3%
Runtime dependencies (2)
| Package | Range | Notes |
|---|---|---|
nitro |
3.0.260610-beta |
|
undici |
8.9.0 |
Peer dependencies (5)
| Package | Range | Notes |
|---|---|---|
@opentelemetry/api |
^1.0.0 |
optional peer |
ai |
catalog: |
|
braintrust |
^3.0.0 |
optional peer |
just-bash |
^3.1.0 |
optional peer |
microsandbox |
^0.5.0 |
optional peer |
eve init install drill-down
eve init install details
- Command:
eve init my-agent - Package manager:
npm - Installed footprint: 115.65 MB across 9403 installed files
- Installed packages: 120 total (114 transitive-only)
- dependencies: 4 direct packages totaling 48.16 MB
- devDependencies: 2 direct packages totaling 5.04 MB
- Other transitive package files: 62.45 MB
Installed footprint is measured from an isolated temporary eve init my-agent using the current packed eve tarball.
Heavy installed dependencies
eve: 30.73 MB (26.6%)@typescript/typescript-linux-x64: 27.95 MB (24.2%)@rolldown/binding-linux-x64-gnu: 19.33 MB (16.7%)zod: 10.37 MB (9.0%)ai: 6.89 MB (6.0%)
Installed footprint breakdown
Installed package size
🔴 eve [########################] 30.73 MB 26.6%
🔴 @typescript/typescript-linux-x64 [######################..] 27.95 MB 24.2%
🔴 @rolldown/binding-linux-x64-gnu [###############.........] 19.33 MB 16.7%
🔴 zod [########................] 10.37 MB 9.0%
🔴 ai [#####...................] 6.89 MB 6.0%
🟠 undici [###.....................] 3.50 MB 3.0%
🔴 Other installed packages [#############...........] 16.88 MB 14.6%
dependencies (4)
| Package | Range | Installed size | Share |
|---|---|---|---|
@vercel/connect |
1.0.0 |
167.9 kB | 0.1% |
ai |
^7.0.82 |
6.89 MB | 6.0% |
eve |
file:eve-0.47.6.tgz |
30.73 MB | 26.6% |
zod |
4.5.4 |
10.37 MB | 9.0% |
devDependencies (2)
| Package | Range | Installed size | Share |
|---|---|---|---|
@types/node |
24.x |
2.54 MB | 2.2% |
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 [########################] 9.93 MB 50.0%
🔴 functions/__server.func [########################] 9.93 MB 50.0%
Top Function Payloads
🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 9.93 MB
| Metric | Value |
|---|---|
| Public routes | /.well-known/workflow/v1/flow |
| Runtime | nodejs24.x |
| Handler | index.mjs |
| Payload | 9.93 MB |
| Function files | 9.93 MB across 110 files |
| Traced dependencies | 0 B |
| Signal | 🟠 Bundled file index.mjs is 1.97 MB (19.8%) |
🟠 🔎 Dependency Analysis
📦 Bundled files:
Bundled file size
🟠 index.mjs [##########..............] 1.97 MB 19.8%
🟡 _libs/undici.mjs [#####...................] 980.5 kB 9.9%
🟡 _chunks/decode_jwt-Col8JOnf.mjs [###.....................] 702.6 kB 7.1%
🟡 _chunks/frames-Dl2Hcma4.mjs [###.....................] 678.7 kB 6.8%
🟡 _chunks/chatgpt-model.mjs [###.....................] 667.7 kB 6.7%
🔴 Other bundled files [########################] 4.93 MB 49.7%
🧾 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 • 9.93 MB
| Metric | Value |
|---|---|
| Public routes | //eve/v1/activity/[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/task-input/[token] |
| Internal aliases | /__server |
| Runtime | nodejs24.x |
| Handler | index.mjs |
| Payload | 9.93 MB |
| Function files | 9.93 MB across 110 files |
| Traced dependencies | 0 B |
| Signal | 🟠 Bundled file index.mjs is 1.97 MB (19.8%) |
🟠 🔎 Dependency Analysis
📦 Bundled files:
Bundled file size
🟠 index.mjs [##########..............] 1.97 MB 19.8%
🟡 _libs/undici.mjs [#####...................] 980.5 kB 9.9%
🟡 _chunks/decode_jwt-Col8JOnf.mjs [###.....................] 702.6 kB 7.1%
🟡 _chunks/frames-Dl2Hcma4.mjs [###.....................] 678.7 kB 6.8%
🟡 _chunks/chatgpt-model.mjs [###.....................] 667.7 kB 6.7%
🔴 Other bundled files [########################] 4.93 MB 49.7%
🧾 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: 2.52 s -> 2.37 s (-157.9 ms) vs
rui/hitl-authorization-interpreter (de7c03d). - Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `rui/hitl-authorization-interpreter (de7c03d)`
| Phase | Baseline | Current | Delta |
|---|---|---|---|
extension.check |
1.1 ms | 11.8 ms | +10.7 ms |
project.resolve |
0.3 ms | 0.3 ms | 0.0 ms |
workspace.create |
0.7 ms | 0.7 ms | 0.0 ms |
host.prepare |
573.2 ms | 389.8 ms | -183.4 ms |
vercel.service-prefix.resolve |
1.9 ms | 2.4 ms | +0.5 ms |
nitro.create |
258.1 ms | 262.5 ms | +4.4 ms |
sandbox.prewarm |
225.9 ms | 256.0 ms | +30.1 ms |
nitro.cache.prepare |
0.2 ms | 0.2 ms | 0.0 ms |
nitro.prepare |
0.6 ms | 0.7 ms | +0.1 ms |
nitro.public-assets |
0.7 ms | 0.7 ms | 0.0 ms |
nitro.prerender |
0.5 ms | 0.5 ms | 0.0 ms |
nitro.bundle |
1.41 s | 1.39 s | -20.0 ms |
nitro.cache.write |
0.3 ms | 0.3 ms | 0.0 ms |
vercel.workflow-function.materialize |
43.1 ms | 42.6 ms | -0.5 ms |
agent-summary.emit |
0.7 ms | 0.7 ms | 0.0 ms |
nitro.close |
0.2 ms | 0.1 ms | -0.1 ms |
output.publish |
3.0 ms | 3.3 ms | +0.3 ms |
workspace.remove |
1.8 ms | 1.8 ms | 0.0 ms |
Signed-off-by: Rui Conti <ruiconti@gmail.com>
ruiconti
changed the base branch from
rui/hitl-authorization-interpreter
to
main
September 1, 2026 04:41
This was referenced Sep 1, 2026
ruiconti
marked this pull request as draft
September 1, 2026 13:31
Contributor
Author
|
Marking this draft again: the current branch centralizes storage and routing, but it does not yet establish the interpreter as the sole lifecycle authority. I am continuing on this PR with reducer verdicts, durable ready/delivered Group completion, ResponseAttempt identity, internal Authorization Requests, and forced closure before requesting review. |
Signed-off-by: Rui Conti <ruiconti@gmail.com>
![vercel[bot]](https://cdn.statically.io/img/avatars.githubusercontent.com/in/8329?s=60&v=4){kind=small}
Comment on lines
+40
to
+50
| readonly limitContinuation: { readonly granted: boolean }; | ||
| } { | ||
| const messages = [...input.messages]; | ||
| appendResolvedBatchTranscript(messages, input.batch, []); | ||
| const limitContinuation = resolveSessionLimitContinuation({ | ||
| requests: input.pendingBatch.requests, | ||
| requests: input.batch.requests, | ||
| responses: input.responses, | ||
| }); | ||
| if (limitContinuation === undefined) { | ||
| throw new TypeError("Answered session-limit batches must resolve a continuation verdict."); | ||
| } |
Contributor
There was a problem hiding this comment.
Suggested change
| readonly limitContinuation: { readonly granted: boolean }; | |
| } { | |
| const messages = [...input.messages]; | |
| appendResolvedBatchTranscript(messages, input.batch, []); | |
| const limitContinuation = resolveSessionLimitContinuation({ | |
| requests: input.pendingBatch.requests, | |
| requests: input.batch.requests, | |
| responses: input.responses, | |
| }); | |
| if (limitContinuation === undefined) { | |
| throw new TypeError("Answered session-limit batches must resolve a continuation verdict."); | |
| } | |
| readonly limitContinuation?: { readonly granted: boolean }; | |
| } { | |
| const messages = [...input.messages]; | |
| appendResolvedBatchTranscript(messages, input.batch, []); | |
| // An ambiguous answer (invalid `optionId`, text-only, or missing option) | |
| // resolves the batch without a continuation grant. The violation still | |
| // holds, so the harness re-prompts on the next step rather than crashing. | |
| const limitContinuation = resolveSessionLimitContinuation({ | |
| requests: input.batch.requests, | |
| responses: input.responses, | |
| }); |
reduceSessionLimitRequestVerdict throws a TypeError (crashing the harness step) when a client answers a session-limit continuation prompt with an ambiguous response (invalid optionId, text-only, or missing optionId), a regression from the HITL interpreter refactor.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Related to #1224. Approval, Question, Limit, and internal Authorization currently persist and interpret the same park/resume lifecycle through separate state machines. This replaces them with one versioned Request ledger and interpreter, then represents the framework approval gate as a Group owner rather than another durable waiting state.
Requests and Groups now retain terminal identity for stale-versus-invalid classification, migrate legacy pending state on first mutation, and use conditional ledger writes. Approval response attempts keep their existing two-phase policy and Authorization flow. AI SDK approval parts, public approval policies, request IDs, events, and transcript behavior are preserved.
Review the ledger migration and conditional-write boundary first, then the approval-attempt migration. Workflow-backed tool bodies and public
ctx.request/ctx.authremain out of scope.Validation
The focused ledger, Authorization, approval-response, lifecycle, input-request, and full tool-loop unit suites passed: 291 tests for the approval-interpreter migration and 268 tests for framework-gate ownership. Package typechecking and formatting passed. The two approval integration files could not start in the isolated worktree because its generated workflow-bundle prerequisite was absent; CI runs them after the normal build.
Checklist
CONTRIBUTING.mdevepackagegit commit --signoff)Diff size
Docs — 1 file ·
+5 / -0One release-note changeset covers the complete runtime migration.
Implementation — 9 files ·
+748 / -478The new ledger and interpreter account for most additions. Existing pending-input and stale-response routers shrink to adapters, while approval coordination moves under the interpreter namespace.
Tests — 5 files ·
+390 / -12Adds ledger migration and cross-kind conformance coverage, moves approval tests with their implementation, and updates one tool-loop assertion to use the supported pending-input projection.