[BUG] Brand font validation accepts prohibited fonts when an approved fallback is present
#939
[BUG] DCF valuation reuses old cash flows after set_assumptions changes the model
#936
[BUG] Tornado analysis raises ZeroDivisionError for a zero baseline output
#935
[BUG] Ratio trend analysis labels all changes from a zero baseline as Stable
#933
[BUG] Scenario analysis carries inputs between scenarios and returns order-dependent results
#931
[BUG] Breakeven analysis silently returns the wrong boundary for decreasing outputs
#929
[BUG] Brand validator rejects approved palette colors in RGB and shorthand hex
#912
[DOCS] Refresh supported models in the memory cookbook
#911
[BUG] Notebook structure CI succeeds without validating notebooks
#906
[BUG] patterns/agents/util.py and 15 other files: temperature= raises TypeError on anthropic 1.x
#891
BUG REPORT — Self-filed, no sugarcoating
1
#863
[BUG] claude_agent_sdk/05_Building_a_session_browser.ipynb, cell 14: message renderer prints the user's prompt as blank whenever `content` is a string
#862
[BUG] fable_5_fallback_billing/guide.ipynb, cell 14: `betas=betas or None` raises TypeError when there's no fallback credit token
#861
[PROPOSAL] Cookbook: narrowing a sub-agent's tools at the handoff
#855
`misc/building_evals.ipynb`: model-based grader uses the ineffective “reason first, verdict second” ordering, with a stray `=` also present in the prompt.
#854
tool_use/tool_choice.ipynb: the {"type": "any"} SMS bot is a hard 400 on Claude Fable 5.1
#845
Cookbook idea: a portable-eval-format example alongside evals/ and tool_evaluation/
1
#838
agents.md
#837
orchestrator_workers.ipynb: context dict is silently dropped from prompts
1
#830
Memory store never mounts in deployment-created sessions — CMA memory cookbook pattern breaks under scheduled deployments
1
#826
[PROPOSAL] Evaluate Traditional Chinese content with structured outputs
1
#798
Recipe: turn a bad prompt into a great one — automatic prompt scoring + repair with Claude
#797
Related eval: REFUTE scientific critique + calibration benchmark
#779
Cookbook idea: research agents with BGPT scientific evidence MCP
