feat(ai): rework tool-call budgets as middleware hooks#972
Open
tombeckenham wants to merge 3 commits into
Open
feat(ai): rework tool-call budgets as middleware hooks#972tombeckenham wants to merge 3 commits into
tombeckenham wants to merge 3 commits into
Conversation
Contributor
🚀 Changeset Version Preview3 package(s) bumped directly, 44 bumped as dependents. 🟥 Major bumps
🟨 Minor bumps
🟩 Patch bumps
|
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughThe chat engine removes built-in tool-call budgets and adds middleware-driven continuation control. Tool-call accounting remains available through ChangesTool-call budgeting middleware
Estimated code review effort: 3 (Moderate) | ~25 minutes Sequence Diagram(s)sequenceDiagram
participant TextEngine
participant AgentLoopStrategy
participant MiddlewareRunner
participant ToolExecution
TextEngine->>ToolExecution: record deduplicated tool calls
TextEngine->>AgentLoopStrategy: evaluate loop state
TextEngine->>MiddlewareRunner: runOnShouldContinue(ctx, state)
MiddlewareRunner-->>TextEngine: continue or stop
TextEngine->>ToolExecution: execute executable tool calls
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
View your CI Pipeline Execution ↗ for commit 18f47a4
☁️ Nx Cloud last updated this comment at |
@tanstack/ai
@tanstack/ai-acp
@tanstack/ai-angular
@tanstack/ai-anthropic
@tanstack/ai-bedrock
@tanstack/ai-claude-code
@tanstack/ai-client
@tanstack/ai-code-mode
@tanstack/ai-code-mode-skills
@tanstack/ai-codex
@tanstack/ai-devtools-core
@tanstack/ai-durable-stream
@tanstack/ai-elevenlabs
@tanstack/ai-event-client
@tanstack/ai-fal
@tanstack/ai-gemini
@tanstack/ai-grok
@tanstack/ai-grok-build
@tanstack/ai-groq
@tanstack/ai-isolate-cloudflare
@tanstack/ai-isolate-node
@tanstack/ai-isolate-quickjs
@tanstack/ai-mcp
@tanstack/ai-mistral
@tanstack/ai-ollama
@tanstack/ai-openai
@tanstack/ai-opencode
@tanstack/ai-openrouter
@tanstack/ai-preact
@tanstack/ai-react
@tanstack/ai-react-ui
@tanstack/ai-sandbox
@tanstack/ai-sandbox-cloudflare
@tanstack/ai-sandbox-daytona
@tanstack/ai-sandbox-docker
@tanstack/ai-sandbox-local-process
@tanstack/ai-sandbox-sprites
@tanstack/ai-sandbox-vercel
@tanstack/ai-solid
@tanstack/ai-solid-ui
@tanstack/ai-svelte
@tanstack/ai-utils
@tanstack/ai-vue
@tanstack/ai-vue-ui
@tanstack/openai-base
@tanstack/preact-ai-devtools
@tanstack/react-ai-devtools
@tanstack/solid-ai-devtools
commit: |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
testing/e2e/src/routes/api.max-tool-calls-wire.ts (1)
8-11: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueMove type-only import to the existing
import typeblock.To resolve the static analysis linting warning and maintain a consistent top-level type import style, consider moving
ChatMiddlewareto the existing type-only import statement.♻️ Proposed refactor
- type ChatMiddleware, } from '`@tanstack/ai`' import { z } from 'zod' -import type { AnyTextAdapter, StreamChunk } from '`@tanstack/ai`' +import type { AnyTextAdapter, ChatMiddleware, StreamChunk } from '`@tanstack/ai`'🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@testing/e2e/src/routes/api.max-tool-calls-wire.ts` around lines 8 - 11, Move ChatMiddleware from the regular `@tanstack/ai` import into the existing import type declaration alongside AnyTextAdapter and StreamChunk, leaving the runtime zod import unchanged.Source: Linters/SAST tools
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/ai/src/activities/chat/index.ts`:
- Around line 1964-1994: Update shouldContinue so loopStrategy(state) and
middlewareRunner.runOnShouldContinue(this.middlewareCtx, state) are both
evaluated on every non-executeToolCalls check, including when the strategy
returns false. Combine their boolean results afterward with the existing
toolPhase === 'continue' condition, preserving the executeToolCalls early
return.
---
Nitpick comments:
In `@testing/e2e/src/routes/api.max-tool-calls-wire.ts`:
- Around line 8-11: Move ChatMiddleware from the regular `@tanstack/ai` import
into the existing import type declaration alongside AnyTextAdapter and
StreamChunk, leaving the runtime zod import unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 4df1b917-28b5-4bea-9899-f4105b50345f
📒 Files selected for processing (24)
.changeset/max-tool-calls-middleware.mddocs/advanced/built-in-middleware.mddocs/advanced/middleware.mddocs/api/ai.mddocs/chat/agentic-cycle.mddocs/config.jsondocs/reference/functions/combineStrategies.mddocs/reference/functions/maxIterations.mddocs/reference/functions/maxToolCalls.mddocs/reference/index.mddocs/reference/interfaces/AgentLoopState.mddocs/reference/interfaces/TextOptions.mdpackages/ai/skills/ai-core/middleware/SKILL.mdpackages/ai/skills/ai-core/tool-calling/SKILL.mdpackages/ai/src/activities/chat/agent-loop-strategies.tspackages/ai/src/activities/chat/index.tspackages/ai/src/activities/chat/middleware/compose.tspackages/ai/src/activities/chat/middleware/types.tspackages/ai/src/index.tspackages/ai/src/types.tspackages/ai/tests/agent-loop-strategies.test.tspackages/ai/tests/chat.test.tstesting/e2e/src/routes/api.max-tool-calls-wire.tstesting/e2e/tests/max-tool-calls.spec.ts
💤 Files with no reviewable changes (6)
- docs/reference/functions/maxToolCalls.md
- docs/reference/interfaces/TextOptions.md
- docs/reference/index.md
- docs/reference/functions/combineStrategies.md
- packages/ai/tests/agent-loop-strategies.test.ts
- packages/ai/src/index.ts
Replace the unreleased maxToolCalls strategy and chat({ maxToolCallsPerTurn })
with an onShouldContinue middleware hook so apps can stop further agent turns
without aborting. Keep toolCallCount / lastTurnToolCallCount on AgentLoopState
for strategies and middleware. Document an app-owned tool-budget recipe
instead of shipping a built-in maxToolCallsMiddleware.
Evaluate agentLoopStrategy and middleware onShouldContinue together so middleware still observes the final state when the strategy is what stops the loop. Also use a type-only import for ChatMiddleware in the E2E wire route.
tombeckenham
force-pushed
the
feat/max-tool-calls-middleware
branch
from
July 21, 2026 10:15
abf5532 to
18f47a4
Compare
jherr
approved these changes
Jul 21, 2026
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
2 participants
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
maxToolCalls()strategy andchat({ maxToolCallsPerTurn })onShouldContinuemiddleware hook so policies can stop further agent-loop turns without hard-abortingAgentLoopState.toolCallCount/lastTurnToolCallCountfor custom strategies and middlewareonBeforeToolCallskip +onShouldContinue) in agentic-cycle docs — not a built-in library exportThis addresses maintainer feedback that tool-call budgeting belongs in middleware extensibility rather than first-class loop strategy + chat options (unreleased, so safe to rework).
Test plan
testing/e2e/tests/max-tool-calls.spec.ts(updated to inline budget middleware)docs/chat/agentic-cycle.md§ Tool-call budgetsSummary by CodeRabbit
onShouldContinuemiddleware hook to decide whether the agent starts another model turn (supports async, stops on explicitfalse).maxToolCallsstrategy and themaxToolCallsPerTurnchat option.