Skip to content
CAI
Software that uses CAICheck a score

agentjido/req_llm

53.8

Adequate · 15 November 2026

82.9k

lines of production code

Elixir

primary language

5

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Added PR review and hardening agent skills with BEAM toolchain setup

The .agents directory now includes configuration for automated pull request management. A new 'pr-review' skill enables agents to analyze PRs for code quality, test coverage, and merge conflicts, updating labels to 'ready\_to\_merge' or 'needs\_work' based on findings. A complementary 'pr-harden' skill allows agents to actively fix blocking issues on PR branches and strengthen test coverage. Additionally, setup and resume scripts have been added to install and verify the Erlang/OTP and Elixir toolchain, ensuring the environment is ready for BEAM-based project operations.

.agents · high confidence

Initial configuration for LLM provider catalog and request timeouts

This change introduces the foundational configuration files for the application, establishing a model catalog via \llm\_db\ that defines allowed and denied models for various providers (such as OpenAI, Anthropic, and Google) and sets default request and stream timeouts in \req\_llm\. It also configures development-specific git hooks for commit message checking and code formatting, ensuring consistent development workflows.

config · high confidence

New ReqLLM Agent tutorial series

Added a comprehensive 14-chapter tutorial series in the tutorial/agents directory that demonstrates building LLM agents with ReqLLM. The examples progress from basic synchronous text generation to advanced patterns including tool calling loops, streaming responses, OTP GenServer architectures (phased execution), memory management with sliding windows, interactive CLI REPLs, usage logging, and resilient tool execution using Tasks, parallel execution via Task.Supervisor, and exponential backoff retries.

tutorial · high confidence

New ReqLLM CLI tasks for generation, compatibility, and diagnostics

This release introduces several new Mix tasks to the \lib/mix\ directory. \mix req\_llm.gen\ provides a unified command for generating text or structured JSON objects from various AI models, supporting streaming and non-streaming modes. \mix req\_llm.model\_compat\ allows users to validate model coverage using fixture-based testing, with options to filter by provider, operation type, and support tiers. \mix req\_llm.model\_support\ inspects or generates evidence-backed model support tiers, helping users understand which models are first-class, best-effort, or experimental. \mix req\_llm.provider\_drift\ runs bounded live provider drift verification to detect changes in provider behavior. \mix req\_llm.doctor\ diagnoses installation and runtime configuration issues. \mix req\_llm.install\ simplifies setting up ReqLLM in an application using Igniter. \mix req\_llm.migration\_audit\ scans source code for V2 migration patterns. Finally, \mix test.livebooks\ validates Livebook documentation files by checking their Elixir code blocks for syntax errors or execution failures.

lib/mix · high confidence

New ReqLLM examples project with agent demo and interactive playground

A new nested Mix project in the \examples/\ directory provides runnable demonstrations of ReqLLM capabilities. It includes an interactive agent demo (\demo.exs\) that showcases streaming text generation, tool calling (calculator and web search), and conversation history maintenance. A local web-based playground (\playground.exs\) built with Phoenix LiveView allows users to test and debug LLM requests interactively, supporting multiple providers including OpenAI, Anthropic, OpenRouter, and ZenMux. The project also contains standalone scripts for text generation, streaming, object generation, embeddings, and context reuse, along with shared helper utilities and configuration templates.

examples · high confidence

New provider and configuration documentation guides

The documentation now includes dedicated guides for adding custom providers, configuring global settings (timeouts, pools, telemetry), and detailed usage instructions for specific providers including Amazon Bedrock, Anthropic, Azure, Cerebras, DeepSeek, and Fireworks AI. These guides cover provider registration, model specification, provider options, and implementation details to help users integrate and configure the library effectively.

guides · high confidence

ReqLLM application bootstrapping and unified HTTP connection pooling

ReqLLM now starts its own OTP application that initializes the provider registry, a named ETS table for schema caching, and a centralized Finch HTTP client. This unified connection pool handles both streaming and non-streaming requests across all providers, with configurable pool size, count, and HTTP protocols. The application also supports automatic .env file loading at startup and includes a dev-mode Tidewave plug for local debugging.

_lib/req\llm · high confidence

Behavioural changes

Project renamed from ReqAi to ReqLLM and quality gates standardized

The library has been renamed from ReqAi to ReqLLM, reflected in the package tarball pattern in .gitignore and the project documentation. A .credo.exs configuration file has been added to enforce code quality standards, and the .formatter.exs has been updated to set a line length of 98 characters. Additionally, .gitignore has been expanded to exclude Conductor, Language Server, and Dialyzer PLT files, while .env.example now lists the supported API keys for automatic loading.

(repo-wide) · high confidence

Rename ReqAi to ReqLLM

The main API facade module has been renamed from \ReqAi\ to \ReqLLM\. The previous \ReqAi\ module, which contained only a placeholder \hello/0\ function, has been removed and replaced by the new \ReqLLM\ module, which provides the unified interface for AI providers, model specifications, configuration management, and structured data generation.

lib · high confidence

Test coverage

1 commit adding/updating tests in test/coverage/inference; 20 commits adding/updating tests in test; 20 commits adding/updating tests in test; Added Azure provider test coverage; Added Azure provider test coverage suite; Added Google API coverage tests for grounding, image generation, and multimodal tool results; Added OpenRouter API coverage tests; Added automated test generation for catalog community providers; Added comprehensive test coverage for Anthropic provider capabilities; Added comprehensive test coverage for ReqLLM core components; Added comprehensive test coverage for streaming failure handling and transport configuration; Added comprehensive test coverage for the StreamServer component; Added comprehensive test suite for Cerebras provider; Added comprehensive test suites for Z.AI and Z.AI Coder providers; Added comprehensive tests for provider streaming, materialization, and options handling; Added comprehensive tests for the MiniMax provider; Added comprehensive tests for the Reflection AI provider; Added contract tests for public API and provider extension stability; Added test coverage for Alibaba, Alibaba CN, Cohere, ElevenLabs, Venice, and Zenmux providers; Added test coverage for Amazon Bedrock Converse API features; Added test coverage for Amazon Bedrock, Anthropic, ElevenLabs, Google, and Ollama providers; Added test coverage for Google Vertex AI provider; Added test coverage for LM Studio provider; Added test coverage for Moonshot AI Kimi K3; Added test coverage for error handling, retry logic, usage extraction, and fixture replay steps; Added test coverage for xAI provider capabilities; Added tests for Google Vertex AI authentication, token caching, and Anthropic structured output; Added tests for LLM provider structured output support; Added tests for LLM usage normalization and billing validation; Added tests for ReqLLM CLI tasks and compatibility logic; Added tests for ReqLLM message content part construction; Added tests for ReqLLM response stream summarization; Added tests for StepFun AI chat and audio providers; Added tests for compatibility evidence migration, provider drift, and scenario catalog; Added tests for namespaced provider options normalization; Added tests for non-strict tool schemas and cross-provider tool call ID compatibility; Added unit tests for Bedrock bidirectional streaming and Nova Sonic event handling; Expanded OpenAI feature coverage tests; Expanded test coverage for Amazon Bedrock provider; Expanded test coverage for ReqLLM core subsystems; Expanded test suite with parity checks and video generation coverage; New provider coverage test suites for text, embeddings, images, audio, and video; New test support infrastructure for fixtures, streaming, and provider validation; Validation script for DevDay Responses and Image 2.5 model support.

Dependencies

Add examples project and update dependency lockfiles

The \examples/\ directory now includes a dedicated \mix.exs\ and \mix.lock\ for the \req\_llm\_examples\ application, which depends on the main library and \phoenix\_playground\ (\~\> 0.1.8). The root \mix.exs\ has been updated to reflect the project rename from \ReqAi\ to \ReqLLM\ and sets the version to 1.26.0. Additionally, the root \mix.lock\ and the test fixture \mix.lock\ have been refreshed to resolve the latest dependency versions, including updates to \igniter\, \jsv\, \mint\, and \llm\_db\.

(dependencies) · high confidence

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 54 → 54 (-0.6)
  • Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 89 → 85 (-4.1)
  • Architecture 88 → 95 (+7.8)
  • Maturity 78 → 79 (+1.5)
  • Readiness 66 → 66 (+0.1)
  • Security 32 → 31 (-1.9)

Resolved (18)

  • Duplicated block (13 lines × 3) (lib/req_llm/providers/minimax/images_api.ex)
  • Duplicated block (8 lines × 2) (lib/req_llm/provider/defaults.ex)
  • Duplicated block (8 lines × 4) (lib/req_llm/provider/defaults.ex)
  • Duplicated block (9 lines × 2) (lib/req_llm/provider/defaults.ex)
  • Members sharing a duplicated core (4 members, 50+ identical tokens) (lib/req_llm/provider/defaults.ex)
  • Members sharing a duplicated core (4 members, 50+ identical tokens) (lib/req_llm/provider/defaults.ex)
  • Members sharing a duplicated core (6 members, 50+ identical tokens) (lib/req_llm/providers/minimax.ex)
  • Off-boarding risk: anonymized user #1
  • Orphaned file (lib/req_llm/providers/google/response_builder.ex)
  • Outdated: igniter
  • Outdated: jsv
  • Outdated: phoenix_playground
  • Outdated: splode
  • Projects may be oversized for their cohesion
  • Repeated repair: lib/req_llm/providers/anthropic.ex (lib/req_llm/providers/anthropic.ex)
  • Repeated repair: lib/req_llm/providers/openai_codex.ex (lib/req_llm/providers/openai_codex.ex)
  • Repeated repair: lib/req_llm/providers/zai_coding_plan.ex (lib/req_llm/providers/zai_coding_plan.ex)
  • Usage.handle (cognitive 18) (lib/req_llm/step/usage.ex)

New (203)

  • Duplicated block (11–17 lines × 2) (lib/req_llm/providers/cohere.ex)
  • Duplicated block (13 lines × 3) (lib/req_llm/providers/minimax/images_api.ex)
  • Duplicated block (7 lines × 2) (lib/req_llm/evaluation/protocol.ex)
  • Duplicated block (8 lines × 2) (lib/req_llm/providers/catalog_gateway.ex)
  • Duplicated block (8 lines × 2) (lib/req_llm/providers/google_vertex.ex)
  • Duplicated block (8 lines × 3) (lib/req_llm/providers/catalog_gateway.ex)
  • Duplicated block (8 lines × 4) (lib/req_llm/provider/defaults.ex)
  • Duplicated block (9 lines × 2) (lib/req_llm/provider/defaults.ex)
  • Edited copies of one member (3 members, 12+ corresponding lines) (lib/req_llm/providers/anthropic.ex)
  • Edited copies of one member (3 members, 14+ corresponding lines) (lib/req_llm/providers/anthropic/response.ex)
  • Edited copies of one member (3 members, 2+ corresponding lines) (lib/req_llm/provider/defaults.ex)
  • Edited copies of one member (3 members, 25+ corresponding lines) (examples/scripts/json_schema_examples.exs)
  • Edited copies of one member (3 members, 3+ corresponding lines) (lib/req_llm/providers/anthropic.ex)
  • Edited copies of one member (3 members, 30+ corresponding lines) (lib/req_llm/providers/amazon_bedrock/anthropic.ex)
  • Edited copies of one member (3 members, 36+ corresponding lines) (lib/req_llm/providers/fireworks_ai.ex)
  • Edited copies of one member (3 members, 4+ corresponding lines) (lib/req_llm/auth.ex)
  • Edited copies of one member (3 members, 4+ corresponding lines) (lib/req_llm/streaming.ex)
  • Edited copies of one member (3 members, 4+ corresponding lines) (tutorial/agents/06_memory_context.exs)
  • Edited copies of one member (3 members, 8+ corresponding lines) (examples/lib/req_llm/examples/helpers.ex)
  • Edited copies of one member (3 members, 9+ corresponding lines) (lib/req_llm/ocr.ex)
  • …and 183 more

Changes since last survey

  • 30 commits — 17 feature/other, 13 fixes

By area

  • lib/req_llm — 13 commits
  • (root) — 9 commits
  • test/req_llm — 5 commits
  • test/support — 2 commits
  • guides/anthropic.md — 1 commit

Notable commits

  • fix: fix(anthropic): preserve cache counter presence (#1230)
  • fix: fix(deps): require patched JSV and unblock offline CI (#1235)
  • fix: fix(google): carry raw finish reason onto streamed responses (#1266)
  • fix: fix(google): preserve non-streaming function-call thought signatures (#1246)
  • fix: fix(google): send responseJsonSchema to Gemini 4 models (#1269)
  • fix: fix(google): update JSON schema fixture bodies (#1270)
  • fix: fix(google_vertex): handle non-2xx responses (#1237)
  • fix: fix(mc): repair Groq test URL and mix mc replay routing (#1251)
  • fix: fix(mistral): accept low and medium reasoning effort (#1228)
  • fix: fix(streaming): normalize context window errors (#1262)
  • fix: fix(timeout): stop retries after the total deadline (#1244)
  • fix: fix: derive streamed tool-call argument flags from the assembled fragments (#1256)
  • fix: fix: keep the invalid_arguments flag on buffered tool calls (#1254)
  • change: build(deps): require ex_aws_auth ~> 1.6 (#1264)
  • change: chore(deps): update Zoi to 0.19 (#1240)
  • change: chore: release version v1.30.0
  • change: deps(deps): bump jsv from 0.26.2 to 0.27.0 (#1259)
  • change: deps(deps-dev): bump websock_adapter from 0.6.0 to 0.7.0 (#1239)
  • change: deps(deps-dev): bump websock_adapter from 0.7.0 to 0.7.1 (#1258)
  • change: deps: refresh dependency lock and security patches
  • …and 10 more

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

agentjido/req_llm was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 15 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 38de681029e555efd6a5256a8f4daa618a76d8ab — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-3c33c1882dc1.