github-mirror/n8n
1
0
Fork 0
mirror of https://github.com/n8n-io/n8n.git synced 2026-10-19 16:55:02 +02:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity Graph
22,525 Commits 1,918 Branches 2,206 Tags 4.7 GiB
tmp/eff-token-eff
Commit Graph

551 Commits

Author SHA1 Message Date
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
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
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
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
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
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
José Braulio González Valido
c3b50283fd
fix(ai-builder): Report an unparseable LLM check verdict as errored (no-changelog) (#35198) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-07-30 08:18:36 +00:00
José Braulio González Valido
aad2fa5577
feat(ai-builder): Add a Google Drive credential template to the eval seeder (no-changelog) (#35200) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-07-29 22:17:11 +00:00
Mutasem Aldmour
22c8117321
fix(ai-builder): Route eval report artifacts through --output-dir (no-changelog) (#35083) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-07-29 11:04:42 +00:00
José Braulio González Valido
2ae18ad9f6
feat(ai-builder): Validate the eval conversation-seed message envelope (no-changelog) (#35138) 
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-07-29 08:58:55 +00:00
Luka Zivkovic
650d893151
feat(ai-builder): Emit transcriptPerRun and buildErrorPerRun in eval-results.json (no-changelog) (#35078) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-28 19:25:22 +00:00
Tomi Turtiainen
b964ed6f4b
refactor(core): Move sleep into @n8n/utils and unify sleep/sleepWithAbort (#35057) 2026-07-28 18:47:18 +00:00
José Braulio González Valido
632ef22c0c
feat(ai-builder): Carry an eval case's conversation seed in the case body (no-changelog) (#35074)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Util: Sync API Docs / sync-public-api (push) Waiting to run
Details
2026-07-28 16:26:08 +00:00
Michael Drury
0ef049d12a
build(core): Upgrade agents to AI SDK 7 (#35072) 2026-07-28 16:13:00 +00:00
José Braulio González Valido
6d8b01dc79
fix(ai-builder): Enforce declared field names on eval pin data (no-changelog) (#34960) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-28 13:11:02 +00:00
Michael Kret
b2af755502
fix(core): Prefer n8n credits covered nodes in Instance AI workflow builds (#35019) 2026-07-28 11:58:42 +00:00
n8n-release-tag-merge[bot]
acc62367c2 Merge tag 'n8n@2.33.0' 2026-07-28 07:58:38 +00:00
José Braulio González Valido
66408a0cd5
feat(ai-builder): Push agent intent eval cases from data/agents and drop synced case files (no-changelog) (#34957) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-28 07:25:30 +00:00
n8n-assistant[bot]
60cc920c40
🚀 Release 2.33.0 (#35054) 
Co-authored-by: n8n-release-helper[bot] <265227495+n8n-release-helper[bot]@users.noreply.github.com>
 2026-07-28 07:15:34 +00:00
José Braulio González Valido
9a96941d81
fix(ai-builder): Pin zero-item premises as empty arrays and attribute pinned-fixture faults (no-changelog) (#34953) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-27 13:20:52 +00:00
José Braulio González Valido
ba31860da7
fix(core): Require an authenticated session for the MCP registry test seed endpoint (no-changelog) (#34880) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-27 13:20:38 +00:00
Anne Aguirre
fec6ceef3c
fix(ai-builder): Provision agent prerequisites before build-agent delegation (#34802) 2026-07-27 13:08:56 +00:00
Anne Aguirre
3301e12014
fix(ai-builder): MCP Connections failures are non-blocking for agents (#34722) 2026-07-27 12:47:54 +00:00
Albert Alises
4078318cff
feat: Configure the AI Assistant through a redesigned instance settings page (#34493) 2026-07-27 10:07:28 +00:00
José Braulio González Valido
b0a10229a0
refactor(ai-builder): Split the eval harness runner into domain modules (no-changelog) (#34834) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-27 09:01:09 +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)
Some checks failed
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Build: Benchmark Image / build (push) Has been cancelled
Details
Util: Sync API Docs / sync-public-api (push) Has been cancelled
Details
2026-07-24 15:26:08 +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
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
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
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
José Braulio González Valido
cbe5710c4c
feat(ai-builder): Report per-case claude build cost for MCP eval builds (no-changelog) (#34777) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 18:42:09 +00:00
Riqwan Thamir
b0a14728d7
refactor(core): Remove unused templates and list_skills AI tools (no-changelog) (#34741) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-23 15:38:41 +00:00
Robin Braumann
e5b1ac9f38
feat(core): Build agent drafts before asking for setup in the agent builder (no-changelog) (#34615) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-23 12:55:51 +00:00
José Braulio González Valido
b93a99945b
feat(ai-builder): Harden the eval harness — crash-recovery journal, parity fixes, extension points (no-changelog) (#34747) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 12:25:55 +00:00
Raúl Gómez Morales
a8c90f84fe
fix(core): Fall back to the run's resolved model for AI Assistant verification LLM calls (#34627) 2026-07-23 11:16:03 +00:00
Raúl Gómez Morales
5a647443ad
fix(ai-builder): Keep assistant replies in the user's language during tool-heavy turns (#34761) 2026-07-23 10:08:31 +00:00
Raúl Gómez Morales
206a2581e4
fix(core): Preserve the underlying error as cause on Instance AI workspace file reads (#34759) 2026-07-23 10:08:06 +00:00
José Braulio González Valido
3f63b73d38
fix(ai-builder): Scope user-proxy decisions to the conversation moment (no-changelog) (#34719) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-23 00:04:17 +00:00
José Braulio González Valido
ce6416fe04
docs(ai-builder): Add a source-linking provenance step to the eval-authoring skill (no-changelog) (#34721)
Some checks are pending
Build: Benchmark Image / build (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Build for Github Cache (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (22.22.3) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Unit tests (24.18.0) (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Lint (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Performance (push) Waiting to run
Details
CI: Master (Build, Test, Lint) / Notify Slack on failure (push) Blocked by required conditions
Details
Util: Sync API Docs / sync-public-api (push) Waiting to run
Details 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 22:35:13 +00:00
José Braulio González Valido
463d50b1bd
refactor(ai-builder): Decompose the eval CLI into phase modules with typed seams (no-changelog) (#34691) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 16:25:44 +00:00
Riqwan Thamir
94e505a972
fix(core): Strip null optional node fields from AI-generated workflows (#34668) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-22 15:38:56 +00:00
Riqwan Thamir
c0fe8ba4db
feat(editor): Track Instance AI entry point as action_source on builder messages (#34671) 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-22 13:24:29 +00:00
José Braulio González Valido
5a1aa3feef
fix(ai-builder): Detect datasets changes when re-pushing eval cases to LangTracer (no-changelog) (#34658) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 11:55:48 +00:00
José Braulio González Valido
ee46e64d50
chore(ai-builder): Typecheck the eval harness and pin its external contracts (no-changelog) (#34673) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-22 08:18:41 +00:00
Arvin A
babc0b7344
fix(core): Fix eval-collection scoring, re-run and progress states (no-changelog) (#34475) 2026-07-21 16:08:38 +00:00