feat(core): add context parameter to idGenerator for deterministic ID generation #10964
Conversation
… generation The idGenerator function now receives optional context about what type of ID is being generated (thread, message, run, step) and from which Mastra primitive (agent, workflow, memory). This enables generating IDs that can be shared with external databases. Existing idGenerator functions without parameters continue to work since the context is optional. Fixes #8131
🦋 Changeset detectedLatest commit: 55f4a48 The changes in this PR will be included in the next version bump. This PR includes changesets to release 17 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
WalkthroughContext-aware ID generation is introduced to the Mastra framework via an optional Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes
Possibly related PRs
Suggested reviewers
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing touches
🧪 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (2)
packages/core/src/workflows/workflow.test.ts (1)
996-1000: Context-agnosticidGeneratorwrapper looks correct; consider de-duplicating itUsing
idGenerator: () => randomUUID()is compatible with the new context-aware ID generator API while preserving the existing deterministic behavior driven by the mockedrandomUUID. This aligns the tests with the updated Mastra interface without changing expectations around IDs likemapping_mock-uuid-1.If you expect to tweak ID behavior again, you might want to centralize this in a small helper (e.g.,
const testIdGenerator = () => randomUUID();) and reuse it across these Mastra instantiations to avoid three separate call sites.Also applies to: 2719-2723, 14533-14537
.changeset/add-context-to-id-generator.md (1)
5-30: Align example with “deterministic ID” messagingThe text emphasizes deterministic IDs, but the example uses
Date.now(), which makes IDs time-dependent. Consider switching to an example that’s purely a function of the context (e.g., hashingcontext.threadId/context.entityId) so repeated calls with the same context yield the same ID. That will better illustrate the intended deterministic behavior without changing the API.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (12)
.changeset/add-context-to-id-generator.md(1 hunks)packages/core/src/agent/agent-legacy.ts(1 hunks)packages/core/src/agent/agent.ts(4 hunks)packages/core/src/agent/message-list/index.ts(6 hunks)packages/core/src/loop/loop.ts(1 hunks)packages/core/src/loop/network/index.ts(13 hunks)packages/core/src/mastra/idgenerator.test.ts(2 hunks)packages/core/src/mastra/index.ts(2 hunks)packages/core/src/memory/memory.ts(3 hunks)packages/core/src/types/dynamic-argument.ts(1 hunks)packages/core/src/workflows/workflow.test.ts(3 hunks)packages/core/src/workflows/workflow.ts(5 hunks)
🧰 Additional context used
📓 Path-based instructions (5)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Run
pnpm typecheckto validate TypeScript types across all packages
Files:
packages/core/src/agent/agent-legacy.tspackages/core/src/workflows/workflow.tspackages/core/src/loop/network/index.tspackages/core/src/types/dynamic-argument.tspackages/core/src/agent/agent.tspackages/core/src/mastra/idgenerator.test.tspackages/core/src/mastra/index.tspackages/core/src/agent/message-list/index.tspackages/core/src/loop/loop.tspackages/core/src/workflows/workflow.test.tspackages/core/src/memory/memory.ts
**/*.{ts,tsx,js,jsx,json,md}
📄 CodeRabbit inference engine (CLAUDE.md)
Run
pnpm prettier:formatto format code andpnpm formatto run linting with auto-fix across all packages
Files:
packages/core/src/agent/agent-legacy.tspackages/core/src/workflows/workflow.tspackages/core/src/loop/network/index.tspackages/core/src/types/dynamic-argument.tspackages/core/src/agent/agent.tspackages/core/src/mastra/idgenerator.test.tspackages/core/src/mastra/index.tspackages/core/src/agent/message-list/index.tspackages/core/src/loop/loop.tspackages/core/src/workflows/workflow.test.tspackages/core/src/memory/memory.ts
packages/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
packages/**/*.{ts,tsx}: All packages must use TypeScript with strict type checking enabled
Use telemetry decorators for observability across components
Files:
packages/core/src/agent/agent-legacy.tspackages/core/src/workflows/workflow.tspackages/core/src/loop/network/index.tspackages/core/src/types/dynamic-argument.tspackages/core/src/agent/agent.tspackages/core/src/mastra/idgenerator.test.tspackages/core/src/mastra/index.tspackages/core/src/agent/message-list/index.tspackages/core/src/loop/loop.tspackages/core/src/workflows/workflow.test.tspackages/core/src/memory/memory.ts
**/*.{test,spec}.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{test,spec}.{ts,tsx}: Use Vitest for testing framework in test files
Co-locate test files with source code using naming patterns like *.test.ts or *.spec.ts
Files:
packages/core/src/mastra/idgenerator.test.tspackages/core/src/workflows/workflow.test.ts
.changeset/*.md
⚙️ CodeRabbit configuration file
.changeset/*.md: Changeset files are really important for keeping track of changes in the project. They'll be used to generate release notes and inform users about updates.Review the changeset file according to these guidelines:
- The target audience are developers
- Write short, direct sentences that anyone can understand. Avoid commit messages, technical jargon, and acronyms. Use action-oriented verbs (Added, Fixed, Improved, Deprecated, Removed)
- Avoid generic phrases like "Update code", "Miscellaneous improvements", or "Bug fixes"
- Highlight outcomes! What does change for the end user? Do not focus on internal implementation details
- Add context like links to issues or PRs when relevant
- If the change is a breaking change or is adding a new feature, ensure that a code example is provided. This code example should show the public API usage (the before and after). Do not show code examples of internal implementation details.
- Keep the formatting easy-to-read and scannable. If necessary, use bullet points or multiple paragraphs (Use bold text as the heading for these sections, do not use markdown headings).
- For larger, more substantial changes, also answer the "Why" behind the changes
- Each changeset file contains a YAML frontmatter at the top. It will be one or more package names followed by a colon and the type of change (patch, minor, major). Do not modify this frontmatter. Check that the description inside the changeset file only applies to the packages listed in the frontmatter. Do not allow descriptions that mention changes to packages not listed in the frontmatter. In these cases, the user must create a separate changeset file for those packages.
Files:
.changeset/add-context-to-id-generator.md
🧠 Learnings (6)
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/codemods/v1/**/*.ts : Use `context.hasChanges = true` flag and `context.messages.push()` to track and report what transformations were made in the codemod
Applied to files:
packages/core/src/types/dynamic-argument.tspackages/core/src/mastra/idgenerator.test.tspackages/core/src/mastra/index.tspackages/core/src/memory/memory.ts
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/test/__fixtures__/**/*.ts : Create test fixtures by copying examples DIRECTLY from migration guides in `docs/src/content/en/guides/migrations/upgrade-to-v1/` without hallucinating or inventing changes
Applied to files:
packages/core/src/mastra/idgenerator.test.tspackages/core/src/workflows/workflow.test.ts
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/test/__fixtures__/**/*.ts : In output fixtures, ensure all NEGATIVE test cases remain EXACTLY IDENTICAL to their input fixture counterparts to verify the codemod only transforms intended patterns
Applied to files:
packages/core/src/mastra/idgenerator.test.tspackages/core/src/workflows/workflow.test.ts
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/test/**/*.test.ts : Include test cases for multiple occurrences of the transformation pattern, aliased imports, type imports, and mixed imports to verify the codemod works consistently
Applied to files:
packages/core/src/mastra/idgenerator.test.tspackages/core/src/workflows/workflow.test.ts
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/test/__fixtures__/**/*.ts : In input fixtures, include both POSITIVE test cases (patterns that should transform) and NEGATIVE test cases (unrelated code with similar names/patterns that should NOT transform)
Applied to files:
packages/core/src/mastra/idgenerator.test.ts
📚 Learning: 2025-11-24T16:42:04.244Z
Learnt from: CR
Repo: mastra-ai/mastra PR: 0
File: packages/codemod/AGENTS.md:0-0
Timestamp: 2025-11-24T16:42:04.244Z
Learning: Applies to packages/codemod/src/test/**/*.test.ts : Do NOT use `UPDATE_SNAPSHOT` to force tests to pass; instead fix the codemod implementation when tests fail
Applied to files:
packages/core/src/workflows/workflow.test.ts
🧬 Code graph analysis (4)
packages/core/src/loop/network/index.ts (3)
packages/core/src/types/dynamic-argument.ts (1)
IdGeneratorContext(15-55)packages/core/src/mastra/index.ts (1)
generateId(353-369)packages/core/src/memory/memory.ts (1)
generateId(433-435)
packages/core/src/mastra/idgenerator.test.ts (3)
packages/core/src/memory/mock.ts (1)
MockMemory(25-277)packages/core/src/mastra/index.ts (1)
Mastra(258-3095)packages/core/src/agent/message-list/index.ts (1)
MessageList(108-3369)
packages/core/src/mastra/index.ts (1)
packages/core/src/types/dynamic-argument.ts (1)
IdGeneratorContext(15-55)
packages/core/src/memory/memory.ts (1)
packages/core/src/types/dynamic-argument.ts (1)
IdGeneratorContext(15-55)
🪛 GitHub Check: Lint
packages/core/src/mastra/idgenerator.test.ts
[failure] 958-958:
'mastra' is assigned a value but never used. Allowed unused vars must match /^_/u
packages/core/src/memory/memory.ts
[failure] 20-20:
../types type import should occur before import of ../utils
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (7)
- GitHub Check: Prebuild
- GitHub Check: test
- GitHub Check: test
- GitHub Check: test (express)
- GitHub Check: test (hono)
- GitHub Check: test
- GitHub Check: Analyze (javascript-typescript)
🔇 Additional comments (22)
packages/core/src/types/dynamic-argument.ts (1)
15-55: IdGeneratorContext shape aligns well with intended usageThe unioned
idTypeplus optionalsource,entityId,threadId,resourceId,role, andstepTypecover the key contexts you’re threading through (agents, workflows, memory) while staying forwards‑compatible via optional fields. No changes needed here from a typing/API‑design perspective.packages/core/src/loop/loop.ts (1)
50-57: Context-aware runId generation is correctly wired and backward compatibleThe new
runIdToUselogic preserves the previous behavior (explicitrunIdwins; otherwise fall back to a random UUID) while preferentially using the injectedidGeneratorwith a well-populated context (idType: 'run',source: 'agent',entityId,threadId,resourceId). This matches the newIdGeneratorContextcontract and should enable deterministic run IDs without breaking existing callers.packages/core/src/agent/agent-legacy.ts (1)
706-715: Legacy runId generation now correctly leverages Mastra.generateId with contextThis change cleanly layers the new context‑aware ID generation into the legacy path:
- Precedence is sensible:
args.runId(if provided) →mastra.generateId({ idType: 'run', source: 'agent', entityId, threadId, resourceId })→randomUUID().- The context fields you pass match
IdGeneratorContextand give custom generators enough information to produce deterministic, externally shareable run IDs even for legacy calls.No further changes needed here.
packages/core/src/memory/memory.ts (2)
378-386: Context-aware thread ID generation looks correctUsing
this.generateId({ idType: 'thread', source: 'memory', resourceId })while still honoring an explicitthreadIdachieves deterministic, externally-shareable thread IDs without breaking existing callers.
428-435: generateId(context?) preserves compatibility while adding contextThe new
generateId(context?: IdGeneratorContext)cleanly forwards context to Mastra’s generator and falls back tocrypto.randomUUID(), so existing no-arg callers continue to work while context-aware generators can opt in.packages/core/src/workflows/workflow.ts (1)
547-558: Contextual step and run ID generation is consistent and backward compatiblesleep/sleepUntil, mapping steps, and run creation now all use
this.#mastra?.generateId({ idType: 'step' | 'run', source: 'workflow', entityId: this.id, ... })with arandomUUID()fallback and explicit-ID override. This matches the new IdGeneratorContext contract and should enable deterministic IDs without regressing existing workflows.Also applies to: 577-587, 652-655, 694-697, 1024-1032
packages/core/src/agent/agent.ts (3)
1698-1727: Sub-agent thread/resource ID generation correctly uses contextUsing
context?.mastra?.generateId({ idType: 'thread', source: 'agent', entityId: agentName, resourceId })and a separateidType: 'generic'call forsubAgentResourceId, with fallbacks toinputDataor slugified/random IDs, cleanly integrates sub-agents into the new context-aware ID scheme while preserving existing behavior when no generator is configured.
2502-2511: Agent runId now participates in context-aware ID generationDeriving
runIdfromoptions.runId || this.#mastra?.generateId({ idType: 'run', source: 'agent', entityId: this.id, threadId: threadFromArgs?.id, resourceId }) || randomUUID()aligns agent runs with the global ID strategy and still respects a caller-supplied runId and non-Mastra usage.
2797-2827: Network loop IDs and generator wiring match the new APIThe network method now:
- Derives
threadId/resourceIdfromoptions.memory.- Builds
runIdviathis.#mastra?.generateId({ idType: 'run', source: 'agent', entityId: this.id, threadId, resourceId }) || randomUUID().- Passes
generateId: context => this.#mastra?.generateId(context) || randomUUID()plusthreadIdandresourceIdintonetworkLoop.This is consistent with
NetworkIdGeneratorand ensures networked interactions benefit from contextual, deterministic IDs where configured.packages/core/src/mastra/index.ts (1)
333-369: Context-aware ID generation is well implemented.The optional
contextparameter maintains backward compatibility while enabling deterministic ID generation. ExistingidGeneratorimplementations without parameters will continue to work since the context argument is simply ignored when not used.packages/core/src/mastra/idgenerator.test.ts (2)
728-728: Good alignment with context-aware ID generation.Using
agentMemory.generateId()ensures the test validates that the custom ID generator is properly wired through the memory instance.
801-873: Comprehensive test suite for context-aware ID generation.This test suite provides excellent coverage of the feature request #8131, validating context propagation for various ID types (thread, message, run) and sources (agent, workflow, memory). The tests demonstrate the deterministic ID generation use case well.
The
as anycasts forcontextAwareIdGeneratorare acceptable given the new signature(context?: IdGeneratorContext) => stringis compatible at runtime.packages/core/src/loop/network/index.ts (6)
18-21: Well-defined type alias for context-aware ID generation.The
NetworkIdGeneratortype properly encapsulates the new signature, maintaining consistency withMastra.generateId.
162-168: Proper context for user message ID generation.The context correctly identifies this as a message from an agent with the user role, including thread and resource context for deterministic generation.
297-301: Correct context for routing agent step IDs.The step ID generation properly identifies the context as an agent routing step, enabling deterministic ID generation based on the step type.
617-622: Agent execution step IDs include entity context.Good inclusion of
entityIdto identify which agent is executing, enabling deterministic IDs that can be traced to specific agents.
795-800: Workflow execution correctly identifies source.The
source: 'workflow'andentityId: wf.idcorrectly distinguish workflow-generated IDs from agent-generated ones, supporting the deterministic ID use case.
982-987: Tool execution context properly structured.The tool call ID correctly uses
source: 'agent'since tools are invoked from agents, withentityIdidentifying the specific tool for traceability.packages/core/src/agent/message-list/index.ts (4)
17-17: LGTM - Import and property type changes support the new context-aware ID generation.The
IdGeneratorContextimport and the updatedgenerateMessageIdproperty type correctly establish the foundation for context-aware ID generation while maintaining backward compatibility through the optional parameter.Also applies to: 129-129
150-154: Well-designed backward-compatible constructor signature.The union type
((context?: IdGeneratorContext) => string) | AIV4Type.IdGeneratorcorrectly preserves backward compatibility. ExistingidGeneratorimplementations that take no parameters will continue to work, as they can simply ignore the context object passed to them.
1601-1612: Core implementation correctly provides context for deterministic ID generation.The
newMessageIdmethod properly constructs the context object with relevant fields (idType,source,threadId,resourceId,role) that enable users to generate deterministic IDs. The hardcodedsource: 'memory'is appropriate sinceMessageListspecifically handles message storage and memory operations.
1636-1636: Role context is consistently propagated across all ID generation call sites.The changes correctly pass the message role to
newMessageIdat all call sites:
hydrateMastraDBMessageFields: usesmessage.roledirectlyaiV4UIMessageToMastraDBMessage: extracts viagetRole()for proper normalizationaiV4CoreMessageToMastraDBMessage: usescoreMessage.roledirectlyThis enables users to generate role-aware deterministic IDs as intended by the PR objectives.
Also applies to: 1694-1697, 1705-1705
| const mastra = new Mastra({ | ||
| idGenerator: contextAwareIdGenerator as any, | ||
| logger: false, | ||
| workflows: { 'context-test-workflow': workflow }, | ||
| }); |
There was a problem hiding this comment.
Rename unused variable to satisfy lint rules.
The mastra variable is assigned but never used in this test. Per your linting rules, unused variables must be prefixed with _.
- const mastra = new Mastra({
+ const _mastra = new Mastra({
idGenerator: contextAwareIdGenerator as any,
logger: false,
workflows: { 'context-test-workflow': workflow },
});📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const mastra = new Mastra({ | |
| idGenerator: contextAwareIdGenerator as any, | |
| logger: false, | |
| workflows: { 'context-test-workflow': workflow }, | |
| }); | |
| const _mastra = new Mastra({ | |
| idGenerator: contextAwareIdGenerator as any, | |
| logger: false, | |
| workflows: { 'context-test-workflow': workflow }, | |
| }); |
🧰 Tools
🪛 GitHub Check: Lint
[failure] 958-958:
'mastra' is assigned a value but never used. Allowed unused vars must match /^_/u
🤖 Prompt for AI Agents
In packages/core/src/mastra/idgenerator.test.ts around lines 958 to 962, the
local variable "mastra" is assigned but never used; rename it to "_mastra" to
satisfy the lint rule for unused variables (prefix unused variables with an
underscore). Update the variable name in this assignment only, leaving other
code unchanged.
| import { deepMerge } from '../utils'; | ||
| import type { IdGeneratorContext } from '../types'; |
There was a problem hiding this comment.
Fix import ordering to satisfy lint rule
Static analysis expects the ../types type-only import to appear before the value import from ../utils. Swap these two lines to fix the lint failure:
-import { deepMerge } from '../utils';
-import type { IdGeneratorContext } from '../types';
+import type { IdGeneratorContext } from '../types';
+import { deepMerge } from '../utils';📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| import { deepMerge } from '../utils'; | |
| import type { IdGeneratorContext } from '../types'; | |
| import type { IdGeneratorContext } from '../types'; | |
| import { deepMerge } from '../utils'; |
🧰 Tools
🪛 GitHub Check: Lint
[failure] 20-20:
../types type import should occur before import of ../utils
🤖 Prompt for AI Agents
In packages/core/src/memory/memory.ts around lines 19 to 20, the import order is
causing a lint failure because the type-only import from '../types' must appear
before the value import from '../utils'; swap the two import lines so "import
type { IdGeneratorContext } from '../types';" comes before "import { deepMerge }
from '../utils';" to satisfy the rule.
| /** | ||
| * Custom ID generator function for creating unique identifiers. | ||
| * Receives optional context about what type of ID is being generated | ||
| * and where it's being requested from. | ||
| * | ||
| * @example | ||
| * ```typescript | ||
| * const mastra = new Mastra({ | ||
| * idGenerator: (context) => { | ||
| * if (context?.idType === 'message' && context?.threadId) { | ||
| * return `msg-${context.threadId}-${Date.now()}`; | ||
| * } | ||
| * if (context?.idType === 'run' && context?.entityId) { | ||
| * return `run-${context.entityId}-${Date.now()}`; | ||
| * } | ||
| * return crypto.randomUUID(); | ||
| * } | ||
| * }); | ||
| * ``` | ||
| */ | ||
| export type MastraIdGenerator = (context?: IdGeneratorContext) => NonEmpty<string>; |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
cat -n packages/core/src/types/dynamic-argument.tsRepository: mastra-ai/mastra
Length of output: 2707
🏁 Script executed:
rg -A 10 -B 5 "IdGeneratorContext" packages/core/src/types/Repository: mastra-ai/mastra
Length of output: 1720
🏁 Script executed:
rg "deterministic" packages/core/src/types/dynamic-argument.tsRepository: mastra-ai/mastra
Length of output: 131
🏁 Script executed:
cd packages/core && ls -la | grep -E "(package\.json|pnpm-lock)" && head -20 package.jsonRepository: mastra-ai/mastra
Length of output: 538
🏁 Script executed:
rg "deterministic|context-aware" packages/core/src/types/ -A 2 -B 2Repository: mastra-ai/mastra
Length of output: 458
Clarify documentation to match implementation: deterministic IDs require pure context-based generation
The JSDoc comment at line 12 promises "deterministic IDs based on the context," but the example contradicts this by using Date.now() and crypto.randomUUID(). Deterministic generation requires the same context to always produce the same ID. Revise either:
- Rephrase to "context-aware IDs" to accurately reflect the example, or
- Show a deterministic example:
msg-${context.threadId}-${context.entityId}without time or randomness components.
After changes, run pnpm typecheck and pnpm prettier:format to validate types and formatting per the repository guidelines.
🤖 Prompt for AI Agents
In packages/core/src/types/dynamic-argument.ts around lines 57 to 77, the JSDoc
claims "deterministic IDs based on the context" but the example uses Date.now()
and crypto.randomUUID(), which is not deterministic; update the doc so the
wording matches the implementation by either (A) changing "deterministic IDs" to
"context-aware IDs" and keep the current (non-deterministic) example, or (B)
provide a fully deterministic example (e.g., compose ID solely from context
fields like `msg-${context.threadId}-${context.entityId}`) and remove
time/randomness; after editing, run pnpm typecheck and pnpm prettier:format to
validate types and formatting.
The
idGeneratorfunction now receives optional context about what type of ID is being generated and from which Mastra primitive. This lets you generate deterministic IDs that can be shared with external databases.Context includes
idType(thread, message, run, step, generic),source(agent, workflow, memory),entityId,threadId,resourceId,role, andstepType.Existing
idGeneratorfunctions without parameters continue to work since context is optional.Fixes #8131
Summary by CodeRabbit
Release Notes
New Features
Chores
✏️ Tip: You can customize this high-level summary in your review settings.