posit-dev/chatlas

View on GitHub

Your friendly guide to building LLM chat apps in Python with less effort and more clarity.

Stars: 176
Forks: 28
Open beginner issues: 0
Indexed issues: 50
Avg merge: 18h 42m
Merged PRs (30d): 16

Dominant language: Python
License: MIT
Last GitHub push: Sep 13, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

50 open issues indexed

A streaming text delta that repeats everything streamed so far is missing from the recorded turn Open

ai-triage:done Priority: Medium

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

posit-dev/chatlas#435 · Opened Sep 14, 2026
Back ChatSnowflake() with the Cortex REST API: thin Anthropic/OpenAI provider subclasses, model-name dispatch, credentials-callable auth Open

ai-triage:done Priority: Medium

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#432 · 2 comments · Opened Sep 11, 2026
tool_context() equivalent: per-conversation store and tool-calling context Open

ai-triage:done Priority: Low

Difficulty 4/5 3-5 days Newbie friendliness 52/100

posit-dev/chatlas#425 · 1 comment · Opened Sep 4, 2026
No easy way to reuse an uploaded file from its id Open

ai-triage:done Priority: Low

Difficulty 3/5 1-2 days Newbie friendliness 65/100

posit-dev/chatlas#417 · 1 comment · Opened Sep 2, 2026
Bedrock providers ignore AWS_ENDPOINT_URL_BEDROCK_RUNTIME env var Open

ai-triage:done Priority: Low

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

posit-dev/chatlas#415 · Opened Sep 2, 2026
Anthropic provider drops empty assistant turns, breaking role alternation Open

ai-triage:done Priority: Medium

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

posit-dev/chatlas#416 · Opened Sep 2, 2026
OpenAI provider incorrectly maps params(top_k=) to top_logprobs Open

ai-triage:done Priority: Medium

Difficulty 3/5 1-2 days Newbie friendliness 72/100

posit-dev/chatlas#412 · Opened Sep 2, 2026
Add on_request_start() / on_request_end() hooks to Chat Open

ai-triage:done Priority: Low

Difficulty 4/5 3-5 days Newbie friendliness 68/100

posit-dev/chatlas#413 · 1 comment · Opened Sep 2, 2026
`ChatBedrock()` mantle APIs: default model isn't served, and cross-region prefix isn't stripped from requests Open

ai-triage:done Priority: Medium

Difficulty 3/5 1-2 days Newbie friendliness 68/100

posit-dev/chatlas#411 · Opened Sep 1, 2026
`ChatBedrock()` mantle APIs send URL content sources, which Bedrock rejects Open

ai-triage:done Priority: Medium

Difficulty 3/5 1-2 days Newbie friendliness 72/100

posit-dev/chatlas#410 · Opened Sep 1, 2026
feat(pricing): refresh bundled prices and consider an explicit user update API Open

ai-triage:done Priority: Low

Difficulty 4/5 3-5 days Newbie friendliness 55/100

posit-dev/chatlas#395 · Opened Aug 19, 2026
feat: expose logical conversation rounds over flat turn history Open

ai-triage:done Priority: Low

Difficulty 5/5 Over a week Newbie friendliness 45/100

posit-dev/chatlas#394 · Opened Aug 19, 2026
Anthropic document_index citations don't account for documents embedded in custom tool results Open

ai-triage:done Priority: Low

Difficulty 3/5 1-2 days Newbie friendliness 68/100

posit-dev/chatlas#381 · Opened Aug 8, 2026
Tracking: expand first-class built-in (provider-executed) tools Open

ai-triage:needs-review

Difficulty 5/5 Over a week Newbie friendliness 25/100

posit-dev/chatlas#369 · Opened Jul 29, 2026
Scope decision: file search / provider-hosted RAG as a built-in tool? Open

ai-triage:needs-review

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#366 · Opened Jul 29, 2026
feat: server-side MCP connector as a built-in tool Open

ai-triage:needs-review

Difficulty 5/5 Over a week Newbie friendliness 30/100

posit-dev/chatlas#365 · Opened Jul 29, 2026
feat: tool_code_execution() — provider-executed code execution Open

ai-triage:needs-review

Difficulty 5/5 Over a week Newbie friendliness 25/100

posit-dev/chatlas#364 · Opened Jul 29, 2026
Tracking: competitive review workstreams (July 2026) Open

ai-triage:needs-review

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#360 · Opened Jul 29, 2026
feat: usage guards (max tool calls / cost budget) for the tool-calling loop Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#359 · Opened Jul 29, 2026
Lean into provider-native caching (explicit Gemini context caching, docs, visibility) Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#358 · Opened Jul 29, 2026
History compaction: chat.compact() Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#356 · 1 comment · Opened Jul 29, 2026
feat: structured-output repair loop on validation failure Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#357 · Opened Jul 29, 2026
Docs: finish and expand why-chatlas.qmd Open

ai-triage:needs-review documentation

Difficulty 4/5 3-5 days Newbie friendliness 52/100

posit-dev/chatlas#355 · Opened Jul 29, 2026
Docs: "Chat as a tool" multi-agent delegation recipe Open

ai-triage:needs-review documentation

Difficulty 2/5 1-2 days Newbie friendliness 76/100

posit-dev/chatlas#354 · Opened Jul 29, 2026
feat: retry with backoff and opt-in model fallback Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#353 · Opened Jul 29, 2026
Scope decision: thin embed() helper, or explicit non-goal? Open

ai-triage:needs-review question

Difficulty 5/5 Over a week Newbie friendliness 30/100

posit-dev/chatlas#351 · Opened Jul 29, 2026
Conversation persistence: chat.save() / Chat.load() (+ optional local conversation log) Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 48/100

posit-dev/chatlas#352 · Opened Jul 29, 2026
Scope decision: minimal CLI for one-off scripted prompts? Open

ai-triage:needs-review enhancement question

Difficulty 5/5 Over a week Newbie friendliness 25/100

posit-dev/chatlas#350 · Opened Jul 29, 2026
Prompt "profiles": serializable bundles of system prompt + tools + schema Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#349 · Opened Jul 29, 2026
Deferred (async) tool approval: pause a turn and resume later Open

ai-triage:needs-review enhancement

Difficulty 5/5 Over a week Newbie friendliness 38/100

posit-dev/chatlas#348 · Opened Jul 29, 2026
Support configuring context window size (`num_ctx`) for local models in `ChatOllama` Open

ai-triage:done Priority: Medium

Difficulty 4/5 3-5 days Newbie friendliness 52/100

posit-dev/chatlas#327 · 1 comment · Opened Jul 8, 2026
feature: Add llms-full.txt Open

Priority: Low

Difficulty 3/5 1-2 days Newbie friendliness 65/100

posit-dev/chatlas#309 · Opened May 12, 2026
When provider_model is not provided, ChatAuto should look for known environment variables to select a default provider Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

posit-dev/chatlas#266 · Opened Jan 15, 2026
Translate Inspect solvers into chatlas Open

ai-triage:needs-review needs clarification Priority: Low

Difficulty 4/5 3-5 days Newbie friendliness 25/100

posit-dev/chatlas#235 · 3 comments · Opened Nov 21, 2025
Support MCP Prompts and Resources Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

posit-dev/chatlas#220 · 2 comments · 1 reaction · Opened Nov 7, 2025
Feature request: Consider exposing extra API headers as argument Open

Difficulty 3/5 1-2 days Newbie friendliness 52/100

posit-dev/chatlas#190 · 8 comments · Opened Oct 13, 2025
Set tool annotations by decorating the tool function, not in `chat.register_tool()` Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

posit-dev/chatlas#170 · 4 comments · Opened Sep 4, 2025
Can't list ollama models without providing a `model` Open

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

posit-dev/chatlas#166 · Opened Aug 31, 2025
Minor documentaiton improvements Open

posit-dev/chatlas#153 · 1 assignee · Opened Aug 20, 2025
Allow passing env vars to stdio MCP tools Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

posit-dev/chatlas#139 · 2 comments · Opened Aug 6, 2025
Add `content_ephemeral()` Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

posit-dev/chatlas#136 · Opened Jul 16, 2025
feat: more export types: dataframe, csv, string Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

posit-dev/chatlas#121 · Opened Jun 25, 2025
Wrap a chatlas bot inside a FastAPI instead of Shiny Open

documentation Priority: Low

Difficulty 5/5 Over a week Newbie friendliness 25/100

posit-dev/chatlas#109 · 2 comments · Opened Jun 19, 2025
Chatlas in a shinyapp: How to specify an uploaded file as the tool argument? Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

posit-dev/chatlas#104 · 3 comments · Opened Jun 4, 2025
Do strict type checking Open

Difficulty 1/5 Under an hour Newbie friendliness 55/100

posit-dev/chatlas#53 · Opened Feb 18, 2025
Add configuration options for method description when registering tools Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

posit-dev/chatlas#35 · 1 comment · Opened Jan 15, 2025
Conditional flow with tool calls Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

posit-dev/chatlas#33 · 13 comments · Opened Jan 13, 2025
feat: Update and submit user value Open

Difficulty 3/5 1-2 days Newbie friendliness 42/100

posit-dev/chatlas#32 · 1 comment · Opened Jan 9, 2025
`content_image_url` throws error in local vision model Open

Difficulty 3/5 1-2 days Newbie friendliness 38/100

posit-dev/chatlas#20 · 1 comment · 1 reaction · Opened Dec 13, 2024
Make it easier to impose limits on conversation size. Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

posit-dev/chatlas#8 · Opened Nov 15, 2024

posit-dev/chatlas

Get new issues in your inbox