@ultrakit/ultrakit 0.0.0

package/dist/template/.opencode/dcp-prompts/overrides/compress-message.md

@@ -0,0 +1,71 @@
+Collapse selected individual messages in the conversation into detailed summaries.
+
+THE SUMMARY
+Your summary must be EXHAUSTIVE. Use the following 9-section structure to ensure nothing is lost.
+Capture file paths, function signatures, decisions made, constraints discovered, key findings, tool outcomes, and user intent details that matter... EVERYTHING that preserves the value of the selected message after the raw message is removed.
+
+STRUCTURED SUMMARY FORMAT
+When summarizing each message, organize findings into these sections (omit empty sections):
+
+1. **Primary Request** — What the user actually wants. Quote exact instructions when short.
+2. **Key Technical Concepts** — Decisions made, constraints discovered, architecture choices, patterns identified.
+3. **Files and Code** — Exact file paths with line numbers (`path/file.ts:42-67`). Function signatures. Code snippets critical to understanding.
+4. **Errors and Fixes** — What broke, root cause, what fixed it. Include error messages verbatim when diagnostic.
+5. **Problem Solving** — Approaches tried (including failures). What worked and why.
+6. **User Messages** — Preserve exact user intent. Directly quote short user instructions when that best preserves meaning.
+7. **Pending Tasks** — Incomplete work with current status.
+8. **Current Work** — What's actively happening right now.
+9. **Next Step** — What should happen next (if clear from context).
+
+USER INTENT FIDELITY
+When a selected message contains user intent, preserve that intent with extra care. Do not change scope, constraints, priorities, acceptance criteria, or requested outcomes.
+Directly quote short user instructions when that best preserves exact meaning.
+
+Yet be LEAN. Strip away the noise: failed attempts that led nowhere, verbose tool output, and repetition. What remains should be pure signal — golden nuggets of detail that preserve full understanding with zero ambiguity.
+
+MESSAGE IDS
+You specify individual raw messages by ID using the injected IDs visible in the conversation:
+
+- `mNNNN` IDs identify raw messages
+
+Each message has an ID inside XML metadata tags like `<dcp-message-id priority="high">m0007</dcp-message-id>`.
+The ID tag appears at the end of the message it belongs to — each ID covers all the content above it back to the previous ID.
+Treat these tags as message metadata only, not as content to summarize. Use only the inner `mNNNN` value as the `messageId`.
+The `priority` attribute indicates relative context cost. Prefer higher-priority closed messages before lower-priority ones.
+Messages marked as `<dcp-message-id>BLOCKED</dcp-message-id>` cannot be compressed.
+
+Rules:
+
+- Pick each `messageId` directly from injected IDs visible in context.
+- Only use raw message IDs of the form `mNNNN`.
+- Ignore XML attributes such as `priority` when copying the ID; use only the inner `mNNNN` value.
+- Do NOT use compressed block IDs like `bN`.
+- Do not invent IDs. Use only IDs that are present in context.
+- Do not target prior compressed blocks or block summaries.
+
+BATCHING
+Select MANY messages in a single tool call when they are independently safe to compress.
+Each entry should summarize exactly one message, and the tool can receive as many entries as needed in one batch.
+When several messages are equally safe to compress, prefer higher-priority messages first.
+
+Because each message is compressed independently:
+
+- Do not describe ranges
+- Do not use start/end boundaries
+- Do not use compressed block placeholders
+- Do not reference prior compressed blocks with `(bN)`
+
+THE FORMAT OF COMPRESS
+
+```
+{
+  topic: string,           // Short label (3-5 words) for the overall batch
+  content: [               // One or more messages to compress independently
+    {
+      messageId: string,   // Raw message ID only: mNNNN (ignore metadata attributes like priority)
+      topic: string,       // Short label (3-5 words) for this one message summary
+      summary: string      // Complete technical summary replacing that one message (use 9-section format above)
+    }
+  ]
+}
+```

package/dist/template/.opencode/dcp.jsonc

@@ -0,0 +1,115 @@
+{
+	"$schema": "https://raw.githubusercontent.com/Opencode-DCP/opencode-dynamic-context-pruning/master/dcp.schema.json",
+	"enabled": true,
+	"debug": false,
+	// "off" | "minimal" | "detailed" — keep minimal for low-noise dev flow
+	"pruneNotification": "minimal",
+	// "chat" (in-conversation) or "toast" (system notification)
+	"pruneNotificationType": "toast",
+	// Slash commands: /dcp context, /dcp stats, /dcp sweep, /dcp compress, /dcp decompress, /dcp recompress
+	"commands": {
+		"enabled": true,
+		// Additional tools to protect from /dcp sweep (supports glob wildcards)
+		"protectedTools": ["observation", "memory-*"]
+	},
+	// Manual mode: disables autonomous context management
+	"manualMode": {
+		"enabled": false,
+		"automaticStrategies": true
+	},
+	// Protect recent tool outputs from pruning
+	"turnProtection": {
+		"enabled": false,
+		"turns": 4
+	},
+	// Glob patterns for files that should never be auto-pruned
+	// Keep tight: broad patterns reduce DCP effectiveness
+	// .opencode/** and .beads/** removed — memory-* and tilth_* outputs
+	// already survive compression via compress.protectedTools
+	"protectedFilePatterns": [
+		"**/.env*",
+		"**/AGENTS.md",
+		"**/package.json",
+		"**/tsconfig.json"
+	],
+	// Unified context compression tool (v3.1.0)
+	"compress": {
+		// "range" (stable) compresses spans into block summaries
+		// "message" (experimental) compresses individual raw messages
+		"mode": "range",
+		// "allow" (no prompt) | "ask" (prompt) | "deny" (tool not registered)
+		"permission": "allow",
+		"showCompression": false,
+		// v3.1.0: active summary tokens extend effective maxContextLimit
+		"summaryBuffer": true,
+		// Soft upper threshold: above this, strong compression nudges fire
+		// Use numeric values — percentage requires modelContextLimit from runtime
+		// which may be unavailable for some provider/model combos (e.g. GitHub Copilot)
+		// Rule: must be BELOW OpenCode emergency threshold (model_max - reserved - max_output)
+		// For Copilot Claude (216k ctx, 64k out, 16k reserved): emergency = 136k
+		// So DCP must start compressing well before 136k
+		"maxContextLimit": 100000,
+		// Per-model override for maxContextLimit (takes priority over global)
+		"modelMaxLimits": {
+			// Claude: 216k ctx, 64k out → emergency at 136k → DCP starts at 110k
+			"github-copilot/claude-opus-4.6": 110000,
+			"github-copilot/claude-opus-4.5": 110000,
+			"github-copilot/claude-sonnet-4.6": 110000,
+			"github-copilot/claude-sonnet-4.5": 110000,
+			"github-copilot/claude-sonnet-4": 110000,
+			// Haiku: smaller model, be more conservative
+			"github-copilot/claude-haiku-4.5": 90000,
+			// GPT/Gemini: assume similar 200k+ windows
+			"github-copilot/gpt-5.4": 110000,
+			"github-copilot/gpt-5.3-codex": 110000,
+			"github-copilot/gemini-3.1-pro-preview": 110000
+		},
+		// Soft lower threshold: below this, turn/iteration reminders are off
+		// Use numeric values — same reason as maxContextLimit above
+		"minContextLimit": 50000,
+		// Per-model override for minContextLimit (takes priority over global)
+		"modelMinLimits": {
+			"github-copilot/claude-opus-4.6": 65000,
+			"github-copilot/claude-opus-4.5": 65000,
+			"github-copilot/claude-sonnet-4.6": 65000,
+			"github-copilot/claude-sonnet-4.5": 65000,
+			"github-copilot/claude-sonnet-4": 65000,
+			"github-copilot/claude-haiku-4.5": 50000,
+			"github-copilot/gpt-5.4": 65000,
+			"github-copilot/gpt-5.3-codex": 65000,
+			"github-copilot/gemini-3.1-pro-preview": 65000
+		},
+		// How often context-limit nudge fires above maxContextLimit (1 = every fetch)
+		"nudgeFrequency": 5,
+		// Messages since last user message before adding compression reminders
+		"iterationNudgeThreshold": 15,
+		// "strong" = more likely to compress, "soft" = less likely
+		"nudgeForce": "soft",
+		// Keep user messages compressible to avoid permanent context growth
+		"protectUserMessages": false,
+		// Auto-protected by DCP: task, skill, todowrite, todoread, compress, batch, plan_enter, plan_exit, write, edit
+		// Only list ADDITIONAL tools whose outputs should be appended to compression summaries
+		"protectedTools": ["observation", "memory-*", "tilth_*"]
+	},
+	// Experimental features
+	"experimental": {
+		// Allow DCP processing in subagent sessions (default: false)
+		"allowSubAgents": false,
+		// Enable user-editable prompt overrides under dcp-prompts directories
+		"customPrompts": true
+	},
+	// Automatic pruning strategies (zero LLM cost)
+	"strategies": {
+		// Removes duplicate tool calls (same tool + same arguments), keeps most recent
+		"deduplication": {
+			"enabled": true,
+			"protectedTools": []
+		},
+		// Prunes inputs from errored tool calls after N turns (error messages preserved)
+		"purgeErrors": {
+			"enabled": true,
+			"turns": 4,
+			"protectedTools": []
+		}
+	}
+}

package/dist/template/.opencode/memory/README.md

@@ -0,0 +1,89 @@
+---
+purpose: PARA-organized memory system with SQLite backing
+updated: 2026-02-04
+---
+
+# Project Memory
+
+Multi-layer memory system combining PARA organization with SQLite + FTS5 search.
+
+## Directory Structure
+
+```
+memory/
+├── project/           # Tacit knowledge (always-injected context)
+│   ├── user.md        # User preferences, identity
+│   ├── tech-stack.md  # Framework, dependencies, constraints
+│   └── gotchas.md     # Footguns, edge cases, warnings
+├── knowledge/         # PARA-organized reference (curated)
+│   ├── projects/      # Active work with deadlines
+│   ├── areas/         # Ongoing responsibilities
+│   ├── resources/     # Reference material
+│   └── archives/      # Completed/inactive items
+├── daily/             # Chronological session logs
+├── research/          # Deep-dive analysis documents
+├── handoffs/          # Session handoff context
+└── _templates/        # File templates
+```
+
+## Memory Layers (3-Layer Architecture)
+
+| Layer               | Location      | Purpose                 | Access                             |
+| ------------------- | ------------- | ----------------------- | ---------------------------------- |
+| **Knowledge Graph** | SQLite + FTS5 | Searchable observations | `memory-search()`, `observation()` |
+| **Daily Notes**     | `daily/`      | Chronological narrative | Manual review                      |
+| **Tacit Knowledge** | `project/`    | Always-present context  | Auto-injected                      |
+
+## SQLite Memory Tools
+
+| Tool                | Purpose                                       |
+| ------------------- | --------------------------------------------- |
+| `observation()`     | Write structured observations to SQLite       |
+| `memory-search()`   | FTS5 full-text search (returns compact index) |
+| `memory-get()`      | Fetch full observation details by ID          |
+| `memory-timeline()` | Get chronological context around anchor       |
+| `memory-update()`   | Update markdown files in memory               |
+
+## PARA Categories
+
+- **Projects**: Active work with deadlines → `knowledge/projects/`
+- **Areas**: Ongoing responsibilities → `knowledge/areas/`
+- **Resources**: Reference material → `knowledge/resources/`
+- **Archives**: Completed/inactive → `knowledge/archives/`
+
+## Memory Tiers (Decay-based)
+
+| Tier     | Access Pattern | Location                   |
+| -------- | -------------- | -------------------------- |
+| **Hot**  | Daily/Weekly   | Active SQLite + `project/` |
+| **Warm** | Monthly        | `knowledge/` directories   |
+| **Cold** | Rarely         | `knowledge/archives/`      |
+
+## Workflow
+
+### Session Start
+
+1. `memory-search()` - Find relevant context
+2. Read `project/` files (auto-injected)
+3. Check `daily/` for recent sessions if needed
+
+### During Work
+
+1. Use `observation()` for decisions, patterns, gotchas
+2. Update `project/gotchas.md` for footguns
+3. Add to `knowledge/` for curated reference
+
+### Session End
+
+1. Summary appended to `daily/YYYY-MM-DD.md`
+2. Sync beads: `br sync --flush-only`
+
+## Philosophy
+
+**Three-layer memory beats single-layer:**
+
+- SQLite for searchability (Knowledge Graph)
+- Daily notes for context (Chronological)
+- Project files for presence (Tacit Knowledge)
+
+Each layer serves a different retrieval pattern.

package/dist/template/.opencode/memory/_templates/design.md

@@ -0,0 +1,59 @@
+# Design Document
+
+**Bead ID:** [bead-id]
+**Created:** [date]
+**Status:** Draft | Validated
+
+## Problem Statement
+
+What we're solving and why it matters:
+
+## Approaches Considered
+
+### Option A: [Name]
+
+- **Pros:** [advantages]
+- **Cons:** [drawbacks]
+
+### Option B: [Name]
+
+- **Pros:** [advantages]
+- **Cons:** [drawbacks]
+
+### Chosen Approach
+
+[Which option and why]
+
+## Architecture
+
+High-level structure and how components fit together:
+
+### Components
+
+- [Component 1]: [purpose]
+- [Component 2]: [purpose]
+
+### Data Flow
+
+[How data moves through the system]
+
+## Error Handling
+
+How the design handles failure cases:
+
+- [Error scenario 1]: [handling approach]
+- [Error scenario 2]: [handling approach]
+
+## Testing Strategy
+
+How we'll validate this design works:
+
+- [Testing approach 1]
+- [Testing approach 2]
+
+## Open Questions
+
+Unresolved items to address during implementation:
+
+- [ ] [Question 1]
+- [ ] [Question 2]

package/dist/template/.opencode/memory/_templates/prd.md

@@ -0,0 +1,203 @@
+# Beads PRD Template
+
+> **Template Instructions:**
+>
+> - Replace ALL bracketed placeholders with real content
+> - If you cannot fill a section with confidence, use `[NEEDS CLARIFICATION: reason]` instead of guessing
+> - Any `[NEEDS CLARIFICATION]` markers MUST be resolved before planning can proceed
+> - Delete this instruction block after filling the template
+
+**Bead:** br-[id]  
+**Created:** [date]  
+**Status:** Draft | In Review | Approved
+
+## Bead Metadata
+
+```yaml
+depends_on: [] # Bead IDs that must complete before this one
+parallel: true # Can run concurrently with other parallel beads
+conflicts_with: [] # Bead IDs that modify same files (cannot parallelize)
+blocks: [] # Bead IDs waiting on this one
+estimated_hours: 2 # Time estimate for planning
+```
+
+---
+
+## Problem Statement
+
+### What problem are we solving?
+
+[Clear description of the problem. Include user impact and business impact. If unclear, use [NEEDS CLARIFICATION: what specifically is unknown]]
+
+### Why now?
+
+[What triggered this work? Cost of inaction? Use [NEEDS CLARIFICATION] if motivation is unclear]
+
+### Who is affected?
+
+- **Primary users:** [Description]
+- **Secondary users:** [Description]
+
+---
+
+## Scope
+
+### In-Scope
+
+- [List what's in scope. Use [NEEDS CLARIFICATION] for ambiguous boundaries]
+
+### Out-of-Scope
+
+- [List what's explicitly off-limits. Use [NEEDS CLARIFICATION] for unresolved scope questions]
+- [Deferred to future iterations]
+
+---
+
+## Proposed Solution
+
+### Overview
+
+[One paragraph describing what this feature does when complete. Use [NEEDS CLARIFICATION] for uncertain design decisions]
+
+### User Flow (if user-facing)
+
+1. [Step 1]
+2. [Step 2]
+3. [Step 3]
+
+---
+
+## Requirements
+
+### Functional Requirements
+
+#### [Requirement Name]
+
+Brief description of what must be true.
+
+**Scenarios:**
+
+- **WHEN** [precondition or trigger] **THEN** [expected outcome]
+- **WHEN** [edge case condition] **THEN** [expected behavior]
+
+### Non-Functional Requirements
+
+- **Performance:** [constraint if applicable]
+- **Security:** [constraint if applicable]
+- **Accessibility:** [WCAG level if applicable]
+- **Compatibility:** [constraint if applicable]
+
+> If any requirement is unknown or unresearched, mark it `[NEEDS CLARIFICATION: what needs investigation]` rather than omitting it.
+
+---
+
+## Success Criteria
+
+- [ ] [Specific, measurable criterion 1]
+  - Verify: `[command or manual check]`
+- [ ] [Specific, measurable criterion 2]
+  - Verify: `[command or manual check]`
+
+---
+
+## Technical Context
+
+### Existing Patterns
+
+- Pattern 1: `src/path/to/example.ts` - Why relevant
+
+### Key Files
+
+- `src/relevant/file.ts` - Why relevant
+
+### Affected Files
+
+Files this bead will modify (for conflict detection):
+
+```yaml
+files:
+  - src/path/to/file.ts # Why
+  - src/path/to/other.ts # Why
+```
+
+---
+
+## Risks & Mitigations
+
+| Risk   | Likelihood   | Impact       | Mitigation      |
+| ------ | ------------ | ------------ | --------------- |
+| Risk 1 | High/Med/Low | High/Med/Low | How to mitigate |
+
+---
+
+## Open Questions
+
+| Question   | Owner | Due Date | Status        |
+| ---------- | ----- | -------- | ------------- |
+| Question 1 | Name  | Date     | Open/Resolved |
+
+> **All `[NEEDS CLARIFICATION]` markers should be converted to entries in this table for tracking.**
+
+---
+
+## Tasks
+
+Write tasks in a machine-convertible format for `prd-task` skill.
+
+**Rules:**
+
+- Each task is a `### <Title> [category]` heading
+- Provide one sentence describing the end state
+- Include `**Metadata:**` with dependency info
+- Include `**Verification:**` with bullet steps proving it works
+
+### <Task Title> [category]
+
+<One sentence describing the end state>
+
+**Metadata:**
+
+```yaml
+depends_on: [] # Task titles that must complete first
+parallel: true # Can run with other parallel tasks
+conflicts_with: [] # Task titles modifying same files
+files: [] # Files this task will modify
+```
+
+**Verification:**
+
+- [Command or check]
+- [Command or check]
+
+### <Task Title> [category]
+
+<One sentence describing the end state>
+
+**Metadata:**
+
+```yaml
+depends_on: ["<Previous Task Title>"]
+parallel: false
+files: []
+```
+
+**Verification:**
+
+- [Command or check]
+
+---
+
+## Dependency Legend
+
+| Field            | Purpose                                           | Example                                    |
+| ---------------- | ------------------------------------------------- | ------------------------------------------ |
+| `depends_on`     | Must complete before this task starts             | `["Setup database", "Create schema"]`      |
+| `parallel`       | Can run concurrently with other parallel tasks    | `true` / `false`                           |
+| `conflicts_with` | Cannot run in parallel (same files)               | `["Update config"]`                        |
+| `files`          | Files this task modifies (for conflict detection) | `["src/db/schema.ts", "src/db/client.ts"]` |
+
+---
+
+## Notes
+
+[Additional context, constraints, or decisions]

package/dist/template/.opencode/memory/_templates/project.md

@@ -0,0 +1,58 @@
+---
+purpose: Project vision, goals, and success criteria (loaded into all AI contexts)
+updated: 2024-12-21
+---
+
+# Project Vision
+
+## The Goal
+
+<!-- One sentence: What does this project achieve? Outcome-shaped, not task-shaped. -->
+<!-- Good: "A real-time chat application with persistent message history" -->
+<!-- Bad: "Build chat components and API endpoints" -->
+
+## Success Criteria
+
+<!-- How do we know the project is successful? List 3-7 observable outcomes. -->
+<!-- Each should be verifiable by using the application, not by checking code. -->
+
+1. **[Criterion 1]** - [Specific, measurable outcome]
+2. **[Criterion 2]** - [Specific, measurable outcome]
+3. **[Criterion 3]** - [Specific, measurable outcome]
+
+## Target Users
+
+<!-- Who will use this? What do they need? -->
+
+- **Primary:** [User type and their core need]
+- **Secondary:** [User type and their core need]
+
+## Core Principles
+
+<!-- Non-negotiable principles that guide all decisions -->
+
+1. **[Principle 1]** - [Explanation]
+2. **[Principle 2]** - [Explanation]
+3. **[Principle 3]** - [Explanation]
+
+## Current Phase
+
+<!-- Where are we in the project lifecycle? -->
+
+- **Status:** [Discovery / Planning / Implementation / Polish / Maintenance]
+- **Milestone:** [Current milestone name]
+- **Next Milestone:** [Next milestone name]
+
+## Key Links
+
+<!-- Important references -->
+
+- **Repository:** [URL]
+- **Documentation:** [URL]
+- **Staging:** [URL]
+- **Production:** [URL]
+
+---
+
+_Update this file when project direction or phase changes._
+_AI uses this to maintain context across sessions and make decisions aligned with project goals._

package/dist/template/.opencode/memory/_templates/proposal.md

@@ -0,0 +1,38 @@
+# Proposal
+
+**Bead:** [bead-id]
+**Author:** [author]
+**Date:** [YYYY-MM-DD]
+
+## Why
+
+<!-- What problem does this solve? Why now? -->
+
+## What Changes
+
+<!-- High-level description of the proposed changes -->
+
+## Capabilities
+
+### New Capabilities
+
+- `capability-name`: Brief description of what it enables
+
+### Modified Capabilities
+
+- `capability-name`: How existing behavior changes
+
+## Impact
+
+### Users Affected
+
+- [User type or system]
+
+### Migration Required
+
+- [ ] Yes / No
+- If yes: [brief migration notes]
+
+## Open Questions
+
+- [ ] [Question that needs answering before proceeding]