feat: reorg of codebase

.github/PULL_REQUEST_TEMPLATE/component.md

@@ -0,0 +1,27 @@
+# Component PR
+
+Use this template when adding or modifying components in `mellea/stdlib/components/`.
+
+## Description
+- [ ] Link to Issue: 
+
+<!-- Brief description of the component being added/modified along with an explanation for why it should be in the standard library. -->
+
+## Implementation Checklist
+
+### Protocol Compliance
+- [ ] `parts()` returns list of constituent parts (Components or CBlocks)
+- [ ] `format_for_llm()` returns TemplateRepresentation or string
+- [ ] `_parse(computed: ModelOutputThunk)` parses model output correctly into the specified Component return type
+
+### Content Blocks
+- [ ] CBlock used appropriately for text content
+- [ ] ImageBlock used for image content (if applicable)
+
+### Integration
+- [ ] Component exported in `mellea/stdlib/components/__init__.py` or, if you are adding a library of components, from your sub-module
+
+### Testing
+- [ ] Tests added to `tests/components/`
+- [ ] New code has 100% coverage
+- [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

.github/PULL_REQUEST_TEMPLATE/misc.md

@@ -0,0 +1,18 @@
+# Misc PR
+
+## Type of PR
+
+- [ ] Bug Fix
+- [ ] New Feature
+- [ ] Documentation
+- [ ] Other
+
+## Description
+- [ ] Link to Issue: 
+
+<!-- Brief description of the change being made along with an explanation. -->
+
+### Testing
+- [ ] Tests added to the respective file if code was changed
+- [ ] New code has 100% coverage if code as added
+- [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

.github/PULL_REQUEST_TEMPLATE/requirement.md

@@ -0,0 +1,30 @@
+# Requirement PR
+
+Use this template when adding or modifying requirements in `mellea/stdlib/requirements/`.
+
+## Description
+- [ ] Link to Issue: 
+
+<!-- Brief description of the requirement being added/modified along with an explanation for why it should be in the standard library. -->
+
+## Implementation Checklist
+
+### Base Class
+- [ ] Extends appropriate base class:
+  - `Requirement` - standard requirement
+  - `ALoraRequirement` - uses specialized Intrinsic/Adapter for generation-based validation
+
+### Validation Logic
+- [ ] `validation_fn` defined (if using Python-based validation)
+    - [ ] re-usable functionality within the validation_fn should be separated out into `mellea/stdlib/tools/`
+- [ ] `validate` returns a `ValidationResult` with 
+    - [ ] a `thunk` and `context` if using a backend to generate
+    - [ ] a specific `reason` and `score` when possible
+
+### Integration
+- [ ] Requirement exported in `mellea/stdlib/requirements/__init__.py` or, if you are adding a library of requirements, from your sub-module
+
+### Testing
+- [ ] Tests added to `tests/requirements/`
+- [ ] New code has 100% coverage
+- [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

.github/PULL_REQUEST_TEMPLATE/sampling.md

@@ -0,0 +1,28 @@
+# Sampling Strategy PR
+
+Use this template when adding or modifying sampling strategies in `mellea/stdlib/sampling/`.
+
+## Description
+- [ ] Link to Issue: 
+
+<!-- Brief description of the sampling strategy being added/modified along with an explanation for why it should be in the standard library. -->
+
+## Implementation Checklist
+
+### Base Class
+- [ ] Extends appropriate base class:
+  - `BaseSamplingStrategy` if your changes are mostly modifying the `repair` and/or `select_from_failure` functions
+  - `SamplingStrategy` if your changes involve a new `sample` method
+  - Other defined sampling strategies if your implementation is similar to existing implementations
+
+### Return Value
+- [ ] Returns a properly typed `SamplingResult`. Specifically, this means:
+  - `ModelOutputThunk`s in `sample_generations` are properly typed from the Component and the `parsed_repr` is the expected type.
+
+### Integration
+- [ ] Strategy exported in `mellea/stdlib/sampling/__init__.py`
+
+### Testing
+- [ ] Tests added to `tests/sampling/`
+- [ ] New code has 100% coverage
+- [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

.github/PULL_REQUEST_TEMPLATE/tool.md

@@ -0,0 +1,22 @@
+# Tool PR
+
+Use this template when adding or modifying components in `mellea/stdlib/tools/`.
+
+## Description
+- [ ] Link to Issue: 
+
+<!-- Brief description of the tool being added/modified along with an explanation for why it should be in the standard library. -->
+
+## Implementation Checklist
+
+### Protocol Compliance
+- [ ] Ensure compatibility with existing backends and providers
+    - For most tools being added as functions, this means that calling `convert_function_to_tool` works
+
+### Integration
+- [ ] Tool exported in `mellea/stdlib/tools/__init__.py` or, if you are adding a library of components, from your sub-module
+
+### Testing
+- [ ] Tests added to `tests/stdlib/tools/`
+- [ ] New code has 100% coverage
+- [ ] Ensure existing tests and github automation passes (a maintainer will kick off the github automation when the rest of the PR is populated)

.github/pull_request_template.md

@@ -0,0 +1,13 @@
+# Pull Request
+
+NOTE: Please ensure you have an issue that has been acknowledged by a core contributor and routed you to open a pull request against this repository. Otherwise, please open an issue before continuing with this pull request.
+
+Only modify this text by checking one of the boxes below. This comment will be overwritten with a specific pull request template based off your choice.
+
+Type of Pull Request:
+
+- [ ] Component
+- [ ] Requirement
+- [ ] Sampling Strategy
+- [ ] Tool
+- [ ] Misc: Bug Fix, New Feature, Documentation Update, Other

.github/workflows/pr-update.yml

@@ -0,0 +1,73 @@
+name: PR Bot
+
+on:
+  pull_request_target:
+    types: [opened, edited]
+
+jobs:
+  update-pr-body:
+    runs-on: ubuntu-latest
+    if: ${{ !contains(github.event.pull_request.body, 'mellea-pr-edited-marker') }}
+    permissions:
+      pull-requests: write
+      contents: read
+    steps:
+      - name: Checkout code # Checks out the base branch, not PR branch.
+        uses: actions/checkout@v4
+
+      - name: Detect PR type from checkboxes
+        id: detect-type
+        env:
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          PR_TYPE=""
+
+          # Check for checked boxes (supports [x] and [X])
+          if echo "$PR_BODY" | grep -qi '\[x\] Component'; then
+            PR_TYPE="component"
+          elif echo "$PR_BODY" | grep -qi '\[x\] Requirement'; then
+            PR_TYPE="requirement"
+          elif echo "$PR_BODY" | grep -qi '\[x\] Sampling Strategy'; then
+            PR_TYPE="sampling"
+          elif echo "$PR_BODY" | grep -qi '\[x\] Tool'; then
+            PR_TYPE="tool"
+          elif echo "$PR_BODY" | grep -qi '\[x\] Misc'; then
+            PR_TYPE="misc"
+          fi
+
+          if [ -z "$PR_TYPE" ]; then
+            echo "::error::No PR type selected. Please check one of of the boxes from the original pr template."
+            exit 1
+          fi
+
+          echo "pr_type=$PR_TYPE" >> "$GITHUB_OUTPUT"
+          echo "Detected PR type: $PR_TYPE"
+
+      - name: Update PR body with checklist
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PR_BODY: ${{ github.event.pull_request.body }}
+          PR_TYPE: ${{ steps.detect-type.outputs.pr_type }}
+        run: |
+          TEMPLATE_FILE=".github/PULL_REQUEST_TEMPLATE/${PR_TYPE}.md"
+
+          if [ -f "$TEMPLATE_FILE" ]; then
+            MARKER="<!-- mellea-pr-edited-marker: do not remove this marker -->"
+            TEMPLATE_CONTENT=$(cat "$TEMPLATE_FILE")
+
+            NEW_BODY="${MARKER}
+            ${TEMPLATE_CONTENT}"
+
+            gh pr edit ${{ github.event.pull_request.number }} --body "$NEW_BODY"
+            echo "Updated PR body with ${PR_TYPE} checklist"
+          else
+            echo "::error::Template file not found: $TEMPLATE_FILE"
+            echo "Something as gone wrong. Contact a maintainer."
+            exit 1
+          fi
+
+      - name: Comment on PR
+        uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc
+        with:
+          message: |
+            The PR description has been updated. Please fill out the template for your PR to be reviewed. 

README.md

@@ -174,7 +174,7 @@ the output is checked against the constraints using (in this case) LLM-as-a-judg
 ```python
 # file: https://github.com/generative-computing/mellea/blob/main/docs/examples/instruct_validate_repair/101_email_with_validate.py
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
+from mellea.backends import ModelOption
 from mellea.backends.ollama import OllamaModelBackend
 from mellea.backends import model_ids
 from mellea.stdlib.sampling import RejectionSamplingStrategy

cli/decompose/pipeline.py

@@ -7,7 +7,7 @@
 from mellea import MelleaSession
 from mellea.backends.ollama import OllamaModelBackend
 from mellea.backends.openai import OpenAIBackend
-from mellea.backends.types import ModelOption
+from mellea.backends import ModelOption
 
 from .prompt_modules import (
     constraint_extractor,

cli/decompose/prompt_modules/constraint_extractor/_constraint_extractor.py

@@ -3,8 +3,8 @@
 from typing import Any, TypeVar, final
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import BackendGenerationError, TagExtractionError

cli/decompose/prompt_modules/general_instructions/_general_instructions.py

@@ -3,8 +3,8 @@
 from typing import Any, TypeVar, final
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import BackendGenerationError, TagExtractionError

cli/decompose/prompt_modules/subtask_constraint_assign/_subtask_constraint_assign.py

@@ -5,8 +5,8 @@
 from typing_extensions import Unpack
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import BackendGenerationError, TagExtractionError

cli/decompose/prompt_modules/subtask_list/_subtask_list.py

@@ -3,8 +3,8 @@
 from typing import Any, TypeVar, final
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import (
@@ -15,7 +15,7 @@
 from ._prompt import get_system_prompt, get_user_prompt
 from ._types import SubtaskItem
 
-# from mellea.stdlib.requirement import Requirement
+# from mellea.stdlib.requirements import requirement
 
 T = TypeVar("T")
 

cli/decompose/prompt_modules/subtask_prompt_generator/_subtask_prompt_generator.py

@@ -5,8 +5,8 @@
 from typing_extensions import Unpack
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import BackendGenerationError, TagExtractionError

cli/decompose/prompt_modules/validation_decision/_validation_decision.py

@@ -3,8 +3,8 @@
 from typing import Any, Final, Literal, TypeVar, final
 
 from mellea import MelleaSession
-from mellea.backends.types import ModelOption
-from mellea.stdlib.chat import Message
+from mellea.backends import ModelOption
+from mellea.stdlib.components import Message
 
 from .._prompt_modules import PromptModule, PromptModuleString
 from ._exceptions import BackendGenerationError, TagExtractionError

cli/eval/runner.py

@@ -4,9 +4,9 @@
 from typing import List
 
 import mellea
-from mellea.stdlib.base import ModelOutputThunk
+from mellea.core import ModelOutputThunk
 from mellea.stdlib.test_based_eval import TestBasedEval
-from mellea.backends.types import ModelOption
+from mellea.backends import ModelOption
 
 from rich.console import Console
 from rich.progress import BarColumn, Progress, SpinnerColumn, TextColumn

docs/dev/requirement_aLoRA_rerouting.md

@@ -33,7 +33,8 @@ Suppose that the user creates a backend and then adds a generic constraint check
 
 ```python
 from mellea import start_session
-from mellea.stdlib.requirement import Requirement
+from mellea.core import Requirement
+from mellea.backends.adapters import GraniteCommonAdapter
 
 m = start_session(
     "huggingface.LocalHFBackend:ibm-granite/granite-3.2-8b-instruct")

docs/examples/agents/react.py

@@ -8,14 +8,9 @@
 from jinja2 import Template
 
 import mellea
-import mellea.backends
-import mellea.backends.types
-import mellea.stdlib
-import mellea.stdlib.base
-import mellea.stdlib.chat
-from mellea.backends import model_ids
-from mellea.helpers.fancy_logger import FancyLogger
-from mellea.stdlib.base import ChatContext
+import mellea.stdlib.components.chat
+from mellea.core import FancyLogger
+from mellea.stdlib.context import ChatContext
 
 FancyLogger.get_logger().setLevel("ERROR")
 
@@ -120,8 +115,8 @@ def react(
 
     # Add the system prompt and the goal to the chat history.
     m.ctx = m.ctx.add(
-        mellea.stdlib.chat.Message(role="system", content=_sys_prompt)
-    ).add(mellea.stdlib.chat.Message(role="user", content=f"{goal}"))
+        mellea.stdlib.components.chat.Message(role="system", content=_sys_prompt)
+    ).add(mellea.stdlib.components.chat.Message(role="user", content=f"{goal}"))
 
     # The main ReACT loop as a dynamic program:
     # (  ?(not done) ;
@@ -162,7 +157,9 @@ def react(
 
         print("### Observation")
         tool_output = react_toolbox.call_tool(selected_tool, act_args.content)
-        m.ctx = m.ctx.add(mellea.stdlib.chat.Message(role="tool", content=tool_output))
+        m.ctx = m.ctx.add(
+            mellea.stdlib.components.chat.Message(role="tool", content=tool_output)
+        )
         print(tool_output)
 
         print("### Done Check")