Commit Graph

858 Commits

Author SHA1 Message Date
Jaakko Husso
f34c093f08
feat(core): Add an optional model for n8n Assistant memory tasks (#41137)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 13:55:06 +00:00
Jaakko Husso
b78913f75d
fix(core): Keep the workflow source file when n8n Assistant sends blank source (#41201)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 13:28:54 +00:00
Jaakko Husso
bab83634ce
perf(core): Reuse the prebaked runtime skills bundle in the sandbox (no-changelog) (#41027)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 08:35:34 +00:00
Raúl Gómez Morales
50c4ced224
fix(core): Keep pending setup for nodes that n8n Assistant added in an earlier build (#41070) 2026-10-14 16:52:18 +00:00
Raúl Gómez Morales
3c7dcf902d
feat(ai-builder): Write LangTracer results from the routing evals (no-changelog) (#40954) 2026-10-14 15:42:42 +00:00
Jaakko Husso
56eac665c3
fix(core): Make the Assistant check the n8n side before it names a failure cause (no-changelog) (#41097)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 13:26:37 +00:00
José Braulio González Valido
1b0cdd5998
fix(ai-builder): Report eval helper model failures as infrastructure, not as bad JSON (no-changelog) (#40415)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-14 11:23:25 +00:00
Raúl Gómez Morales
578eea403d
fix(core): Stop asking to set up a node when n8n Assistant only adds a step next to it (#41067) 2026-10-14 11:20:43 +00:00
Stephen Wright
3800bce812
feat(Text Classifier Node): Add opt-in confidence scores to the output (#40743) 2026-10-14 09:42:05 +00:00
Mutasem Aldmour
0b4c99f10d
fix(core): Pick output schemas by parameter value for Gmail and Notion (no-changelog) (#40757)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-14 09:11:49 +00:00
Jaakko Husso
e3b2603d7b
chore(core): Remove activation-capped AI Assistant trial variant (no-changelog) (#41036)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 08:21:20 +00:00
Jaakko Husso
726a5829c8
fix(core): Use the module registry to decide if the Assistant has the Agents features (#41026)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 08:19:48 +00:00
Bernhard Wittmann
ccf42e3213
fix(ai-builder): Make browser credential-setup evals grade the right thing (no-changelog) (#40858) 2026-10-14 06:24:28 +00:00
José Braulio González Valido
29de1c63ae
fix(ai-builder): Remove the Context7 docs lookup from the eval mock (no-changelog) (#40021)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-13 21:30:08 +00:00
José Braulio González Valido
146d7804af
fix(ai-builder): Count eval runs that read another build's workflow as framework issues (no-changelog) (#40717)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-13 21:29:00 +00:00
José Braulio González Valido
88de3cac20
feat(ai-builder): Move eval judges to Sonnet 5.5 and add per-role eval LLM settings (no-changelog) (#40330)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-13 21:28:25 +00:00
Jaakko Husso
2bc3265e63
perf(ai-builder): Trust a matching prebaked bundle manifest in the sandbox (no-changelog) (#40820)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 11:04:18 +00:00
Jaakko Husso
ffda639b3f
fix(editor): Show follow-up run events in the Assistant after a reconnect (#40883)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 10:12:33 +00:00
n8n-assistant[bot]
bae368caca
🚀 Release 2.44.0 (#40943)
Co-authored-by: n8n-release-helper[bot] <265227495+n8n-release-helper[bot]@users.noreply.github.com>
2026-10-13 07:12:07 +00:00
Anne Aguirre
8b7065a876
fix(core): Block the assistant when AI credits hit zero (#40659) 2026-10-09 10:39:03 +00:00
Raúl Gómez Morales
d900743bce
fix(core): Improve node placement when n8n Assistant edits a workflow (#40139)
Co-authored-by: Mutasem Aldmour <mutasem@n8n.io>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 09:56:40 +00:00
José Braulio González Valido
5480258fb5
feat(ai-builder): Report the eval harness's own model usage per case (no-changelog) (#40718)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-09 07:52:09 +00:00
José Braulio González Valido
5b78e8b655
fix(ai-builder): Run each eval build in its own empty project (no-changelog) (#40715)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-08 21:15:11 +00:00
n8n-cat-bot[bot]
03f7c76acd
fix: Update runtime and MCP dependency APIs (no-changelog) (#40204)
Co-authored-by: n8n-cat-bot[bot] <n8n-cat-bot[bot]@users.noreply.github.com>
Co-authored-by: Michael Drury <michael.drury@n8n.io>
2026-10-08 15:43:51 +00:00
Raúl Gómez Morales
e67e5a9ef1
test(core): Run routing cases that start with state (no-changelog) (#40378) 2026-10-08 15:33:58 +00:00
Jaakko Husso
1d63a8f3a1
chore(core): Log npm output when the sandbox workspace link install fails (#40591)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 09:26:41 +00:00
Raúl Gómez Morales
6b8ac76d96
test(core): Add a routing mode to the Assistant discovery evals (no-changelog) (#40288) 2026-10-08 07:55:26 +00:00
Riqwan Thamir
3816c4afec
feat(ai-builder): Honor reasoning effort override for Anthropic models in evals (no-changelog) (#39809)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-07 14:18:33 +00:00
José Braulio González Valido
0e1c754999
fix(ai-builder): Take feature flags from env only on Instance AI eval instances (no-changelog) (#40117)
Some checks are pending
CI: Master (Build, Test, Lint) / Build & format (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.18.1) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (26.5.1) (push) Waiting to run
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
CI: Master (Build, Test, Lint) / Verify single-instance deps (npm-install) (push) Waiting to run
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-06 20:46:09 +00:00
Riqwan Thamir
90b8205b62
feat(core): Load Instance AI skill references progressively (no-changelog) (#40296)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-06 20:03:33 +00:00
Riqwan Thamir
b36c2b506b
perf(core): Prepare Instance AI skill sandbox in the background (#40363) 2026-10-06 16:17:43 +00:00
Jaakko Husso
5d3866775c
feat(ai-builder): Reopen closed AI Assistant tabs when the agent changes the artifact (#40081)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 11:34:27 +00:00
Jaakko Husso
3366d2b9b3
fix(core): Stop marking the Message an Agent node as hidden (#40358)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 11:24:39 +00:00
n8n-assistant[bot]
a11777054a
🚀 Release 2.43.0 (#40376)
Co-authored-by: n8n-release-helper[bot] <265227495+n8n-release-helper[bot]@users.noreply.github.com>
2026-10-06 07:10:16 +00:00
José Braulio González Valido
b7071c91c7
fix(ai-builder): Treat a blank folder path as no folder in the build tool (#40116)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 13:57:14 +00:00
Riqwan Thamir
fe07e84d0f
fix(core): Keep skill activation and memory compaction from breaking the prompt cache (no-changelog) (#40245)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-05 10:48:35 +00:00
Robin Braumann
ea9021ed86
feat(core): Add durable pause checkpoints for background sub-agents (no-changelog) (#40118) 2026-10-02 13:10:50 +00:00
Matsu
6337b94d3c
chore: Add typescript/no-deprecated and establish a baseline (#40168) 2026-10-02 12:54:37 +00:00
Raúl Gómez Morales
6438ead58d
fix(core): Report empty node output in Instance AI workflow verification (#40047) 2026-10-02 08:45:43 +00:00
Jaakko Husso
7d5730f688
fix(ai-builder): Pack @n8n/errors when linking the workflow SDK into the sandbox (no-changelog) (#40056)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 08:34:28 +00:00
oleg
f82fa0c1af
fix(core): Keep node parameters when n8n Assistant cannot see them (#39454) 2026-10-01 13:55:32 +00:00
Declan Carroll
a4b87fccbe
refactor: Group quality engineering workspaces by capability (#40007) 2026-10-01 11:20:00 +00:00
Anne Aguirre
3745c835b2
feat(core): Add a guardrail runner to the agent loop (#39621)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:21:42 +00:00
Raúl Gómez Morales
0e3f6e996e
feat(editor): Add the AI Assistant test URL card (no-changelog) (#38627) 2026-10-01 09:42:00 +00:00
Robin Braumann
3a445ae2bf
feat(core): Add session approvals for Agent tools (no-changelog) (#39560) 2026-10-01 09:14:23 +00:00
José Braulio González Valido
1b1bb4698d
fix(ai-builder): Bind a seeded eval Agent's model to the case credential (no-changelog) (#39984)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 22:18:59 +00:00
José Braulio González Valido
e185c36c59
fix(ai-builder): Clear eval dedupe state between runs and add a Sheets mock quirk (no-changelog) (#39990)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-30 22:18:56 +00:00
José Braulio González Valido
0c8acfa274
fix(ai-builder): Send requiresMemoryCompaction on eval case push (no-changelog) (#39989)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 17:34:50 +00:00
José Braulio González Valido
54f634d5f9
fix(ai-builder): Cancel the thread when an eval turn budget fires after the run (no-changelog) (#39992)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 17:34:47 +00:00
Raúl Gómez Morales
5c1f8f7f6c
fix: Scope the legacy setup credential picker to the target workflow and report unusable credentials on apply (#38197) 2026-09-30 12:52:56 +00:00