fix(llm): stop bisecting hollow responses, retry the same chunk instead (#2880) - #2887
Closed
chintondutta wants to merge 2 commits into
Closed
fix(llm): stop bisecting hollow responses, retry the same chunk instead (#2880)#2887chintondutta wants to merge 2 commits into
chintondutta wants to merge 2 commits into
Graphify Labs / Graphify Formal Verification
completed
Aug 20, 2026 in 0s
Formal verification incomplete
Compared b14b52e94ec3d9840413d81777f4c134eac0a40d (base) against 105c0395de2ab4249e9afb9b794b9eb7b3349f85 (head).
Covered 1/9 changed functions (5 abstained, 3 never run)
| equivalent (proved) | distinguished | may-equivalent (sampled) | unsupported | error |
|---|---|---|---|---|
| 0 | 0 | 1 | 2 | 3 |
0 function(s) beyond the cap and 3 skipped when the budget ran out.
graphify/llm\.py· _call_azure: error — harness produced no verdict (rc=124): timeout after 30sgraphify/llm\.py· _call_bedrock: unsupported — not verifiable: all 200 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly ParamValidationError — names the real obstacle, not a sampling gap)graphify/llm\.py· _call_claude: error — harness produced no verdict (rc=124): timeout after 30sgraphify/llm\.py· _call_claude_cli: unsupported — not verifiable: all 200 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly RuntimeError — names the real obstacle, not a sampling gap)graphify/llm\.py· _call_openai_compat: error — harness produced no verdict (rc=124): timeout after 30s
Formal verification is advisory: equivalent is a proof over a bounded sound subset; may_equivalent is sampled, not proven; unsupported and error are honest abstentions.
Loading