[mohammadatallah-scale]

Important

Pending Mohammad's self-review. This note is removed by a human, not automation.

The problem. Offline failure checks read attributes that an agent declares on its spans, and AgentEx agents have to hand-build every key with nothing checking the values (OVE-1375). They also cannot recognise a successful harness tool call or decode an object result from the OpenAI hooks.

The fix. A helper that writes and validates those attributes from one spec. The scale-gp-beta port is scaleapi/sgp-dev-python-staging#10.

• Spec: one validated object writes the root span's declarations as flat attribute keys, with the output schema as JSON text that is checked again when it renders.
• Per-span helpers: one call each for a required output, a verification result and an escalation, passed as a span's data.
• Tool spans: harness tool spans carry gen_ai.operation.name and gen_ai.tool.name, and the OpenAI hooks record object results as JSON.

Test plan

• Same results and error messages as the scale-gp-beta port over 160,000 generated inputs, including schema edits made after construction and random non-string keys.
• The failure checks' own span reader (OVE-1371 branch) reads Claude Code and Codex tool spans, passed or failed, as tool calls and decodes an object OpenAI result.
• gap: not exported to a live SGP spans API from an AgentEx agent, the span request tests cover the payload and the port's dev-sgp round trip covers the store.
• gap: a traced example whose spans pass the failure checks is not shown here, the end-to-end harness in OVE-1400 proves it.

🤖 Generated with Claude Code

Confidence Score: 5/5

The PR appears safe to merge; no new blocking issues were found.

Summary

Adds validated helpers for failure-check attributes and exposes them through the ADK.

• Agents can add checked failure-check details to their trace spans.
• Tool spans now identify their operation and tool name.
• OpenAI tool spans record structured results as JSON text.

No new actionable issues were found. The earlier unnumbered finding is fixed: the deep-schema test now uses NESTING_DEPTH_PAST_RECURSION_LIMIT.

_{Reviews (5) · Last reviewed commit: "fix(tracing): record non-string OpenAI t..." · Reviewed by Greptile}

[mohammadatallah-scale]

P3 tests/lib/core/tracing/test_failure_attributes.py:154 - the "error names the attribute" contract is pinned only for step_budget, stop_reason and prompt_version. Relabelling escalation_channels as quote_arguments in _NORMALIZERS, or renaming the required_outputs, verification and VerificationRule labels, leaves all 118 tests green.
P3 failure_attributes.py:89 - json.dumps coerces non-string keys, so output_schema={1: "a", "1": "b"} is accepted and silently stored as {"1": "b"} instead of being rejected.

Refuted: __agent_version__ and __commit_sha__ README claims hold at this head (_add_source_to_span, code_revision), and the port's logic matches line for line apart from 3.9 syntax.

[mohammadatallah-scale]

P3 Follow-up: the attribute-naming pins landed in 815dad0, and each label swap above now fails 2 to 11 tests. The non-string key coercion is left open because fixing it changes behavior the scale-gp-beta port must match, so both helpers need it together.