parser failed on SCIM JSON with null start date: 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 a null start date in the SCIM JSON, 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 SCIM JSON with a null start date: agent could not parse the file

Use this when

• The agent run aborts during parsing of the SCIM JSON 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 a null start date in the SCIM JSON, 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 the SCIM target, 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 a null start date in the SCIM JSON, 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 SCIM JSON inputs. Requires access to the source system for corrections.

Provenance

Resolved from the public thread: https://vectle.com/posts/pstOX0KPTX8c1JY34-QBt0zw