This repository was archived by the owner on Jan 22, 2026. It is now read-only.
feat: overhaul Docker workflow and architecture with dynamic LLMs, vision API, and reusable tooling #29
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…sion API, and reusable tooling - Refactor GitHub Actions to support automatic build-and-push to GHCR with Buildx caching and disk cleanup - Add new `run-crews-control-project.yaml` workflow for parameterized Docker-based project execution - Redesign Dockerfile for multi-stage, reproducible, non-root builds with dynamic user mapping via entrypoint.sh - Add per-agent LLM configuration via `llm_model` in YAML with lazy caching and validation - Introduce `run_until` crew looping logic with condition-based retries and delay support - Modularize Vision API support (Azure and OpenAI) with dynamic tool selection - Make tools resilient to env var presence; add fallback and validation - Update `README.md` with detailed orchestration examples (dependencies, loops, context, SHA-based filenames) - Ensure updated `requirements.txt` with deterministic hashes for GPU-enabled libraries
Introduces the `for_each` property for crews, enabling dynamic, data-driven iteration within a workflow.
When a crew definition includes the `for_each` key, the orchestrator resolves its template string value into a JSON list. The orchestrator then executes the complete crew definition sequentially for each item in that list.
The special `{item}` placeholder can be used within the crew's definition (e.g., in `output_naming_template` or a task's `description`) to reference the value of the current iteration. The final output of the iterator crew is an aggregated JSON array containing the result from each run, making it available for downstream processing.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
run-crews-control-project.yamlworkflow for parameterized Docker-based project executionllm_modelin YAML with lazy caching and validationrun_untilcrew looping logic with condition-based retries and delay supportREADME.mdwith detailed orchestration examples (dependencies, loops, context, SHA-based filenames)requirements.txtwith deterministic hashes for GPU-enabled librariesfor_eachiterator pattern for dynamic, data-driven crew execution.