fix(AI Agent Node): Fix tools agent when using memory and Anthropic models #10513
Conversation
This file contains 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
netroy
reviewed
Aug 22, 2024
OlegIvaniv
changed the title
n8n-assistant
bot
added
core
burivuhster
reviewed
Aug 23, 2024
packages/@n8n/nodes-langchain/nodes/agents/Agent/agents/ToolsAgent/execute.ts
Show resolved
Hide resolved
burivuhster
reviewed
Aug 23, 2024
packages/@n8n/nodes-langchain/nodes/agents/Agent/agents/ToolsAgent/execute.ts
Outdated
Show resolved
Hide resolved
|
@burivuhster I've added a more detailed comment explaining what the |
burivuhster
reviewed
Sep 4, 2024
packages/@n8n/nodes-langchain/nodes/agents/Agent/agents/ToolsAgent/execute.ts
Outdated
Show resolved
Hide resolved
burivuhster
reviewed
Sep 4, 2024
packages/@n8n/nodes-langchain/nodes/agents/Agent/agents/ToolsAgent/execute.ts
Outdated
Show resolved
Hide resolved
burivuhster
reviewed
Sep 4, 2024
OlegIvaniv
force-pushed
the
ai-259-issue-with-anthropic-model-tools-agent-memory
branch
from
9096969 to
cf0c33f
Compare
n8n
|
||||||||||||||||||||||||||||
| Project |
n8n
|
| Branch Review |
ai-259-issue-with-anthropic-model-tools-agent-memory
|
| Run status |
|
| Run duration | 04m 45s |
| Commit |
|
| Committer | Oleg Ivaniv |
| View all properties for this run ↗︎ | |
| Test results | |
|---|---|
Failures
|
0
|
Flaky
|
1
|
Pending
|
0
|
Skipped
|
0
|
Passing
|
422
|
| View all changes introduced in this branch ↗︎ | |
|
✅ All Cypress E2E specs passed |
OlegIvaniv
deleted the
ai-259-issue-with-anthropic-model-tools-agent-memory
branch
MiloradFilipovic
added a commit
that referenced
this pull request
Sep 5, 2024
* master: refactor(RabbitMQ Trigger Node): Improve type-safety, add tests, and fix issues with manual triggers (#10663) feat(editor): Add support for nodes with multiple main inputs in new canvas (no-changelog) (#10659) fix(editor): Set minimum zoom to 0 to allow fitting very large workflows in new canvas (no-changelog) (#10666) feat(editor): Change selection to be default canvas behaviour (no-changelog) (#10668) feat: More hints to nodes (#10565) fix(editor): Fix opening executions tab from a new, unsaved workflow (#10652) fix(AI Agent Node): Fix tools agent when using memory and Anthropic models (#10513) feat(editor): Make highlighted data pane floating (#10638) fix(editor): Fix workflow loading after switching to executions view in new canvas (no-changelog) (#10655) refactor(benchmark): Separate cloud env provisioning from running benchmarks (#10657) feat(core): Implement wrapping of regular nodes as AI Tools (#10641) refactor(editor): Remove Trial logic in personalization modal and port to script setup (#10649) fix(core): Declutter webhook insertion errors (#10650) feat: Reintroduce collaboration feature (#10602) feat(benchmark): Add scenario for expressions with Set node (#10647) feat(benchmark): Add benchmark scenario for binary files (#10648) build: Add `reset` script (#10627) feat(editor): Overhaul node insert position computation in new canvas (no-changelog) (#10637)
Merged
|
Got released with |
riascho
pushed a commit
that referenced
this pull request
Sep 23, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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
When using Anthropic models paired with memory, we discovered an issue with a Tools agent which would throw an error when populating the memory. To fix it, we need to check
AgentFinishstep if it contains string or array output(in Anthropic's case) and merge the text-only array of outputs to a single item.Related Linear tickets, Github issues, and Community forum posts
Review / Merge checklist
release/backport(if the PR is an urgent fix that needs to be backported)