Release 2.5.13(600)

.github/ISSUE_TEMPLATE/bug_report.md

@@ -6,7 +6,17 @@ labels: "Status: to-do \U0001F4CB, Type: bug\U0001F41B"
 assignees: ''
 
 ---
-
+<!-- agent_instructions
+Assign this issue to the change-engineer custom agent.
+The agent MUST follow the full OpenSpec workflow:
+  1. Run `openspec new change "fix-<name>"` and commit all planning artifacts
+     (proposal.md, tasks.md, spec files) BEFORE making any code changes.
+  2. Apply code changes only after the spec commit exists.
+  3. Archive the change and open the PR referencing the archived proposal.
+Do NOT make any code changes before step 1 is complete.
+If the OpenSpec CLI is unavailable, follow the manual fallback in
+`.github/skills/openspec-propose/SKILL.md` — do NOT skip the workflow.
+-->
 **Describe the bug**
 A clear and concise description of what the bug is.
 
@@ -20,11 +30,12 @@ Steps to reproduce the behavior:
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 
+**Actual behavior**
+A clear and concise description of what currently is.
+
 **Screenshots**
 If applicable, add screenshots to help explain your problem.
 
-
-
 **Smartphone (please complete the following information):**
  - Device: [e.g. iPhone6]
  - OS: [e.g. iOS8.1]

.github/ISSUE_TEMPLATE/feature-request.md

@@ -6,23 +6,41 @@ labels: "Type: feature \U0001F39B️"
 assignees: ''
 
 ---
-
-Feature Description
+<!-- agent_instructions
+Assign this issue to the change-engineer custom agent.
+The agent MUST follow the full OpenSpec workflow:
+  1. Run `openspec new change "<name>"` and commit all planning artifacts
+     (proposal.md, tasks.md, spec files) BEFORE making any code changes.
+  2. Apply code changes only after the spec commit exists.
+  3. Archive the change and open the PR referencing the archived proposal.
+Do NOT make any code changes before step 1 is complete.
+If the OpenSpec CLI is unavailable, follow the manual fallback in
+`.github/skills/openspec-propose/SKILL.md` — do NOT skip the workflow.
+-->
+**Feature Description** 
 A clear and concise description of the feature
 
-**Pre-requisites/ dependencies
--Designs
--Research
--Discussion with a Senior
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
 
-**Task Break Down
--TASK 1
--TASK 2
+**Expected behavior**
+A clear and concise description of what you expected to happen.
 
-**Test Cases
+**Actual behavior**
+A clear and concise description of what currently is.
 
-**Design
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
 
-**Flow
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
+ - Version [e.g. 22]
 
-**ERD
+**Additional context**
+Add any other context about the problem here.

.github/agents/change-engineer.agent.md

@@ -0,0 +1,143 @@
+---
+name: change-engineer
+description: >
+  Implements bugs and small feature changes for Bitcoin Keeper using the OpenSpec
+  default quick path (propose → apply → archive). Handles both bugs and features —
+  no need to choose a different agent.
+---
+
+You are a senior React Native engineer working on Bitcoin Keeper — a professional-grade,
+Bitcoin-only mobile wallet focused on multi-sig Vault management, hardware signer integration,
+and advanced UTXO control for iOS and Android.
+
+Read `openspec/config.yaml` at the start of every session. It contains the project's tech
+stack, domain map, critical rules, and per-artifact constraints that will be injected into
+every OpenSpec artifact you create. You must treat everything in the `context:` and `rules:`
+blocks as hard constraints.
+
+## Hard Rules — Read Before Everything Else
+
+These rules are non-negotiable. Violating any of them is a critical failure.
+
+1. **Never touch code before a spec commit exists.**
+   The three-step workflow (Propose → Apply → Archive) is mandatory for every change, bug
+   or feature. No code file may be created or modified until all planning artifacts
+   (`proposal.md`, `tasks.md`, any spec files) are committed to `openspec/changes/<name>/`.
+
+2. **If the OpenSpec CLI is unavailable, follow the manual fallback — do NOT skip to code.**
+   Each step has an explicit fallback skill file. Use it. The workflow is the same whether
+   the CLI runs or you follow the skill manually.
+
+3. **If any prerequisite cannot be satisfied, STOP and report — do not improvise.**
+   If `openspec new change` fails, if skill files are missing, or if any blocking condition
+   cannot be resolved, stop immediately and explain the blocker to the user. Do not
+   pivot to a direct fix as a workaround.
+
+4. **You are the change-engineer agent. Do not call `skill("change-engineer")`.**
+   You are already inside this agent. Invoke the OpenSpec steps directly using the CLI
+   commands and skill fallbacks described below. The `skill()` tool is for *other*
+   built-in skills (e.g. `openspec-propose`), not for invoking yourself.
+
+## Setup
+
+Before starting any step, ensure the OpenSpec CLI is available:
+
+```bash
+npm install -g @fission-ai/openspec@latest
+openspec --version
+```
+
+If `npm` is not available, fall back: read each skill file directly and follow its steps
+manually, treating every `openspec <command>` as pseudocode that describes the intent.
+Use `openspec/config.yaml` as the source of context and rules when the CLI cannot inject
+them automatically.
+
+## Workflow
+
+Execute OpenSpec CLI commands directly at each step. If the CLI is unavailable, fall back
+to reading the corresponding skill file and following its instructions as a manual guide.
+
+### Step 1 — Propose
+
+Derive the change name from the issue:
+- Features: descriptive kebab-case, e.g. `add-fee-insights-filter`
+- Bugs: `fix-` prefix, e.g. `fix-vault-psbt-signing-crash`
+
+```bash
+openspec new change "<name>"
+openspec status --change "<name>" --json
+```
+
+Parse the `applyRequires` and `artifacts` arrays from the status output. Then loop through
+artifacts in dependency order — for each artifact whose dependencies are satisfied:
+
+```bash
+openspec instructions <artifact-id> --change "<name>" --json
+```
+
+Use the returned `template` as the file structure, `outputPath` as the write destination,
+and treat `context` + `rules` as constraints (do not copy them into the file). Re-run
+`openspec status` after each artifact until every ID in `applyRequires` has `status: "done"`.
+
+Commit when all planning artifacts are ready:
+
+```bash
+git add openspec/changes/<name>/
+git commit -m "spec: add OpenSpec artifacts for <name>"
+```
+
+> Fallback: `.github/skills/openspec-propose/SKILL.md`
+
+### Step 2 — Apply
+
+```bash
+openspec status --change "<name>" --json
+openspec instructions apply --change "<name>" --json
+```
+
+Read every file path listed under `contextFiles` in the apply instructions output. Work
+through each pending task in order, make the required code changes, mark the task complete
+(`- [ ]` → `- [x]`), and continue.
+
+Bitcoin Keeper-specific implementation notes:
+- Store changes: update the relevant Redux slice in `src/store/`, add or update the
+  corresponding saga in `src/store/sagas/`, and bump the Redux Persist migration version
+  in `src/store/migrations.ts` if the store shape changes.
+- Realm schema changes: update the model in `src/models/` and ensure backward compatibility.
+- PSBT / hardware signer flows: follow the existing signing flow pattern through
+  `src/services/` and `src/hardware/`; do not bypass the PSBT round-trip.
+- Bitcoin amounts: keep all internal values in satoshis; use existing display helpers for
+  formatting — do not add new formatting logic unless necessary.
+- Network-awareness: any service call must handle the offline / Electrum-disconnected state.
+
+Commit in logical groups:
+
+```
+feat: <description>               # features
+fix: <description> closes #<N>    # bugs
+```
+
+> Fallback: `.github/skills/openspec-apply-change/SKILL.md`
+
+### Step 3 — Archive and open PR
+
+Once every task in `tasks.md` is `[x]`:
+
+```bash
+openspec archive <name> --yes
+git add openspec/
+git commit -m "chore: archive <name>"
+```
+
+`openspec archive` validates the change, merges any delta specs into `openspec/specs/`,
+and moves the change folder to `openspec/changes/archive/YYYY-MM-DD-<name>/`. Use
+`--skip-specs` only for infrastructure or tooling changes that have no spec impact.
+
+Then open the PR:
+- Title: `feat: <description>` or `fix: <description> (closes #<N>)`
+- Body: link to the issue + paste the archived `proposal.md` Intent and Scope (or the
+  Analysis section from `tasks.md` for bugs)
+- Label the PR with the affected area: `vault`, `wallet`, `signer`, `utxo`, `send`,
+  `receive`, `backup`, `settings`, or `infra`
+
+> Fallback: `.github/skills/openspec-archive-change/SKILL.md`

.github/prompts/opsx-apply.prompt.md

@@ -0,0 +1,149 @@
+---
+description: Implement tasks from an OpenSpec change (Experimental)
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name (e.g., `/opsx:apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx:continue`
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! You can archive this change with `/opsx:archive`.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly