Riqwan Thamir
41e31a11c3
chore: wip
2026-07-27 01:23:20 +02:00
Riqwan Thamir
4d5d8be948
chore: wip
2026-07-26 23:49:57 +02:00
Riqwan Thamir
351ddabdbc
chore: wip
2026-07-26 23:33:00 +02:00
Riqwan Thamir
d8b2a0adf0
chore: wip
2026-07-26 22:50:22 +02:00
Riqwan Thamir
7bee4a7399
chore: wip
2026-07-26 20:47:23 +02:00
Riqwan Thamir
c16cc7f85c
chore: wip
2026-07-26 20:27:35 +02:00
Riqwan Thamir
3e63ae95a0
chore: wip
2026-07-26 16:01:10 +02:00
Riqwan Thamir
a9135e79ed
chore: wip
2026-07-25 22:05:18 +02:00
Riqwan Thamir
fc0c0c45fc
chore: wip
2026-07-25 22:02:47 +02:00
Riqwan Thamir
59b1ec0f1a
chore: wip
2026-07-25 21:56:14 +02:00
Riqwan Thamir
a121aff730
chore: wip
2026-07-25 18:35:53 +02:00
Riqwan Thamir
38688aafe4
ci: Throttle Instance AI evals for Baseten rate limits
...
Expose lanes/eval-concurrency knobs and auto-set 1/2 (plus a 10h timeout)
when model is baseten/*, so GLM experiments fit Basic verified TPM/RPM.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:51 +02:00
Riqwan Thamir
509719d27c
chore: add opus 5
2026-07-25 18:35:48 +02:00
Riqwan Thamir
fa7324779f
feat(core): Wire Baseten into agents providers and builder settings
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:46 +02:00
Riqwan Thamir
74da3599e1
fix(core): Route Baseten chat via openai-compatible (no-changelog)
...
Avoid @ai-sdk/baseten's eager NAPI performance-client load, which pnpm deploy --no-optional strips and breaks Alpine Docker Instance AI evals.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:45 +02:00
Riqwan Thamir
f556fd381e
feat(instance-ai): Add Baseten GLM 5.2 provider support and eval options
...
Integrate @ai-sdk/baseten for native GLM routing, map GLM 5.2 thinking to high effort, raise the default max output token cap to avoid reasoning-only truncation, and wire Baseten models into Instance AI eval experiments via EVALS_BASETEN_KEY.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:43 +02:00
Riqwan Thamir
a19d2d9cfe
ci: Add openai/gpt-5.6-luna to Instance AI evals model options (no-changelog)
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:40 +02:00
Riqwan Thamir
6466dbd6ea
feat(core): Pin OpenAI Instance AI thinking to medium for GPT-5.6 Sol (no-changelog)
...
Use AI SDK reasoningEffort medium by default, expand OpenAI effort types for
GPT-5.6, bump @ai-sdk/openai, and route openai/* evals through EVALS_OPENAI_KEY.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:38 +02:00
Riqwan Thamir
c4532b5692
feat(core): Raise default Instance AI thinking effort to medium (no-changelog)
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:35:01 +02:00
Riqwan Thamir
677b96d1f9
feat(core): Pin low Anthropic adaptive thinking effort (no-changelog)
...
Forward adaptive effort through Anthropic provider options and default
Instance AI / agent builder to effort=low.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:34:58 +02:00
Riqwan Thamir
a6ae91804e
feat(core): Pin low reasoning effort for Grok 4.5 (no-changelog)
...
Also enable xAI thinking capability and default low effort for
grok-4.5 via OpenRouter or native xAI.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:34:57 +02:00
Riqwan Thamir
e4b2df9230
feat(core): Pin low OpenRouter reasoning effort for Kimi K3 (no-changelog)
...
Enable OpenRouter thinking in provider capabilities and default Instance AI
to reasoning.effort=low for kimi-k3 model ids.
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-25 18:34:53 +02:00
Albert Alises
7d8426f055
feat: Add admin-managed instance credentials ( #34364 )
2026-07-25 14:22:22 +00:00
Miguel Ángel Moreno
6d66056058
feat(core): Make MCP clients aware of node groups (no-changelog) ( #34810 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-25 14:17:11 +00:00
Albert Alises
5339b5e48a
fix(core): Keep MCP server display names free-form in agent config ( #34931 )
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
2026-07-24 17:12:51 +00:00
Riqwan Thamir
55e92cc283
refactor(core): Consolidate sandbox and skill guidance in system prompt (no-changelog) ( #34909 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-24 15:50:37 +00:00
Anne Aguirre
decb3228c5
feat(ai-builder): Tidy up tool names and agent builder tool UX ( #34646 )
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: Sync API Docs / sync-public-api (push) Has been cancelled
2026-07-24 15:26:08 +00:00
Anne Aguirre
bac8debc0e
feat(ai-builder): Format zod erros on agent config - better toast msg ( #34867 )
2026-07-24 15:24:59 +00:00
Robin Braumann
8017b3d85f
feat(core): Add telemetry events for agent publishing, builder capabilities, and interactive flows ( #34887 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-24 14:34:11 +00:00
Ricardo Espinoza
99d70aedbd
build: Replace deprecated turbo --parallel with explicit concurrency in dev scripts (no-changelog) ( #34832 )
2026-07-24 14:34:02 +00:00
mfsiega
7089418a6b
feat(core): Add step-executor seam to @n8n/engine (no-changelog) ( #34784 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Iván Ovejero <ivov.src@gmail.com>
2026-07-24 14:31:15 +00:00
Danny Martini
3f2bc68846
feat(core): Detect and heal published-version skew in trigger reconciliation ( #34877 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 14:15:42 +00:00
Arvin A
e6a08eec58
fix(core): Normalize eval-collection scores per-run and harden re-run (no-changelog) ( #34736 )
2026-07-24 14:14:49 +00:00
Svetoslav Dekov
fdd4e33f9c
feat(core): Add availableInMCP column to agents ( #34665 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 14:09:04 +00:00
Kai
5a97bd1a2e
feat(editor): Sync a new workflow version into an existing open review ( #34842 )
2026-07-24 14:06:07 +00:00
Lorent Lempereur
4212fc2202
fix(core): Avoid loading execution data during credentials security audit ( #34876 )
2026-07-24 13:54:37 +00:00
mfsiega
d6c9c38ae7
feat(core): Add workflow_step_execution table to @n8n/engine (no-changelog) ( #34860 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-24 12:52:17 +00:00
Arvin A
e5bb60f663
feat(core): Add agent-scoped eval data model and migration (no-changelog) ( #34657 )
2026-07-24 12:37:53 +00:00
Riqwan Thamir
50789b1553
fix(core): Guiding data-table skill routing better (no-changelog) ( #34882 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-24 12:12:04 +00:00
Charlie Kolb
0c613b4405
fix(core): Publish workspace packages required by n8n at runtime ( #34886 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-24 11:55:52 +00:00
Eugene
3f1b35d669
fix(Wikipedia Tool Node): Surface tool errors as actionable node errors ( #34643 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 11:35:53 +00:00
Sandra Zollner
f4edeeba31
feat(core): Return open and closed counts for the review inbox tabs ( #34789 )
2026-07-24 11:26:39 +00:00
Michael Drury
9503892225
fix: Improve MCP tool handling (no-changelog) ( #34827 )
2026-07-24 11:00:35 +00:00
Guillaume F.
95da84912f
feat(core): Add credential-unnecessary-password community node lint rule ( #34791 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-24 10:44:16 +00:00
yehorkardash
d0b254cff8
fix(HTTP Request Node): Include error body in continueOnFail mode ( #34729 )
2026-07-24 10:07:14 +00:00
Riqwan Thamir
765129c436
refactor(core): Slim system prompt into skills and tool descriptions (no-changelog) ( #34816 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-24 09:58:06 +00:00
Albert Alises
13becf336c
feat(core): Add instance credential database schema ( #34709 )
...
Co-authored-by: Danny Martini <danny@n8n.io>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 09:37:33 +00:00
Guillaume F.
b7dcfc84cb
feat(core): Add no-silent-error-swallowing community node lint rule (no-changelog) ( #34780 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-24 09:13:19 +00:00
Robin Braumann
0b4bbd05b8
feat(core): Add storedAt column to agent_execution ( #34858 )
...
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-24 08:57:18 +00:00
José Braulio González Valido
e904939db2
fix(ai-builder): Halt workflow verification at send-and-wait gates on loops ( #34809 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 08:50:41 +00:00
