Claude
27a18cd961
refactor(core): Return text-only responses from string-payload MCP builder tools
...
The get_node_types, search_nodes, get_workflow_sdk_reference and
get_workflow_best_practices MCP tools mirrored their entire text payload
(multi-KB TypeScript definitions, SDK reference, docs) verbatim into
structuredContent, doubling the size of every response on the wire. The
structured envelope carried no additional semantics for these tools and
has no programmatic consumers, unlike the JSON-payload tools (e.g.
get_workflow_details, whose structuredContent the workflow-preview MCP
app depends on), which keep theirs.
Drop outputSchema and structuredContent from these four tools so the
text block is the single source of the payload. The n8nConnect coverage
block remains appended to the text as before.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017gHjn1wM5srMwPexRpukJg
2026-07-31 13:33:20 +03:00
Claude
d3bc90a777
feat(instance-ai): Record errored MCP build tool calls with messages (no-changelog)
...
Correlate tool_result events back to their tool_use by id and record every
is_error result as {tool, message} (message truncated to 500 chars; string
and text-block-array contents both handled). The failure list rides next to
toolCalls through the whole spend pipeline: buildToolErrorsPerRun per case
and per-tool error counts in summary.mcpBuild.toolErrors in
eval-results.json, a build_tool_errors count as LangSmith row feedback plus
per-tool totals in experiment metadata, and per-build lists + totals in the
manifest builder's stats sidecar. Timed-out builds keep contributing the
errors their partial stream recorded.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GA23ytEUfHpzkv7meRdVAJ
2026-07-31 13:32:37 +03:00
Claude
fad8718e0c
feat(instance-ai): Attribute MCP eval build turns to specific tools (no-changelog)
...
Switch the claude -p MCP build from --output-format json to stream-json
(with --verbose), persist the verbatim NDJSON event stream as the
per-attempt .jsonl build log, and count tool_use blocks per tool name.
The counts ride alongside the existing cost/turns spend: per case as
buildToolCallsPerRun and run-wide as summary.mcpBuild.toolCalls in
eval-results.json, as build_tool_calls in LangSmith experiment metadata,
and in the manifest builder's stats sidecar. Timed-out builds contribute
the attribution their partial stream recorded, so a hung build now says
what it was doing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GA23ytEUfHpzkv7meRdVAJ
2026-07-31 13:32:35 +03:00
Alex Grozav
4e03a0784f
refactor(editor): Single-source CloudPlanState (no-changelog) ( #35328 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-31 10:11:34 +00:00
Svetoslav Dekov
736f570d19
fix(Notion Node): Mark title as required for database page create in v3 ( #35334 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-31 10:08:48 +00:00
Arvin A
bbe1c374af
feat(core): Add REST endpoints for agent evals (no-changelog) ( #35101 )
2026-07-31 09:50:33 +00:00
Nikhil Kuriakose
d512f5c8de
fix(editor): Wait for animated zoom-in transition to settle ( #35244 )
2026-07-31 09:29:21 +00:00
Alex Grozav
5b314258b5
refactor(editor): Move usePageRedirectionHelper's base composable into @n8n/stores (no-changelog) ( #35174 )
...
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
2026-07-31 09:25:09 +00:00
Alex Grozav
3e5cbb8adb
refactor(editor): Relocate the toast bootstrap registration out of the deprecated useToast shim (no-changelog) ( #35151 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-31 09:21:42 +00:00
Kai
f52e2b831d
feat(editor): Show the latest workflow review state in the canvas header ( #35233 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 08:47:32 +00:00
mfsiega
2a310a8e3f
feat(core): Persist step results in @n8n/engine (no-changelog) ( #35192 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 08:43:49 +00:00
Arvin A
4943a064be
feat(core): Add agent-eval rating persistence with edit capture (no-changelog) ( #35252 )
2026-07-31 08:31:45 +00:00
Miguel Ángel Moreno
0e3aead790
feat(core): Make invalid node groups non-fatal in update_workflow and create_workflow_from_code (no-changelog) ( #35060 )
...
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-31 08:24:15 +00:00
Alex Grozav
0ad676cc82
refactor(editor): Drop the IInviteResponse and ModalOpeners re-export shims (no-changelog) ( #35168 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-31 08:07:03 +00:00
Lorent Lempereur
ba21bea63f
fix(editor): Guard optional fields when reading public settings ( #35281 )
2026-07-31 08:03:59 +00:00
RomanDavydchuk
22816b3f34
feat(Cal.com Trigger Node): Fully migrate to API v2 ( #35055 )
2026-07-31 07:58:46 +00:00
Kai
96d37a319f
feat(editor): Make the review inbox URL-addressable with deep-linkable reviews ( #35201 )
2026-07-31 07:44:07 +00:00
Dimitri Lavrenük
ce8669e4db
feat: Add ap-east-2 and ap-southeast-6 AWS regions ( #35278 )
2026-07-31 07:33:16 +00:00
José Braulio González Valido
be12a4ccdc
feat(ai-builder): Let eval runs exercise the builder's web search (no-changelog) ( #35274 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 07:31:10 +00:00
oleg
1cedd9f114
fix(core): Skip error workflow dispatch for AI builder verification runs ( #35247 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 07:17:59 +00:00
oleg
703466644c
fix(core): Preserve saved node positions when the assistant edits a workflow ( #35268 )
...
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-07-31 07:17:45 +00:00
Michael Kret
47569fcd88
fix: Support n8n credits on nodes with multiple credential types ( #35190 )
2026-07-31 05:16:29 +00:00
Elias Meire
5a0697ea0c
refactor(editor): Extract the MCP connect flow into a composable ( #35258 )
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
2026-07-30 21:37:43 +00:00
Svetoslav Dekov
d4902d58f3
feat(editor): Add per-agent MCP access management with agent scopes ( #34853 )
...
Co-authored-by: Ricardo Espinoza <ricardo@n8n.io>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 21:33:15 +00:00
Tomi Turtiainen
ca54f325bd
fix: Validate Send and Wait custom forms before sending ( #35262 )
2026-07-30 21:03:19 +00:00
Michael Drury
703c600b0a
fix(editor): Rename preview AI Agent node to V2 ( #35285 )
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Build: Benchmark Image / build (push) Has been cancelled
Util: Publish API Schema / Cloudflare Pages (push) Has been cancelled
2026-07-30 16:26:37 +00:00
Robin Braumann
94099ba9bd
fix(core): Stream sub-agent output to the chat and keep its trace (no-changelog) ( #35255 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 16:21:46 +00:00
Robin Braumann
33caa35985
fix(editor): Create agent-builder credentials in the agent's project ( #35286 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 16:21:43 +00:00
Jon
e4e33e3363
fix(Slack Node): Add groups:write OAuth scope for private channel actions ( #35288 )
2026-07-30 16:15:10 +00:00
Robin Braumann
9b1d5af815
fix(core): Stop AIA agent builder on cancel without red tree errors (no-changelog) ( #35243 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 15:43:55 +00:00
Kai
eb07728511
feat(core): Block publishing a workflow while its review is open ( #35199 )
2026-07-30 15:37:27 +00:00
Riqwan Thamir
bbd7b7db88
feat(core): Add workflow SDK validation framework for Instance AI ( #35045 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 15:18:11 +00:00
Robin Braumann
3ca4828a20
feat(editor): Show and change the target workflow of an agent workflow tool ( #35276 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 15:15:05 +00:00
Michael Kret
1c11f43556
feat: Enable n8n Connect for the Agent Builder ( #34298 )
...
Co-authored-by: Robin Braumann <50590409+bjorger@users.noreply.github.com>
2026-07-30 15:14:02 +00:00
Lorent Lempereur
bdf33c1ad3
fix(core): Limit the size of webhook responses relayed through the queue ( #35032 )
2026-07-30 15:00:01 +00:00
Jon
1aed5e6289
feat(Slack Node): Show user real names and handles in user pickers ( #35279 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-30 14:39:06 +00:00
Iván Ovejero
bcf7502adc
feat(core): Complete v1-to-v2 workflow converter (no-changelog) ( #35189 )
2026-07-30 14:25:54 +00:00
Eugene
0932806c05
feat: Support inbound binary attachments for agents (no-changelog) ( #34869 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 14:20:06 +00:00
oleg
d0d0b7a12c
fix(core): Default AI-created workflows to v1 execution order ( #35277 )
2026-07-30 14:09:20 +00:00
Tomi Turtiainen
0d4c3a7e22
fix(core): Preserve cause on execution errors ( #35216 )
2026-07-30 13:55:28 +00:00
Ricardo Espinoza
256478f748
refactor(core): Break credentials-overwrites and frontend service cycle ( #35226 )
2026-07-30 13:13:19 +00:00
n8n-cat-bot[bot]
71273ea3a8
test: Fix assistant credential-help spec for credential-modal default ( #35260 )
...
Co-authored-by: n8n-cat-bot[bot] <n8n-cat-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-30 13:08:43 +00:00
Iván Ovejero
03316691b6
perf(core): Ungate skip persisting run data for discarded executions ( #35256 )
2026-07-30 13:03:07 +00:00
Elias Meire
c1f55776ed
fix(MCP Server Trigger Node): Save execution data only after tool call completes ( #35239 )
2026-07-30 12:59:10 +00:00
Tomi Turtiainen
2d61b0fa65
fix(core): Only wake the publication outbox consumer on the leader (no-changelog) ( #35261 )
2026-07-30 12:55:32 +00:00
Lorent Lempereur
8e62ca250e
fix(core): Import security audit risk reporters with a file extension ( #35263 )
2026-07-30 12:37:41 +00:00
Jan Kalkan
3ce4c62264
refactor(core): Keep a single exact tag name lookup function on TagService ( #35217 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 12:02:55 +00:00
Irénée
70d3ef80b1
feat(core): Support reference-only sub-workflow dependencies in package export (no-changelog) ( #35051 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 11:26:18 +00:00
José Braulio González Valido
00fe448a68
feat(ai-builder): Verify approval-loop branches with scripted gate decisions ( #34822 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 11:05:51 +00:00
Miguel Ángel Moreno
fcaadfa375
ci: Run a package's full test suite when affected by an upstream change ( #34986 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-30 10:32:09 +00:00
