teddy-cli 0.1.17.dev1411__tar.gz → 0.1.17.dev1413__tar.gz

{teddy_cli-0.1.17.dev1411 → teddy_cli-0.1.17.dev1413}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: teddy-cli
-Version: 0.1.17.dev1411
+Version: 0.1.17.dev1413
 Summary: The local-first, test-driven agentic engineering harness. Because you should own the means of development.
 Author: Raphael Atteritano
 License: AGPL-3.0-only
@@ -159,7 +159,7 @@ TeDDy is built on the belief that you should own your software delivery lifecycl
 
 - **High-Level Governance Rules (`PROJECT.md` & `ARCHITECTURE.md`):** The simplest way to guide agents. Define product roadmaps, engineering principles, system laws, and component boundaries in living Markdown documents that agents read on every turn.
 - **Artifact Templates (`docs/templates/`):** Standardize the artifacts produced during development. Customize the Markdown templates for vertical slices, specifications, case files, and milestones to match your documentation standards.
-- **Agent Prompts (`.teddy/prompts/`):** To change the process itself, customize the agent prompts. Each agent's workflow is broken down into structured phases and individual steps, defined entirely in Markdown. You can tweak instructions, add domain-specific quality gates, or introduce brand-new agent personas to match how your team builds software. TeDDy composes each system prompt from the agent's instructions plus a shared response protocol it appends automatically. The composed prompt is saved in the session folder, and `teddy get-prompt <agent>` prints the identical result, so you can read exactly what the model receives. A customized prompt that already carries its own `<response_format>` skips the shared protocol and is used as-is.
+- **Agent Prompts (`.teddy/prompts/`):** To change the process itself, customize the agent prompts. Each agent's workflow is broken down into structured phases and individual steps, defined entirely in Markdown. You can tweak instructions, add domain-specific quality gates, or introduce brand-new agent personas to match how your team builds software. TeDDy composes each system prompt from the agent's instructions plus a shared response protocol it appends automatically. The composed prompt is saved in the session folder. You can also run `teddy get-prompt <agent>` to retrieve it without starting a session. A customized prompt that already includes `<response_format>` opts out of the shared protocol.
 - **Command Automation (`Makefile`):** Instead of hardcoding shell commands inside agent prompts, common development and verification operations are routed through the Makefile. When you need to change a flag, runner, or environment setup, you change it once in the Makefile instead of updating instructions across multiple agent prompts.
 - **Context Filtering (`.teddyignore`):** Control which files TeDDy scans during context generation and tree traversal. A `.teddyignore` file in the project root follows standard ignore syntax and takes precedence over `.gitignore`, allowing you to ignore extra paths or re-include git-ignored files using negation patterns.
 
@@ -334,7 +334,7 @@ teddy context -c review.context
 | `update`                      | Check for updates and display upgrade instructions.                                                                                      |
 | `execute`                     | Execute a Markdown plan (reads from clipboard if no path is provided).                                                                   |
 | `context`                     | Export context payload (system info, git status, file tree, `init.context`). Add ad-hoc files with `-c` and skip defaults with `--only`. |
-| <nobr>`get-prompt`</nobr>     | Print the composed system prompt (agent instructions plus the shared response protocol).                                                 |
+| <nobr>`get-prompt`</nobr>     | Output the composed system prompt (agent instructions plus the shared response protocol).                                                |
 
 > [!NOTE]
 > By default, `execute` and `context` copy output to the clipboard. Use `--no-copy` to bypass.

{teddy_cli-0.1.17.dev1411 → teddy_cli-0.1.17.dev1413}/README.md

@@ -125,7 +125,7 @@ TeDDy is built on the belief that you should own your software delivery lifecycl
 
 - **High-Level Governance Rules (`PROJECT.md` & `ARCHITECTURE.md`):** The simplest way to guide agents. Define product roadmaps, engineering principles, system laws, and component boundaries in living Markdown documents that agents read on every turn.
 - **Artifact Templates (`docs/templates/`):** Standardize the artifacts produced during development. Customize the Markdown templates for vertical slices, specifications, case files, and milestones to match your documentation standards.
-- **Agent Prompts (`.teddy/prompts/`):** To change the process itself, customize the agent prompts. Each agent's workflow is broken down into structured phases and individual steps, defined entirely in Markdown. You can tweak instructions, add domain-specific quality gates, or introduce brand-new agent personas to match how your team builds software. TeDDy composes each system prompt from the agent's instructions plus a shared response protocol it appends automatically. The composed prompt is saved in the session folder, and `teddy get-prompt <agent>` prints the identical result, so you can read exactly what the model receives. A customized prompt that already carries its own `<response_format>` skips the shared protocol and is used as-is.
+- **Agent Prompts (`.teddy/prompts/`):** To change the process itself, customize the agent prompts. Each agent's workflow is broken down into structured phases and individual steps, defined entirely in Markdown. You can tweak instructions, add domain-specific quality gates, or introduce brand-new agent personas to match how your team builds software. TeDDy composes each system prompt from the agent's instructions plus a shared response protocol it appends automatically. The composed prompt is saved in the session folder. You can also run `teddy get-prompt <agent>` to retrieve it without starting a session. A customized prompt that already includes `<response_format>` opts out of the shared protocol.
 - **Command Automation (`Makefile`):** Instead of hardcoding shell commands inside agent prompts, common development and verification operations are routed through the Makefile. When you need to change a flag, runner, or environment setup, you change it once in the Makefile instead of updating instructions across multiple agent prompts.
 - **Context Filtering (`.teddyignore`):** Control which files TeDDy scans during context generation and tree traversal. A `.teddyignore` file in the project root follows standard ignore syntax and takes precedence over `.gitignore`, allowing you to ignore extra paths or re-include git-ignored files using negation patterns.
 
@@ -300,7 +300,7 @@ teddy context -c review.context
 | `update`                      | Check for updates and display upgrade instructions.                                                                                      |
 | `execute`                     | Execute a Markdown plan (reads from clipboard if no path is provided).                                                                   |
 | `context`                     | Export context payload (system info, git status, file tree, `init.context`). Add ad-hoc files with `-c` and skip defaults with `--only`. |
-| <nobr>`get-prompt`</nobr>     | Print the composed system prompt (agent instructions plus the shared response protocol).                                                 |
+| <nobr>`get-prompt`</nobr>     | Output the composed system prompt (agent instructions plus the shared response protocol).                                                |
 
 > [!NOTE]
 > By default, `execute` and `context` copy output to the clipboard. Use `--no-copy` to bypass.

{teddy_cli-0.1.17.dev1411 → teddy_cli-0.1.17.dev1413}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "teddy-cli"
-version = "0.1.17.dev1411"
+version = "0.1.17.dev1413"
 description = "The local-first, test-driven agentic engineering harness. Because you should own the means of development."
 readme = "README.md"
 keywords = [

{teddy_cli-0.1.17.dev1411 → teddy_cli-0.1.17.dev1413}/src/teddy_executor/core/services/context_service.py

@@ -393,8 +393,8 @@ class ContextService(IGetContextUseCase):
         """State both tree limits once, so the compact notices stay meaningful."""
         return (
             f"*Tree capped at depth {self._repo_tree_generator.max_depth} "
-            f"and width {self._repo_tree_generator.max_children}: "
-            "truncated directories show counts only.*"
+            f"and {self._repo_tree_generator.max_children} entries per subdirectory: "
+            "truncated directories show entry counts only.*"
         )
 
     def _format_workspace_contents(

{teddy_cli-0.1.17.dev1411 → teddy_cli-0.1.17.dev1413}/src/teddy_executor/resources/config/config.yaml

@@ -19,7 +19,7 @@ read:
 
 context:
   max_depth: 3                      # Max project tree depth.
-  max_children: 20                  # Max entries listed per directory.
+  max_children: 20                  # Max entries listed per subdirectory.
 
 research:
   max_results: 5                    # Number of search results to fetch and scrape.