Commit Graph

195 Commits

Author SHA1 Message Date
Albert Alises
eba7d056c5
feat(core): Make sandbox thread-scoped and lazy-initialize it on Instance AI (#30904) 2026-05-22 11:39:00 +00:00
José Braulio González Valido
96a9521394
ci: Use PR head ref in eval experiment names (no-changelog) (#30898)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 11:06:50 +00:00
oleg
4ba0f950cc
fix(core): Preserve instance AI image tool results (no-changelog) (#30895) 2026-05-22 10:26:46 +00:00
Rob Hough
a1a8e3d693
refactor(editor): Stack tools and improve naming in Agents (#30918) 2026-05-22 09:38:14 +00:00
Tomi Turtiainen
d82fbc8f85
feat(core): Harden n8n sandbox service adapter (no-changelog) (#30813) 2026-05-22 06:29:52 +00:00
Jaakko Husso
a3210d5ede
fix(core): Guide agent to not pass bogus workflow-id to submit-workflow tool (#30911) 2026-05-21 15:38:04 +00:00
Albert Alises
b272ab4fe8
fix(core): Submit builder workflow file when submit is missed (#30711) 2026-05-21 15:35:03 +00:00
José Braulio González Valido
ada126d9b7
test(ai-builder): Validate user-proxy tool outputs against api-types schemas (no-changelog) (#30905)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 14:15:44 +00:00
José Braulio González Valido
81ea56fa6b
test(ai-builder): Add multi-turn capability for IAI evals (no-changelog) (#30586)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 13:03:35 +00:00
José Braulio González Valido
e9b1c7c48f
chore(ai-builder): Tag Daytona sandboxes with name prefix and labels (no-changelog) (#30697)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 12:43:36 +00:00
Jaakko Husso
52e15bdcaf
feat(core): Add tool for checking workflow validation errors (#30868) 2026-05-21 12:40:47 +00:00
Albert Alises
bd5cd31093
perf(ai-builder): Defer heavy idle-boot dependencies (-27 MiB heap) (#30834)
Some checks are pending
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 (24.15.0) (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
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-05-21 09:28:39 +00:00
Bernhard Wittmann
374e7ed0b2
ci: Fail Instance AI discovery evals only on zero-pass scenarios (no-changelog) (#30816) 2026-05-21 06:44:18 +00:00
Raúl Gómez Morales
41c876ea68
feat(editor): Redesign instance AI approval dialogs (no-changelog) (#30654) 2026-05-20 18:26:28 +00:00
Luca Mattiazzi
e13d4e0465
feat(core): Add eval-data populator tool (no-changelog) (#30680) 2026-05-20 16:18:06 +00:00
Luca Mattiazzi
73eae7f1d4
feat(core): Add eval setup sub-agent (no-changelog) (#30665) 2026-05-20 15:10:35 +00:00
oleg
c8ac2fb1f2
feat(core): Rework LangSmith tracing (no-changelog) (#30017) 2026-05-20 10:06:11 +00:00
Luca Mattiazzi
3f06919c52
feat(core): Add eval-data row services + eval-setup sub-agent prompt (no-changelog) (#30548)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 09:27:02 +00:00
Luca Mattiazzi
dbf20a4c85
feat(core): Add Instance AI evals setup tool (no-changelog) (#30661) 2026-05-20 09:26:01 +00:00
Albert Alises
b60188001a
fix(core): Set HITL confirmation timeout default (#30783) 2026-05-20 09:22:54 +00:00
Albert Alises
4b4f663b08
perf(core): Reduce Instance AI memory usage (#30777)
Some checks are pending
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.x) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.15.0) (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
2026-05-20 09:18:43 +00:00
Albert Alises
cdfc9053f6
fix(core): Keep Instance AI HITL confirmations waiting (#30722)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.x) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.15.0) (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
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-05-19 15:55:46 +00:00
oleg
d7d2cc1442
feat(core): Add native agent substrate (no-changelog) (#30015)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2026-05-19 13:48:45 +00:00
Luca Mattiazzi
b753597b51
feat(core): Add eval tools helpers (no-changelog) (#30669) 2026-05-19 13:31:48 +00:00
n8n-assistant[bot]
5ca71e8c0a
🚀 Release 2.22.0 (#30713)
Co-authored-by: Matsuuu <16068444+Matsuuu@users.noreply.github.com>
2026-05-19 11:36:59 +00:00
Albert Alises
4a0dd577a6
refactor: Remove user-facing AI research mode (no-changelog) (#30699) 2026-05-19 10:10:28 +00:00
José Braulio González Valido
db69aa6509
fix(core): Return plan-tool validator errors as tool results instead of throwing (#30592)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 07:53:55 +00:00
Luca Mattiazzi
6185a9f2d6
feat(core): Add eval workflow analysis helpers (no-changelog) (#30507)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 07:37:20 +00:00
Dimitri Lavrenük
f8f737c828
feat: Improve browser use instructions in the prompt (no-changelog) (#30659)
Co-authored-by: Bernhard Wittmann <bernhard.wittmann@n8n.io>
2026-05-19 05:59:41 +00:00
aikido-autofix[bot]
ac02d32aa9
fix: Fix 13 critical issues in vm2, protobufjs, @daytonaio/sdk and 4 more (#30578)
Co-authored-by: aikido-autofix[bot] <119856028+aikido-autofix[bot]@users.noreply.github.com>
Co-authored-by: Declan Carroll <declan@n8n.io>
2026-05-18 18:27:31 +00:00
Albert Alises
0d262fe638
fix(ai-builder): Ground workflow setup guidance (#30638) 2026-05-18 15:30:03 +00:00
Dimitri Lavrenük
c32591e66c
feat: Computer use tools to safely create credentials (no-changelog) (#30320) 2026-05-18 12:46:17 +00:00
Albert Alises
458709f6c7
fix: Improve AI builder reliability for Sheets and workflow lookups (#30546) 2026-05-18 11:08:35 +00:00
Albert Alises
07c861adf5
test(core): Re-record instance-ai workflow setup traces (no-changelog) (#30479)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.x) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.15.0) (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
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-05-18 08:18:33 +00:00
Tomi Turtiainen
b814f06174
chore: Bump @n8n/sandbox-client to 0.0.4 (no-changelog) (#30502) 2026-05-15 08:25:44 +00:00
Albert Alises
17b64da0f0
fix: Add Switch fallback output guidance for workflow builder (#30449) 2026-05-15 07:33:25 +00:00
Albert Alises
f1fd79f830
fix(core): Avoid unnecessary planner credential prompts (#30451) 2026-05-14 15:36:11 +00:00
José Braulio González Valido
9fcd5c5864
feat(ai-builder): Tool-driven eval mock handler with per-API quirks registry (#30135)
Some checks are pending
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.x) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.14.1) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (25.x) (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
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 14:29:10 +00:00
José Braulio González Valido
6beed60969
fix(core): Extract workflow-sdk examples to a writable cache dir (#30433)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 09:10:23 +00:00
Albert Alises
c3e39f8504
fix(ai-builder): Guide builder to prefer httpBearerAuth for Bearer flows (#30309) 2026-05-13 17:24:56 +00:00
Albert Alises
5d872d1375
fix(core): Add Instance AI first-turn guidance and trace metadata (#30315) 2026-05-13 09:32:29 +00:00
Mutasem Aldmour
2fd54d8230
feat(core): Curate workflow examples for the builder sandbox (#30025)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 06:45:39 +00:00
Bernhard Wittmann
c9ecef2a36
test: Add discovery eval guardrails for browser/computer-use dispatch (no-changelog) (#30236) 2026-05-12 14:29:35 +00:00
Albert Alises
22f2e34fe6
fix(core): Stop workflow builder after terminal remediation (#30289)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (22.x) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (24.14.1) (push) Waiting to run
CI: Master (Build, Test, Lint) / Unit tests (25.x) (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
Util: Sync API Docs / sync-public-api (push) Waiting to run
2026-05-12 13:53:18 +00:00
Jaakko Husso
0ce820de73
fix(core): Abort orchestrator run after repeated plan-guard rejections (no-changelog) (#30274) 2026-05-12 12:11:17 +00:00
Milorad FIlipović
54d62bb4a1
fix(core): Update instance-ai evaluator to include pinned subnodes and allow all mcp tools (#30292) 2026-05-12 09:13:01 +00:00
Albert Alises
5059ce7e3d
feat(ai-builder): Expose generated workflow IDs on LangSmith trace root metadata (#30262) 2026-05-12 08:37:57 +00:00
Bernhard Wittmann
b445221c6a
feat: Computer-use evaluation harness (no-changelog) (#29797)
Co-authored-by: Elias Meire <elias@meire.dev>
2026-05-12 08:36:12 +00:00
Mutasem Aldmour
3297536011
refactor(core): Move node-specific builder guidance to per-node @builderHint (no-changelog) (#29992)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 07:45:33 +00:00
José Braulio González Valido
95cf41c37c
chore(core): Enable Daytona sandbox in Instance AI evals (no-changelog) (#29931)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 07:43:04 +00:00