Merge pull request #17 from laharikarumanchi-AI-ML/restore/groq-400-fix

Merge pull request #15 from laharikarumanchi-AI-ML/feat/auto-dotenv

docs(llm): note tool_use_failed retry exception in chat_with_tools docstring

fix(llm): retry Groq HTTP 400 with code=tool_use_failed

fix(orchestrator): omit assistant `content` field when None alongside tool_calls

fix(llm): log response body on Groq HTTP error before raising

feat(env): auto-load .env at CLI + eval entry points (no more `source .env`)

chore: remove unused imports across multitool/ and tests/

Revert "docs(llm): note tool_use_failed retry exception in chat_with_tools do…"

Revert "fix(llm): retry Groq HTTP 400 tool_use_failed (real root cause of 36% eval crashes)"

docs(llm): note tool_use_failed retry exception in chat_with_tools docstring

fix(llm): retry Groq HTTP 400 with code=tool_use_failed

fix(orchestrator): omit assistant `content` field when None alongside tool_calls

fix(llm): log response body on Groq HTTP error before raising

fix(cli): treat --trace PATH as directory, always (avoid silent trace loss)

fix(cli): drop dead max-steps partial-answer branch + correct test contract

feat(cli): add multitool ask subcommand with argparse

fix(eval): regex truncation, tolerance=None crash, empty-queries crash

feat(eval): run.py harness with per-task checkpointing

feat(eval): scorer with first-float-in-string heuristic

feat(eval): 25-query hand-curated test set, balanced across 5 categories

fix(agent): code-review polish — I-1, I-2 + 4 minor improvements

feat(agent): Orchestrator.run() — main function-calling loop

feat(agent): _dispatch_with_retry with 2-attempt budget

feat(agent): Orchestrator + AgentResult skeleton

feat(agent): Trace — JSON logger flushed after every step

feat(agent): system prompt for the orchestrator

fix(llm): code-review polish — C1 + I1-I5 from PR #5 reviewer

feat(llm): GeminiClient.chat_with_tools() with synthesized call IDs

feat(llm): GroqClient.chat_with_tools() — function-calling API

feat(llm): extend LLMClient Protocol with chat_with_tools()

feat(llm): ToolCall + ToolResponse dataclasses

feat(llm): copy LLMClient from DA Agent + attribution header

fix(tools): code-review polish — 4 fixes from PR #4 reviewer

feat(tools): wikipedia (first-N-sentences of article summary)

feat(tools): unit_convert (pint-based)

feat(tools): datetime_tool (years_between / add_years / day_of_week)

feat(tools): calculator (numexpr-based)

fix(tools): code-review polish — None-safety, error convention, test cleanup

feat(tools): tavily_search with mocked tests

feat(tools): @tool docstring required + optional params excluded from required

feat(tools): @tool decorator with auto-generated JSON Schema

feat(tools): _py_to_json_type handles Optional[X] / X | None

feat(tools): _py_to_json_type for primitive types (str/int/float/bool)

feat(scaffold): package skeleton + smoke test