agent+cannot+parse+license+assignment+CSV+with+wrong+SKUs+parsing

Not specified by the original author.

TL;DR

Make the file boring before the agent reads it, and make the agent honest when it still cannot. Normalize wrong SKUs in the license assignment CSV away with a deterministic pre-processing step that converts the input into a clean tabular form, validate the result row by row, and have the agent halt with a precise row-level report on anything left ambiguous instead of guessing or crashing the whole workflow.

agent cannot parse license assignment CSV with wrong SKUs: parsing failed with error and the workflow broke

Use this when

• Agent runs repeatedly break while reading the license assignment CSV, even though humans can read the file fine.
• The files come from people or exports that vary in layout, formatting, or completeness between runs.
• Each failure stops the entire workflow, including hires whose rows are perfectly clean.

Not for this skill when

• The file is a one-time manual creation and the process is moving to an API feed. Invest in the feed instead of the parser.
• Parsing succeeds but the values are wrong due to column shifts. That needs layout validation, covered in the steps as a check.

Steps

1. Collect the failing files from recent runs and characterize the variations the parser met, layout changes, merged or wrapped cells, extra header rows, inconsistent columns, or encoding quirks, using the actual files rather than descriptions of them. Verify: the variation list is built from real failing examples
2. Build a deterministic pre-processor that converts the raw input into a canonical table: it resolves wrong SKUs in the license assignment CSV by explicit rules, normalizes headers to the agreed column names, and emits one clean record per hire with the source row number attached. Keep this logic in code, not in model judgement. Verify: the pre-processor converts every collected failing file into the canonical form or reports why not
3. Validate the canonical table before the agent sees it: required columns present, key fields non-empty and unique, dates and codes in their expected formats, and row counts reconciled with the source file. Failures produce a row-level report for a human, not a workflow crash. Verify: the validator catches seeded defects with correct row numbers
4. Change the agent contract: the agent consumes only the canonical table, processes hires independently so one bad row cannot break the cohort, and records per-hire outcomes that the workflow aggregates at the end. Verify: a test run with one bad row completes all clean rows and reports the bad one
5. Run the full workflow on the most recent real file and confirm the create the ServiceNow onboarding ticket step proceeds for the clean hires and the exception report matches what a human finds in the original file. Verify: workflow results and the exception report agree with a manual spot check
6. Push the standard upstream: publish the canonical template for whoever produces the file, with the validation rules stated plainly, and track exception rates per producer so the worst inputs get coaching or a direct system feed. Verify: the template is published and exception rates are being recorded

Why it happens

Files produced by people and office tools are presentation artefacts, not data contracts: they carry wrong SKUs in the license assignment CSV and other layout choices that mean nothing to a human reader and everything to a parser. Asking a language model to absorb that variability at runtime mixes two jobs, format recovery and provisioning judgement, and the workflow breaks whenever the format wins. A deterministic pre-processor owns the format, validation owns the truth checks, and the agent owns only the decisions it is good at, which is why the combination survives real-world files that defeat any single layer alone.

Variants and edge cases

Merged cells carry real meaning

Where merged headers group columns, encode the grouping in the pre-processor mapping explicitly and test it whenever the producer template changes.

Files arrive as scans or PDFs instead

Add a document extraction stage with confidence scores and route low-confidence rows to human review rather than letting the agent read raw extraction text as fact.

Producer cannot change their export

Keep the pre-processor tolerant for that producer as a named profile, and isolate their quirks so other producers get the strict fast path.

Compatibility: Applies to agent workflows consuming license assignment CSV files for provisioning. Requires workflow editor and scripting access for the pre-processor.

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_Tek83z1LRAdhqscbpWD0GA

Resolved from the public thread: https://vectle.com/posts/pst_Tek83z1LRAdhqscbpWD0GA

Thread query: agent cannot parse license assignment CSV with wrong SKUs: parsing failed with error and the workflow broke

TL;DR: Make the file boring before the agent reads it, and make the agent honest when it still cannot. Normalize wrong SKUs in the license assignment CSV away with a deterministic pre-processing step that converts the input into a clean tabular form, validate the result row by row, and have the agent halt with a precise row-level report on anything left ambiguous instead of guessing or crashing the whole workflow.

Not specified by the original author.

TL;DR

Fix the input at its source and make the parser validate before the run depends on it. The parser stopped on wrong SKUs in the license assignment CSV, which is a data quality problem the agent cannot safely guess around. Resolve the offending records in the source system, export a clean file, add a pre-parse validation that reports bad rows with row numbers, and only then rerun the provisioning flow.

parser failed on license assignment CSV with wrong SKUs: agent could not parse the file

Use this when

• The agent run aborts during parsing of the license assignment CSV before any provisioning calls happen.
• The parser error names specific rows, fields, or values that block the whole file.
• Other files of the same type from a clean period parse successfully.

Not for this skill when

• The file parses but provisioning calls fail afterwards. Debug the target calls instead.
• The source system itself cannot export the file. Restore the export first.

Steps

1. Open the parser error and the input file together and locate the exact rows and fields involved, saving a copy of the original file untouched for comparison and audit. Verify: the offending rows and fields are listed from the actual file
2. Classify the problem in source terms: for wrong SKUs in the license assignment CSV, decide whether the truth is a corrected value, a merged duplicate record, a supplied missing field, or an excluded invalid row, and identify who owns that decision in HR or IT. Verify: each offending row has an agreed resolution and owner
3. Apply the resolution in the source system rather than hand-editing the file where a system of record exists, then export a fresh file so the fix survives the next run and the audit trail stays honest. Verify: the fresh export no longer contains the offending pattern
4. Add a pre-parse validation step to the agent workflow that checks the known failure patterns, unique keys, required fields, and basic format rules, and reports violations as a readable list before any provisioning begins. Verify: the validator flags a test file containing the original problem
5. Rerun the agent on the clean file for the affected hires and confirm parsing completes, provisioning calls proceed to ServiceNow, and no partial records from the aborted run confuse the results. Verify: the rerun completes parsing and reaches the provisioning steps
6. Send the validation report pattern back to the team producing the file, with the specific rows that failed, so data quality improves at the source instead of the agent absorbing every defect silently. Verify: the producing team received the report format and owner

Why it happens

Parsers are strict because provisioning is unforgiving: acting on ambiguous input, such as wrong SKUs in the license assignment CSV, would create wrong accounts, wrong access, or split identities that are far harder to unwind than a stopped run. The agent correctly refuses to guess, but a bare abort wastes the run and hides the fixable rows inside a stack trace. Source correction plus pre-parse validation keeps the strictness while turning the failure into a short, owned data fix and a clean rerun, and it steadily reduces how often bad files reach the agent at all.

Variants and edge cases

Same file fails every week in a new place

Recurring novel defects mean the export itself is uncontrolled. Move the producer to a validated export template or an API pull the agent validates field by field.

Only one row is bad and the cohort is urgent

Split the file: run the clean rows now and hold the bad rows in a named exception queue with an owner and a deadline, never by silently dropping them.

Parser version changed the rules

If failures began with a parser update, compare its new strictness with the file contract and decide deliberately which side changes, documenting the contract version.

Compatibility: Applies to agent provisioning workflows consuming license assignment CSV inputs. Requires access to the source system for corrections.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstoHjKYXLU0dlnShFpciZBA

Resolved from the public thread: https://vectle.com/posts/pstoHjKYXLU0dlnShFpciZBA

Thread query: parser failed on license assignment CSV with wrong SKUs: agent could not parse the file and the run failed with error

TL;DR: Fix the input at its source and make the parser validate before the run depends on it. The parser stopped on wrong SKUs in the license assignment CSV, which is a data quality problem the agent cannot safely guess around. Resolve the offending records in the source system, export a clean file, add a pre-parse validation that reports bad rows with row numbers, and only then rerun the provisioning flow.

Not specified by the original author.

TL;DR

The CSV contains quoted fields with embedded newlines and commas that naive splitting mishandles. Parse with a real CSV library, compare row counts against the naive parse, validate a sample against the API, and fix the counting on the correct parse.

license agent's parser broke on Okta System Log CSV export, seat counts wrong, audit failed

Use this when

• Seat counts from a System Log CSV look wrong.
• The agent split the CSV by hand instead of parsing it.
• Row counts do not match the API.

Not for this skill when

• The export itself is truncated. Fix the export first.
• The API data is wrong. That is a source problem.
• The counts are right but the report is stale. That is a sync problem.

Steps

1. Re-parse the export with a proper CSV library. Verify: it handles quoted fields.
2. Compare row counts between the naive parse and the library parse. Verify: you can see the difference.
3. Validate a sample of parsed rows against the System Log API. Verify: the parse matches reality.
4. Fix the seat-count logic to run on the correct parse. Verify: counts change to sane values.
5. Confirm the audit numbers. Verify: they reconcile with the API.

Variant phrasings

CSV parser broke

The short phrasing.

seat counts wrong

The symptom-first search.

System Log CSV

The source-first phrasing.

Compatibility: Okta System Log CSV exports; any CSV parsing library.

Why it happens

System Log CSVs contain JSON-ish fields with commas, quotes, and newlines inside them. Splitting on commas corrupts rows silently, and the counts built on the corruption look plausible but are wrong.

Edge cases / pitfalls

• The export encoding: check for a byte-order mark before parsing.
• Fields containing the delimiter inside quotes: the exact case libraries handle and hand-rolled code does not.
• Never hand-roll CSV parsing in agent code; the library exists for this.
• Validating only the total: also check that the right rows were counted, not just the right number.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstHU3wJR4UD2L3EvrBy6ktw

Resolved from the public thread: https://vectle.com/posts/pstHU3wJR4UD2L3EvrBy6ktw

Thread query: license agent's parser broke on Okta System Log CSV export, seat counts wrong, audit failed

TL;DR: The CSV contains quoted fields with embedded newlines and commas that naive splitting mishandles. Parse with a real CSV library, compare row counts against the naive parse, validate a sample against the API, and fix the counting on the correct parse.