@deepidealab/n8n-nodes-tracira 0.10.0 → 0.12.0

package/README.md

@@ -2,7 +2,7 @@
 
 This is an n8n community node for Tracira.
 
-Tracira monitors AI outputs from your automations, evaluates them against rules, and lets you inspect log results from inside n8n workflows.
+Tracira monitors AI outputs from your automations, evaluates them against rules, and lets you inspect results from inside n8n workflows.
 
 [n8n](https://n8n.io/) is a [fair-code licensed](https://docs.n8n.io/sustainable-use-license/) workflow automation platform.
 
@@ -31,24 +31,28 @@ The package ships two nodes: **Tracira** (actions) and **Tracira Trigger** (watc
 
 ### Tracira Trigger
 
-Starts a workflow the moment a log gets a verdict or a human decision in Tracira. Pick which events to watch - the default (`approved` / `rejected` / `sent back for changes`) fires once a human has decided, the usual choice for approval flows; `flagged`, `passed`, and `error` evaluation events are opt-in. Activating the workflow registers the trigger with Tracira automatically (visible under Integrations → Connected triggers); deactivating removes it. Decision events include the AI `output` and the log `metadata`, so an approval workflow can deliver the approved reply with no extra lookup.
+Starts a workflow the moment an output gets a verdict or a human decision in Tracira. Pick which events to watch - the default (`approved` / `rejected` / `edited`) fires once a human has decided, the usual choice for approval flows; `flagged`, `passed`, and `error` evaluation events are opt-in. Activating the workflow registers the trigger with Tracira automatically (visible under Integrations → Connected triggers); deactivating removes it. Decision events include the AI `output` and its `metadata`, so an approval workflow can deliver the approved reply with no extra lookup. When a reviewer edits an output, `output` already carries their corrected version, so a workflow that maps `output` needs no changes: it delivers what the human approved, never the version they replaced. `correctedOutput` and `aiOutput` are there when you need to tell the cases apart.
 
-The typical human-in-the-loop pattern uses two workflows: workflow A creates the log (AI step → `Create a Log`, Wait for Verdict off), and workflow B starts with the Tracira Trigger, filters on `decision = approved`, and delivers the output.
+The typical human-in-the-loop pattern uses two workflows: workflow A submits the output (AI step → `Check an Output`, Wait for Verdict off), and workflow B starts with the Tracira Trigger, filters on `decision = approved`, and delivers the output.
 
 ### Tracira (actions)
 
-The node supports the `Log` resource with these operations (named to match the Tracira Make app modules):
+The node supports the `Output` resource with these operations (named to match the Tracira Make app modules):
 
-- `Create a Log`: Send an AI output to Tracira and create a log for evaluation. Waits for the verdict by default; supports async (fire-and-forget) mode, callback URL with event filtering, and all standard context fields. `Project Name` and `Task Name` offer a searchable dropdown of your existing Tracira projects/tasks, or accept a new name typed manually.
-- `Get a Log`: Fetch a single log by ID.
-- `Search Logs`: List logs with filters such as status, project, task, and date range.
-- `Set a Decision`: `Approve` or `Reject` a flagged log, or `Send Back for Changes` with a comment. The comment is delivered to the downstream automation, which regenerates the output and resubmits it with the `Create a Log` operation's `Revision Of` field set to the original log ID — forming a revision chain.
-- `Flag a Log`: Flag an evaluated log for human review — for example when an end-user reports an issue with an AI response. The log re-enters the pending-review queue and notification channels fire.
-- `Upload a File`: Upload a large file (PDF, image, audio) directly to Tracira storage and get back a `key`. Use it for files over ~3 MB that exceed the request size limit; map a binary field (e.g. `data`). Supports up to 32 MB. Pass the returned `key` to the `Create a Log` operation's `Input Attachments` or `Output Attachments` field.
+- `Check an Output`: Send an AI output to Tracira and have it checked against your rules. Waits for the verdict by default; supports async (fire-and-forget) mode, callback URL with event filtering, and all standard context fields. `Project Name` and `Task Name` offer a searchable dropdown of your existing Tracira projects/tasks, or accept a new name typed manually.
+- `Get an Output`: Fetch a single output by ID.
+- `Search Outputs`: List outputs with filters such as status, project, task, and date range.
+- `Set a Decision`: record a human decision on an output.
+  - `Approve` - the workflow proceeds with the output as it stands.
+  - `Edit` - the output was wrong. Either send the corrected version (`I Have the Corrected Version`), which the workflow acts on with nothing regenerated, or a comment (`Ask the AI to Redo It`), which is delivered to the downstream automation so it regenerates the output and resubmits it with the `Check an Output` operation's `Revision Of` field set to the original output ID, forming a revision chain.
+  - `Reject` - the workflow does not proceed. Always inaction: it never means "do the opposite". To reverse a call the AI made, use `Edit` with the corrected value.
+  - `Take Over` - a human handled it outside Tracira. The task is done and the AI output went unused. Records no teaching signal, because taking over is not a judgement that the AI was wrong.
+- `Flag an Output`: Flag an already-checked output for human review, for example when an end-user reports an issue with an AI response. The output re-enters the pending-review queue and notification channels fire.
+- `Upload a File`: Upload a large file (PDF, image, audio) directly to Tracira storage and get back a `key`. Use it for files over ~3 MB that exceed the request size limit; map a binary field (e.g. `data`). Supports up to 32 MB. Pass the returned `key` to the `Check an Output` operation's `Input Attachments` or `Output Attachments` field.
 
-The `Create a Log` operation also has `Input Attachments` (files the AI received) and `Output Attachments` (media the AI produced: generated images, synthesized audio, rendered documents) fields, each with three sources: `Upload File` (send a binary field inline with the request — keep under ~3 MB), `From URL` (a publicly accessible HTTPS URL), or `Tracira Upload` (a `key` from the `Upload a File` operation, for large files). `AI Output` text is required unless an `Output Attachment` carries a media-only output.
+The `Check an Output` operation also has `Input Attachments` (files the AI received) and `Output Attachments` (media the AI produced: generated images, synthesized audio, rendered documents) fields, each with three sources: `Upload File` (send a binary field inline with the request — keep under ~3 MB), `From URL` (a publicly accessible HTTPS URL), or `Tracira Upload` (a `key` from the `Upload a File` operation, for large files). `AI Output` text is required unless an `Output Attachment` carries a media-only output.
 
-The `Create a Log` operation's optional `Action (Gate Mode)` field gates a **proposed action** on human review. When your AI decides to run something with side effects (issue a refund, delete a record), fill in the action's `Name`, a plain-language `Summary`, and optional `Parameters (JSON)`. Reviewers approve or reject the action in Tracira before your workflow executes it, and data-field rules can gate it via paths like `action.params.amount`. Combine with a `Callback URL` so the workflow runs the action only after approval.
+The `Check an Output` operation's optional `Action (Gate Mode)` field gates a **proposed action** on human review. When your AI decides to run something with side effects (issue a refund, delete a record), fill in the action's `Name`, a plain-language `Summary`, and optional `Parameters (JSON)`. Reviewers approve or reject the action in Tracira before your workflow executes it, and data-field rules can gate it via paths like `action.params.amount`. Combine with a `Callback URL` so the workflow runs the action only after approval.
 
 The node also supports the `API` resource with:
 
@@ -56,7 +60,7 @@ The node also supports the `API` resource with:
 
 ### Sync vs async
 
-By default the `Create a Log` operation **waits for the verdict** (`Wait for Verdict` is on): Tracira evaluates inline and responds with the full `{ ok, id, status, verdict, confidenceScore, explanation }` so you can branch on `status` or `verdict` in the same workflow execution. Evaluation is capped at 30 seconds.
+By default the `Check an Output` operation **waits for the verdict** (`Wait for Verdict` is on): Tracira evaluates inline and responds with the full `{ ok, id, status, verdict, confidenceScore, explanation }` so you can branch on `status` or `verdict` in the same workflow execution. Evaluation is capped at 30 seconds.
 
 Turn **Wait for Verdict** off for fire-and-forget logging: Tracira responds immediately with HTTP `202` and `{ ok, id, status: "pending" }`, then evaluates in the background. Use this for high-volume logging where you don't need the verdict inline.
 
@@ -86,9 +90,9 @@ This package is being set up against the current n8n community-node tooling and
 Typical pattern:
 
 1. Run your AI step in n8n.
-2. Send the model output to `Tracira -> Log -> Create a Log`.
+2. Send the model output to `Tracira -> Output -> Check an Output`.
 3. Branch on the returned `status`, `verdict`, or `confidenceScore`.
-4. Optionally query historic logs with `Get a Log` or `Search Logs`.
+4. Optionally query past outputs with `Get an Output` or `Search Outputs`.
 
 ## Example workflow
 
@@ -97,7 +101,7 @@ An importable example workflow is available at [examples/log-and-branch.workflow
 The example does this:
 
 1. Starts from a manual trigger.
-2. Logs an execution to Tracira.
+2. Submits an output to Tracira.
 3. Branches with an `If` node based on the returned `status`.
 
 ## Verification notes
@@ -133,7 +137,7 @@ Every node class in this package must follow the conventions that got the existi
 4. **`usableAsTool`**: set `true` on every node class, triggers included. Do NOT try to exempt the `node-usable-as-tool` rule with an eslint-disable comment: the verification scanner lints with `allowInlineConfig: false`, so disable comments are ignored and the package fails review (0.9.2 review finding). A trigger is never actually invoked as a tool, so the property is inert there, and the type only permits `true`.
 5. **Trigger nodes**: name them `<X> Trigger` / `<x>Trigger`, add `activationMessage` and `eventTriggerDescription`, keep the registration id in `getWorkflowStaticData('node')`, and make `checkExists` verify against the API (Tracira auto-prunes dead subscriptions, so a stale local id must re-register).
 6. **Register the node** in `package.json` → `n8n.nodes` (the `dist/...js` path) - the build does not do this for you.
-7. **Field naming and order**: manager-friendly labels matching the Make custom app ("Input Text", "Input Attachments", "AI Output", "Output Attachments"), ordered as the story of the log: project/task → what the AI received → what it produced → behaviour. Renaming a `displayName` is free; **never rename a parameter `name`** - that breaks existing workflows.
+7. **Field naming and order**: manager-friendly labels matching the Make custom app ("Input Text", "Input Attachments", "AI Output", "Output Attachments"), ordered as the story of the output: project/task → what the AI received → what it produced → behaviour. Renaming a `displayName` is free; **never rename a parameter `name`** - that breaks existing workflows.
 8. **Add a `default`** to every parameter object the scanner can see - including each mode object inside a resourceLocator's `modes` array (`default: ''` on the `list` and `name` modes; 0.9.2 review finding).
 9. **Verify locally** with `npm run verify` (lint + scanner ESLint + build; needs Node 22+). `npm run scan:source` alone reproduces the verification scanner's ESLint pass against the working tree - `npm run lint` does NOT match it (see PUBLISHING.md). The full published-package scan runs in CI post-publish.
 

package/dist/nodes/Tracira/Tracira.node.js

@@ -107,7 +107,7 @@ class Tracira {
             group: ['transform'],
             version: 1,
             subtitle: '={{$parameter["operation"] + ": " + $parameter["resource"]}}',
-            description: 'Log and inspect Tracira AI log data',
+            description: 'Check and inspect your AI outputs in Tracira',
             usableAsTool: true,
             codex: {
                 categories: ['Analytics'],
@@ -144,7 +144,7 @@ class Tracira {
                     noDataExpression: true,
                     options: [
                         {
-                            name: 'Log',
+                            name: 'Output',
                             value: 'log',
                         },
                         {
@@ -168,40 +168,40 @@ class Tracira {
                     },
                     options: [
                         {
-                            name: 'Create a Log',
+                            name: 'Check an Output',
                             value: 'log',
-                            action: 'Create a log',
-                            description: 'Send an AI output to Tracira and create a log for evaluation. Returns a verdict, confidence score, and explanation based on your configured rules.',
+                            action: 'Check an output',
+                            description: 'Send an AI output to Tracira and have it checked against your rules. Returns a verdict, confidence score, and explanation based on your configured rules.',
                         },
                         {
-                            name: 'Flag a Log',
+                            name: 'Flag an Output',
                             value: 'flag',
-                            action: 'Flag a log',
-                            description: 'Flag an evaluated log for human review, e.g. when an end-user reports an issue',
+                            action: 'Flag an output',
+                            description: 'Flag an already-checked output for human review, e.g. when an end-user reports an issue',
                         },
                         {
-                            name: 'Get a Log',
+                            name: 'Get an Output',
                             value: 'get',
-                            action: 'Get a log',
-                            description: 'Fetch a single log by ID, including verdict, explanation, and human decision',
+                            action: 'Get an output',
+                            description: 'Fetch a single output by ID, including verdict, explanation, and human decision',
                         },
                         {
-                            name: 'Search Logs',
+                            name: 'Search Outputs',
                             value: 'search',
-                            action: 'Search logs',
-                            description: 'Return a filtered list of logs from Tracira. Filter by status, project, task name, or date range.',
+                            action: 'Search outputs',
+                            description: 'Return a filtered list of outputs from Tracira. Filter by status, project, task name, or date range.',
                         },
                         {
                             name: 'Set a Decision',
                             value: 'setDecision',
                             action: 'Set a decision',
-                            description: 'Approve, reject, or send a flagged log back to the AI with a comment',
+                            description: 'Approve or reject an output, edit it, or record that a human took over',
                         },
                         {
                             name: 'Upload a File',
                             value: 'upload',
                             action: 'Upload a file',
-                            description: 'Upload a large file directly to Tracira storage, then attach it to a log by key',
+                            description: 'Upload a large file directly to Tracira storage, then attach it to an output by key',
                         },
                     ],
                     default: 'log',
@@ -239,7 +239,7 @@ class Tracira {
                     displayOptions: {
                         show: instructionsAnyDisplay,
                     },
-                    description: 'Must match the Project Name used in the Create a Log operation so the instructions and the logs belong together',
+                    description: 'Must match the Project Name used in the Check an Output operation so the instructions and the outputs belong together',
                     modes: [
                         {
                             displayName: 'From List',
@@ -268,7 +268,7 @@ class Tracira {
                     displayOptions: {
                         show: instructionsAnyDisplay,
                     },
-                    description: 'Must match the Task Name used in the Create a Log operation',
+                    description: 'Must match the Task Name used in the Check an Output operation',
                     modes: [
                         {
                             displayName: 'From List',
@@ -329,14 +329,14 @@ class Tracira {
                     description: 'Optional. The reviewer comment that caused this update (map the Comment from the Tracira Trigger). Shown in the Tracira dashboard as the reason this version exists.',
                 },
                 {
-                    displayName: 'Log ID',
+                    displayName: 'Output ID',
                     name: 'instructionsLogId',
                     type: 'string',
                     default: '',
                     displayOptions: {
                         show: instructionsUpdateDisplay,
                     },
-                    description: 'Optional. The Tracira log the feedback came from (map the Log ID from the Tracira Trigger).',
+                    description: 'Optional. The Tracira output the feedback came from (map the Output ID from the Tracira Trigger).',
                 },
                 {
                     displayName: 'Operation',
@@ -357,7 +357,7 @@ class Tracira {
                     default: 'call',
                 },
                 {
-                    displayName: 'Log ID',
+                    displayName: 'Output ID',
                     name: 'logId',
                     type: 'string',
                     required: true,
@@ -365,10 +365,10 @@ class Tracira {
                     displayOptions: {
                         show: getDisplay,
                     },
-                    description: 'The log ID to fetch',
+                    description: 'The output ID to fetch',
                 },
                 {
-                    displayName: 'Log ID',
+                    displayName: 'Output ID',
                     name: 'decisionLogId',
                     type: 'string',
                     required: true,
@@ -376,7 +376,7 @@ class Tracira {
                     displayOptions: {
                         show: setDecisionDisplay,
                     },
-                    description: 'The log ID to approve or reject',
+                    description: 'The output ID to approve or reject',
                 },
                 {
                     displayName: 'Decision',
@@ -397,12 +397,61 @@ class Tracira {
                             value: 'rejected',
                         },
                         {
-                            name: 'Send Back for Changes',
+                            name: 'Edit',
                             value: 'changed',
-                            description: 'Send the log back to the AI with a comment to regenerate',
+                            description: 'The output was wrong. Send the corrected version, or a comment asking the AI to redo it.',
+                        },
+                        {
+                            name: 'Take Over',
+                            value: 'handled',
+                            description: 'A human handled this outside Tracira. The task is done and the AI output went unused. Records no teaching signal.',
                         },
                     ],
-                    description: 'Approve or reject the flagged log, or send it back to the AI with a comment',
+                    description: 'Approve or reject the output, edit it, or record that a human took over. Reject always means the workflow does not proceed - it never means "do the opposite"; to reverse a call the AI made, use Edit with the corrected value.',
+                },
+                {
+                    displayName: 'How',
+                    name: 'editMode',
+                    type: 'options',
+                    required: true,
+                    default: 'redo',
+                    displayOptions: {
+                        show: {
+                            ...setDecisionDisplay,
+                            decision: ['changed'],
+                        },
+                    },
+                    options: [
+                        {
+                            name: 'I Have the Corrected Version',
+                            value: 'corrected',
+                            description: 'Send the fixed output. Nothing is regenerated, so there is no second review round.',
+                        },
+                        {
+                            name: 'Ask the AI to Redo It',
+                            value: 'redo',
+                            description: 'Send an instruction back to the AI so it can rewrite the output',
+                        },
+                    ],
+                    description: 'Send the corrected version when you already know the right answer: it is the faster path and teaches Tracira more. Ask the AI to redo it when the output needs rewriting rather than fixing.',
+                },
+                {
+                    displayName: 'Corrected Output',
+                    name: 'correctedOutput',
+                    type: 'string',
+                    typeOptions: {
+                        rows: 4,
+                    },
+                    required: true,
+                    default: '',
+                    displayOptions: {
+                        show: {
+                            ...setDecisionDisplay,
+                            decision: ['changed'],
+                            editMode: ['corrected'],
+                        },
+                    },
+                    description: 'The corrected version of the output, in the same shape the workflow submitted (plain text, or the same JSON fields). The workflow acts on this version. It arrives on the Tracira Trigger as both output and correctedOutput.',
                 },
                 {
                     displayName: 'Comment',
@@ -417,12 +466,13 @@ class Tracira {
                         show: {
                             ...setDecisionDisplay,
                             decision: ['changed'],
+                            editMode: ['redo'],
                         },
                     },
-                    description: 'The instruction sent back to the AI describing what to change. Required when Decision is Send Back for Changes. The AI should regenerate the output and resubmit it with the Create a Log operation, setting Revision Of to this log ID.',
+                    description: 'The instruction sent back to the AI describing what to change. The AI should regenerate the output and resubmit it with the Check an Output operation, setting Revision Of to this output ID.',
                 },
                 {
-                    displayName: 'Log ID',
+                    displayName: 'Output ID',
                     name: 'flagLogId',
                     type: 'string',
                     required: true,
@@ -430,7 +480,7 @@ class Tracira {
                     displayOptions: {
                         show: flagDisplay,
                     },
-                    description: 'The log ID to flag for review',
+                    description: 'The output ID to flag for review',
                 },
                 {
                     displayName: 'Reason',
@@ -443,7 +493,7 @@ class Tracira {
                     displayOptions: {
                         show: flagDisplay,
                     },
-                    description: 'Optional reason for flagging, stored as the log explanation, for example the message your end-user submitted when reporting the issue',
+                    description: 'Optional reason for flagging, stored as the output explanation, for example the message your end-user submitted when reporting the issue',
                 },
                 {
                     displayName: 'Input Binary Field',
@@ -545,7 +595,7 @@ class Tracira {
                     displayOptions: {
                         show: logOperationDisplay,
                     },
-                    description: "Optional. The text the AI received: the user's message or the prompt. Shown on the person's side of the log.",
+                    description: "Optional. The text the AI received: the user's message or the prompt. Shown on the person's side of the conversation.",
                 },
                 {
                     displayName: 'Input Attachments',
@@ -662,7 +712,7 @@ class Tracira {
                     displayOptions: {
                         show: logOperationDisplay,
                     },
-                    description: "Files the AI produced: generated images, synthesized audio, or rendered documents. Same options as Input Attachments; shown as the AI's reply in the log.",
+                    description: "Files the AI produced: generated images, synthesized audio, or rendered documents. Same options as Input Attachments; shown as the AI's reply in the conversation.",
                     options: [
                         {
                             name: 'attachment',
@@ -850,7 +900,7 @@ class Tracira {
                             name: 'instructionsVersion',
                             type: 'number',
                             default: 0,
-                            description: 'Optional. The Version returned by the Get Instructions operation. The log then links back to the exact instructions the AI ran with, and reviewers can open them from the log.',
+                            description: 'Optional. The Version returned by the Get Instructions operation. The output then links back to the exact instructions the AI ran with, and reviewers can open them from the output.',
                         },
                         {
                             displayName: 'Latency',
@@ -859,12 +909,6 @@ class Tracira {
                             default: 0,
                             description: 'Duration of the AI call in milliseconds',
                         },
-                        {
-                            displayName: 'Log ID',
-                            name: 'id',
-                            type: 'string',
-                            default: '',
-                        },
                         {
                             displayName: 'Metadata JSON',
                             name: 'metadataJson',
@@ -873,14 +917,20 @@ class Tracira {
                                 rows: 4,
                             },
                             default: '',
-                            description: 'Optional JSON object to store as log metadata',
+                            description: 'Optional JSON object to store as output metadata',
+                        },
+                        {
+                            displayName: 'Output ID',
+                            name: 'id',
+                            type: 'string',
+                            default: '',
                         },
                         {
                             displayName: 'Revision Of',
                             name: 'revisionOf',
                             type: 'string',
                             default: '',
-                            description: 'The original log ID when this output is a regeneration triggered by a Changed decision. Tracira links the two as a revision chain so reviewers see every attempt.',
+                            description: 'The original output ID when this submission is a regeneration triggered by a Changed decision. Tracira links the two as a revision chain so reviewers see every attempt.',
                         },
                         {
                             displayName: 'Session ID',
@@ -899,7 +949,7 @@ class Tracira {
                             name: 'timestamp',
                             type: 'dateTime',
                             default: '',
-                            description: 'Optional. Override the log timestamp — useful when replaying or reprocessing past executions. Leave blank to use the current time.',
+                            description: 'Optional. Override the output timestamp: useful when replaying or reprocessing past executions. Leave blank to use the current time.',
                         },
                     ],
                 },
@@ -918,7 +968,7 @@ class Tracira {
                         { name: 'Pass', value: 'pass' },
                         { name: 'Pending', value: 'pending' },
                     ],
-                    description: 'Filter logs by status',
+                    description: 'Filter outputs by status',
                 },
                 {
                     displayName: 'Project Name',
@@ -928,7 +978,7 @@ class Tracira {
                     displayOptions: {
                         show: getAllDisplay,
                     },
-                    description: 'Optional. Filter logs to a specific project name.',
+                    description: 'Optional. Filter outputs to a specific project name.',
                     modes: [
                         {
                             displayName: 'From List',
@@ -956,7 +1006,7 @@ class Tracira {
                     displayOptions: {
                         show: getAllDisplay,
                     },
-                    description: 'Optional. Filter logs to a specific task name within a project.',
+                    description: 'Optional. Filter outputs to a specific task name within a project.',
                     modes: [
                         {
                             displayName: 'From List',
@@ -994,7 +1044,7 @@ class Tracira {
                     displayOptions: {
                         show: getAllDisplay,
                     },
-                    description: 'Only include logs at or after this date',
+                    description: 'Only include outputs at or after this date',
                 },
                 {
                     displayName: 'To Date',
@@ -1004,7 +1054,7 @@ class Tracira {
                     displayOptions: {
                         show: getAllDisplay,
                     },
-                    description: 'Only include logs up to this date',
+                    description: 'Only include outputs up to this date',
                 },
                 {
                     displayName: 'Limit',
@@ -1312,11 +1362,20 @@ class Tracira {
                 else if (resource === 'log' && operation === 'setDecision') {
                     const logId = this.getNodeParameter('decisionLogId', itemIndex);
                     const decision = this.getNodeParameter('decision', itemIndex);
-                    const comment = decision === 'changed'
+                    const editMode = decision === 'changed'
+                        ? this.getNodeParameter('editMode', itemIndex, 'redo')
+                        : '';
+                    const comment = editMode === 'redo'
                         ? this.getNodeParameter('comment', itemIndex, '')
                         : '';
-                    if (decision === 'changed' && !comment.trim()) {
-                        throw new n8n_workflow_1.NodeOperationError(this.getNode(), 'Comment is required when Decision is Send Back for Changes', { itemIndex });
+                    const correctedOutput = editMode === 'corrected'
+                        ? this.getNodeParameter('correctedOutput', itemIndex, '')
+                        : '';
+                    if (editMode === 'redo' && !comment.trim()) {
+                        throw new n8n_workflow_1.NodeOperationError(this.getNode(), 'Comment is required when you ask the AI to redo the output', { itemIndex });
+                    }
+                    if (editMode === 'corrected' && !correctedOutput.trim()) {
+                        throw new n8n_workflow_1.NodeOperationError(this.getNode(), 'Corrected Output is required when you send the corrected version', { itemIndex });
                     }
                     requestOptions = {
                         method: 'PATCH',
@@ -1324,6 +1383,7 @@ class Tracira {
                         body: stripEmpty({
                             decision,
                             comment: comment || undefined,
+                            correctedOutput: correctedOutput || undefined,
                         }),
                     };
                 }