gobby 0.2.6__py3-none-any.whl → 0.2.7__py3-none-any.whl

gobby/prompts/defaults/handoff/compact.md

@@ -1,63 +0,0 @@
----
-description: Compact handoff summary prompt for cumulative compression
-required_variables:
-  - transcript_summary
-  - last_messages
-  - git_status
-  - file_changes
-optional_variables:
-  - previous_summary
-  - todo_list
----
-You are creating a session continuation summary after a compaction event.
-
-## Context from Earlier in This Session (if any):
-{{ previous_summary }}
-
-If there is previous context above, focus your summary on what happened AFTER
-that point. Compress the historical context into a brief "Session History" section.
-If no previous context, this is the first segment - summarize the full session.
-
-## Current Transcript:
-{{ transcript_summary }}
-
-## Last Messages:
-{{ last_messages }}
-
-## Git Status:
-{{ git_status }}
-
-## Files Changed:
-{{ file_changes }}
-
-{% if todo_list %}
-{{ todo_list }}
-{% endif %}
-
----
-
-Create a continuation summary optimized for resuming work after compaction.
-Use these sections:
-
-### Current Focus
-[What is being actively worked on RIGHT NOW - be specific and detailed.
-This is the most important section.]
-
-### This Segment's Progress
-[Bullet points of what was accomplished in this segment]
-
-### Session History
-[1-2 sentences summarizing the overall session journey. Include if there was
-previous context, otherwise skip this section.]
-
-### Technical State
-- Key files modified: [list files]
-- Git status: [uncommitted changes summary]
-- Any blockers or pending items
-
-### Next Steps
-[Numbered list of concrete actions to take when resuming]
-
-IMPORTANT: Prioritize recency. "Current Focus" and "This Segment's Progress"
-should be detailed and specific. Historical context should be compressed.
-Use only ASCII-safe characters.

gobby/prompts/defaults/handoff/session_end.md

@@ -1,57 +0,0 @@
----
-description: Session end handoff summary prompt
-required_variables:
-  - transcript_summary
-  - last_messages
-  - git_status
-  - file_changes
-optional_variables:
-  - todo_list
----
-Analyze this Claude Code session transcript and create a comprehensive session summary.
-
-## Transcript (last 50 turns):
-{{ transcript_summary }}
-
-## Last Messages:
-{{ last_messages }}
-
-## Git Status:
-{{ git_status }}
-
-## Files Changed:
-{{ file_changes }}
-
-Create a markdown summary with the following sections (do NOT include a top-level '# Session Summary' header):
-
-## Overview
-[1-2 paragraph summary of what was accomplished in this session]
-
-## Key Decisions
-[List of important technical or architectural decisions made, with bullet points]
-
-## Important Lessons Learned
-[Technical insights, gotchas, or patterns discovered, with bullet points]
-
-## Substantive Interrupts
-[Times when the user changed direction significantly - NOT simple "continue" or "resume" prompts]
-
-## Research & Epiphanies
-[Key discoveries from research or debugging that should be remembered, with bullet points]
-
-## Files Changed
-{{ file_changes }}
-[Add specific details about WHY each file was changed and WHAT the changes accomplish.]
-
-## Git Status
-```
-{{ git_status }}
-```
-
-{{ todo_list }}
-
-## Next Steps
-[Concrete, numbered suggestions for what to do when resuming work. Be specific and actionable.]
-
-Focus on actionable insights and context that would be valuable when resuming work later.
-Use only ASCII-safe characters - avoid Unicode em-dashes, smart quotes, or special characters.

gobby/prompts/defaults/memory/extract.md

@@ -1,61 +0,0 @@
----
-description: Extract reusable memories from session transcripts
-required_variables:
-  - transcript_summary
-  - project_name
-optional_variables:
-  - task_refs
-  - files
-  - tool_summary
-  - min_importance
-  - max_memories
-defaults:
-  min_importance: 0.7
-  max_memories: 5
----
-Analyze this coding session and extract ONLY high-value, reusable memories.
-
-## Session Context
-- Project: {{ project_name }}
-{% if task_refs %}- Tasks worked: {{ task_refs }}{% endif %}
-{% if files %}- Files modified: {{ files }}{% endif %}
-{% if tool_summary %}- Key tool actions: {{ tool_summary }}{% endif %}
-
-## Session Transcript
-{{ transcript_summary }}
-
-## Extract memories that are:
-- **FACTS**: Project architecture, technology choices, API patterns, file locations
-- **PATTERNS**: Code conventions, testing approaches, file organization, naming conventions
-- **PREFERENCES**: User-stated preferences about style, approach, or tools
-- **CONTEXT**: Important background that helps future work on this project
-
-## DO NOT extract:
-- Temporary debugging information
-- Session-specific state that won't apply later
-- Obvious/generic programming knowledge
-- Information already documented in the codebase
-- Duplicate information from previous memories
-
-## Output Format
-Return a JSON array of memories. Each memory should be:
-- Self-contained and understandable without session context
-- Specific to this project (not generic programming advice)
-- Actionable or informative for future sessions
-
-```json
-[
-  {
-    "content": "The reusable knowledge (1-3 sentences, specific and actionable)",
-    "memory_type": "fact | pattern | preference | context",
-    "importance": 0.7,
-    "tags": ["relevant", "tags"]
-  }
-]
-```
-
-Guidelines:
-- Only include memories with importance >= {{ min_importance | default(0.7) }}
-- Maximum {{ max_memories | default(5) }} memories
-- If nothing worth remembering, return an empty array: []
-- importance scale: 0.7 = useful, 0.8 = valuable, 0.9 = critical, 1.0 = essential

gobby/prompts/defaults/research/step.md

@@ -1,58 +0,0 @@
----
-name: research-step
-description: ReAct loop prompt for codebase research
-version: "1.0"
-variables:
-  task_title:
-    type: str
-    required: true
-    description: Task title being researched
-  task_description:
-    type: str
-    default: ""
-    description: Task description
-  found_files:
-    type: list
-    default: []
-    description: List of files found so far
-  snippets_keys:
-    type: list
-    default: []
-    description: List of snippet keys/paths found
-  history:
-    type: str
-    default: ""
-    description: Formatted history of recent agent turns
-  step:
-    type: int
-    required: true
-    description: Current step number (1-indexed)
-  max_steps:
-    type: int
-    default: 10
-    description: Maximum number of steps
-  search_tool_section:
-    type: str
-    default: ""
-    description: Optional web search tool description if available
----
-Task: {{ task_title }}
-Description: {{ task_description }}
-
-You are researching this task to identify relevant files and implementation details.
-You have access to the following tools:
-
-1. glob(pattern): Find files matching a pattern (e.g. "src/**/*.py")
-2. grep(pattern, path): Search for text in files (e.g. "def login", "src/")
-3. read_file(path): Read the content of a file
-4. done(reason): Finish research
-{{ search_tool_section }}
-
-Current Context:
-Found Files: {{ found_files }}
-Snippets: {{ snippets_keys }}
-
-History:
-{{ history }}
-
-Step {{ step }}/{{ max_steps }}. What is your next move? Respond with THOUGHT followed by ACTION.

gobby/prompts/defaults/validation/criteria.md

@@ -1,47 +0,0 @@
----
-name: validation-criteria
-description: Prompt for generating validation criteria from task description
-version: "1.0"
-variables:
-  title:
-    type: str
-    required: true
-    description: Task title
-  description:
-    type: str
-    default: "(no description)"
-    description: Task description
----
-Generate validation criteria for this task.
-
-Task: {{ title }}
-Description: {{ description }}
-
-CRITICAL RULES - You MUST follow these:
-1. **Only stated requirements** - Include ONLY requirements explicitly written in the title or description
-2. **No invented values** - Do NOT invent specific numbers, timeouts, thresholds, or limits unless they appear in the task
-3. **No invented edge cases** - Do NOT add edge cases, error scenarios, or boundary conditions beyond what's described
-4. **Proportional detail** - Vague tasks get vague criteria; detailed tasks get detailed criteria
-5. **When in doubt, leave it out** - If something isn't mentioned, don't include it
-
-For vague requirements like "fix X" or "add Y", use criteria like:
-- "X no longer produces the reported error/warning"
-- "Y functionality works as expected"
-- "Existing tests continue to pass"
-- "No regressions introduced"
-
-DO NOT generate criteria like:
-- "timeout defaults to 30 seconds" (unless 30 seconds is in the task description)
-- "handles edge case Z" (unless Z is mentioned in the task)
-- "logs with format X" (unless that format is specified)
-
-Format as markdown checkboxes:
-## Deliverable
-- [ ] What the task explicitly asks for
-
-## Functional Requirements
-- [ ] Only requirements stated in the description
-
-## Verification
-- [ ] Tests pass (if applicable)
-- [ ] No regressions

gobby/prompts/defaults/validation/validate.md

@@ -1,38 +0,0 @@
----
-name: validation-validate
-description: Base prompt for validating task completion against criteria
-version: "1.0"
-variables:
-  title:
-    type: str
-    required: true
-    description: Task title
-  category_section:
-    type: str
-    default: ""
-    description: Optional category/test strategy section
-  criteria_text:
-    type: str
-    required: true
-    description: Validation criteria or task description
-  changes_section:
-    type: str
-    required: true
-    description: Summary of changes made (files, diffs, etc.)
-  file_context:
-    type: str
-    default: ""
-    description: Optional file content context
----
-Validate if the following changes satisfy the requirements.
-
-Task: {{ title }}
-{{ category_section }}{{ criteria_text }}
-
-{{ changes_section }}
-IMPORTANT: Return ONLY a JSON object, nothing else. No explanation, no preamble.
-Format: {"status": "valid", "feedback": "..."} or {"status": "invalid", "feedback": "..."}
-{% if file_context %}
-File Context:
-{{ file_context }}
-{% endif %}