363 lines
27 KiB
Markdown
363 lines
27 KiB
Markdown
<!--
|
||
GENERATED BY KRI AGENT HARNESS. DO NOT EDIT DIRECTLY.
|
||
Project: kart-front-next
|
||
Schema version: 1
|
||
Edit the source fragments or repository .agent files, then recompose.
|
||
-->
|
||
|
||
# KRI Development Base Instructions
|
||
|
||
This document defines the shared working rules for KRI development repositories.
|
||
Keep project-specific facts and commands in the project profile and project rules.
|
||
|
||
## Instruction Resolution
|
||
|
||
Apply repository instructions in this order:
|
||
|
||
1. Base rules
|
||
2. Project-type rules
|
||
3. Technology-stack rules
|
||
4. Shared consumer contracts
|
||
5. Project-specific rules
|
||
6. The explicitly approved task scope
|
||
|
||
Later and more specific instructions may override earlier general instructions only within their stated scope.
|
||
|
||
- Apply a shared consumer contract only when `.agent/profile.yml` declares it.
|
||
- Do not silently resolve a material instruction conflict. Report the conflicting rules and request a decision before changing files.
|
||
- Rules involving destructive actions, credentials, external systems, production, deployment, databases, or Git publication require explicit authorization even when a later rule is less restrictive.
|
||
|
||
## Communication
|
||
|
||
- Respond to the user in Korean unless the user requests another language.
|
||
- Keep code identifiers, commands, paths, protocol names, and external API terms in their original form.
|
||
- Follow the repository's existing language conventions for code comments and user-facing messages.
|
||
- Lead with the result or decision, then provide only the detail needed to verify it.
|
||
- Do not create or retain a full session transcript.
|
||
|
||
### Attention-Aware Response Style
|
||
|
||
- Use `attention-aware-communication` for substantive answers, progress updates, and completion reports.
|
||
- Default to concise, bottom-line-first Korean without omitting a condition, risk, number, or uncertainty needed for a correct decision.
|
||
- Give full detail when the user requests depth. Use Spartan style only when explicitly requested.
|
||
- Presentation rules never reduce investigation, implementation, validation, or reporting obligations.
|
||
|
||
## Work Authorization
|
||
|
||
- The default workflow is discussion first and explicit execution approval second.
|
||
- During discussion, perform only read-only investigation needed to understand the task and propose a concrete plan, unless the user prohibits inspection.
|
||
- Read-only investigation may include file inspection, code search, encoding checks, `git status`, `git diff`, `git log`, and sanitized official-documentation lookup.
|
||
- Before execution approval, do not edit files, install dependencies, run builds or tests, start services, connect to databases, or change local or external state.
|
||
- Before requesting approval, describe the intended scope, affected areas, validation plan, and material risks.
|
||
- Treat approval as limited to the presented scope. Pause and discuss again if the work materially expands.
|
||
- If the user explicitly requests immediate execution without prior discussion, the discussion gate may be skipped for the stated scope.
|
||
- Fast-track authorization does not implicitly authorize protected operations such as destructive commands, production changes, deployments, database mutations, Git publication, or external messages.
|
||
|
||
## Local Development Environment
|
||
|
||
- Primary OS: Windows 11.
|
||
- Primary shell: PowerShell.
|
||
- Use Git Bash only when the repository already depends on Bash or POSIX shell behavior.
|
||
- Prefer repository-provided wrappers and scripts over globally installed commands.
|
||
- Do not assume that GNU utilities, WSL, Docker, or a Unix-compatible shell are available unless the project profile confirms them.
|
||
- Detect Java, Node.js, .NET, Python, package-manager, and database-tool versions from repository configuration.
|
||
- Do not install or modify global toolchains as part of a project task.
|
||
|
||
Preferred human-facing tools:
|
||
|
||
- Classic ASP: Visual Studio Code
|
||
- Java and Spring Boot: IntelliJ IDEA
|
||
- C# and .NET: JetBrains Rider
|
||
- JavaScript, TypeScript, and Next.js: JetBrains WebStorm
|
||
- Python: JetBrains PyCharm
|
||
- Microsoft SQL Server: SQL Server Management Studio
|
||
- Other databases: JetBrains DataGrip
|
||
|
||
- These preferences do not authorize launching or controlling a GUI application.
|
||
- Prefer IDE-independent commands that can also run in CI.
|
||
- Do not modify global IDE settings.
|
||
- Do not create or modify `.idea`, `.vscode`, workspace, or run-configuration files unless the approved task requires it.
|
||
- Preserve existing shared IDE configuration when it is already tracked.
|
||
|
||
## PowerShell and Path Safety
|
||
|
||
- Quote paths containing spaces, brackets, parentheses, Korean characters, or PowerShell metacharacters.
|
||
- Prefer `-LiteralPath` when operating on an exact filesystem path.
|
||
- Use project-relative paths in committed configuration and documentation. Do not commit machine-specific paths such as `D:\_____Dev\...`.
|
||
- Do not pass filesystem targets between PowerShell, `cmd.exe`, and Bash for destructive or recursive operations.
|
||
- Keep a filesystem operation within one shell from target resolution through execution.
|
||
- Before a recursive delete or move, resolve and verify every absolute target.
|
||
- Never use a drive root, workspace root, user profile, unresolved variable, wildcard, or broad glob as a recursive delete target.
|
||
- Prefer recoverable operations when practical.
|
||
|
||
## Change Discipline
|
||
|
||
- Preserve all existing user changes, including uncommitted and untracked work.
|
||
- Keep changes minimal but complete for the approved objective.
|
||
- Avoid unrelated cleanup, formatting, renaming, dependency upgrades, and architectural refactoring.
|
||
- Do not overwrite or revert unrelated changes.
|
||
- Stop and report when the requested change overlaps existing work in a way that cannot be handled safely.
|
||
- Prefer changing an authoritative source over editing generated output.
|
||
- Treat files marked as generated as read-only unless regeneration is part of the approved plan.
|
||
- Do not edit vendored dependencies, build outputs, caches, or generated clients unless explicitly required.
|
||
- Do not regenerate a broad set of files for a narrow change without first explaining the expected output scope.
|
||
|
||
## Text Encoding and Korean Content Safety
|
||
|
||
- Treat the existing file encoding, BOM state, and line-ending style as part of the file's contract.
|
||
- Preserve Korean comments, user-facing messages, error messages, identifiers, and documentation exactly unless the task explicitly requires changing them.
|
||
- Do not assume that garbled terminal output means the file itself is corrupted. Verify bytes and encoding before modifying suspicious text.
|
||
- Before editing an existing text file, determine its current encoding and BOM state when repository configuration does not already guarantee them.
|
||
- Do not convert encoding, add or remove a BOM, or normalize line endings as a side effect of an unrelated change.
|
||
- Avoid whole-file rewrites for small changes.
|
||
- Do not rewrite source files through `Get-Content | Set-Content`, `Out-File`, shell redirection, or another method whose encoding behavior is implicit.
|
||
- Do not use a patching or formatting tool on a non-UTF-8 file unless it is known to preserve that file's encoding.
|
||
- Treat a console display problem and an on-disk encoding problem as separate issues.
|
||
- After editing Korean text, inspect the diff for replacement characters (`<60>`), mojibake, unexpected escapes, BOM changes, and unrelated line-ending changes.
|
||
- Run `.agent/tools/check-encoding.ps1` when it is available and the change touches Korean text or a non-default encoding.
|
||
- If encoding cannot be identified confidently, stop before writing and report the affected file and evidence.
|
||
- For a new text file, follow repository configuration. If no rule exists, use UTF-8 without BOM.
|
||
|
||
## Git Safety
|
||
|
||
- Use `git status`, `git diff`, and `git log` for read-only investigation.
|
||
- Do not run `commit`, `push`, `pull`, `fetch`, `merge`, `rebase`, `reset`, `checkout`, `switch`, `stash`, `clean`, `tag`, or force operations unless that specific operation is explicitly approved.
|
||
- Source-edit approval does not include commit or push approval.
|
||
- Never amend an existing commit unless explicitly requested.
|
||
- Before an approved commit, show the intended files, validation results, and proposed commit message.
|
||
- Never push directly to a protected branch unless the user names the target branch and explicitly authorizes the push.
|
||
|
||
## Dependencies and External Actions
|
||
|
||
- Use the package manager, lockfile, and toolchain already selected by the repository.
|
||
- Do not install global packages.
|
||
- Do not add, remove, or upgrade a dependency unless it was included in the approved plan.
|
||
- Pause for approval if an unplanned dependency becomes necessary.
|
||
- Keep lockfiles synchronized with approved dependency changes.
|
||
- Do not deploy, publish packages, create releases, send messages or email, call business APIs, or modify external services unless explicitly requested.
|
||
- Never upload proprietary source code, internal documents, credentials, customer data, or database contents to an external service.
|
||
- Remove secrets and unnecessary internal identifiers from external search queries.
|
||
|
||
## Database Safety
|
||
|
||
- Treat writing or reviewing SQL as source code separately from executing SQL against a database.
|
||
- SQL files, migrations, schema proposals, and query drafts may be created within an approved source-change scope.
|
||
- Do not connect to a shared, staging, or production database without explicit authorization for that environment.
|
||
- Read-only queries against a non-local database also require authorization because results may contain sensitive data.
|
||
- Do not execute DDL, DML, stored procedures, migrations, administrative commands, or data-correction scripts against a non-disposable database without separate authorization for the exact target and operation.
|
||
- Source-change approval does not authorize migration execution.
|
||
- Use a disposable local or test database for approved validation only after verifying its identity and disposable nature.
|
||
- Never place credentials, connection strings, or sensitive query results in source files, logs, generated documents, or chat output.
|
||
|
||
## Secrets and Sensitive Data
|
||
|
||
- Never add credentials, tokens, passwords, private keys, connection strings, session identifiers, or production data to source control.
|
||
- Read sensitive files only when the approved task requires it and no safer source exists.
|
||
- Prefer inspecting configuration keys and schemas without displaying secret values.
|
||
- Never echo secrets into terminal output, chat responses, logs, diffs, generated documents, test fixtures, or screenshots.
|
||
- Redact sensitive values when reporting errors or command output.
|
||
- If a possible secret is discovered, do not repeat it. Report only its location, type, and recommended containment action.
|
||
- Do not rotate, revoke, copy, or otherwise modify credentials unless that exact action is explicitly authorized.
|
||
|
||
## Workflow Skills
|
||
|
||
- Use `project-reference-loader` before substantive repository analysis, planning, implementation, debugging, or review. Read only the current project and shared references routed for that task, and reread them for each related task even if they were loaded earlier in the session.
|
||
- Use `karpathy-guidelines` when implementing, refactoring, or reviewing code. It keeps assumptions visible, changes surgical, and success criteria verifiable.
|
||
- Use `verification-before-completion` before claiming that work is complete, fixed, passing, ready, or safe to commit or publish.
|
||
- A skill does not expand task scope or authorize Git publication, database execution, deployment, destructive actions, or external communication.
|
||
|
||
## Validation
|
||
|
||
- Discover supported build, test, lint, type-check, and formatting commands from repository files and project instructions. Do not invent commands.
|
||
- Include intended validation in the discussion-phase plan.
|
||
- After approved changes, run the narrowest relevant validation first, then broader checks when appropriate.
|
||
- Limit formatting to files within the approved scope.
|
||
- Do not run tests that require a shared database, production service, paid external API, or sensitive data unless separately authorized.
|
||
- Do not claim that a check passed unless it was executed successfully.
|
||
- If a check cannot be run, state the exact reason.
|
||
- Distinguish a current-change failure from a pre-existing failure or an undetermined failure.
|
||
- Do not fix unrelated failures without expanding the approved scope.
|
||
- Inspect the worktree after validation for unexpected generated files, formatting churn, encoding changes, or lockfile changes.
|
||
|
||
## Artifacts and Session Records
|
||
|
||
- Do not create full-session transcripts, automatic HTML copies, analysis reports, or extra documentation unless explicitly requested.
|
||
- Store durable information in the repository's existing documentation structure.
|
||
- Do not place generated reports or temporary analysis files in the repository root.
|
||
- Remove task-specific temporary files created by the current task after validation when removal is safe.
|
||
|
||
## Completion Report
|
||
|
||
When implementation is complete, report in Korean:
|
||
|
||
- what changed and why;
|
||
- the main affected files or components;
|
||
- validation commands actually executed and their results;
|
||
- checks not executed and the reason;
|
||
- remaining risks, assumptions, or follow-up work;
|
||
- database, deployment, dependency, encoding, and compatibility impact when applicable.
|
||
|
||
- Do not report completion while required validation is failing or known encoding corruption is unresolved.
|
||
- Keep the report concise and do not include a full session transcript.
|
||
|
||
## Internal Service Project Rules
|
||
|
||
- Internal-only usage does not reduce security, privacy, compatibility, or validation requirements.
|
||
- Preserve authentication, authorization, role boundaries, auditability, and personal-data protections.
|
||
- Identify affected user workflows before changing visible behavior.
|
||
- Treat Frontend and Backend repositories as separate deployable systems with an explicit API contract between them.
|
||
- Coordinate request, response, authentication, error, and versioning changes across both sides when the approved scope includes both repositories.
|
||
- Do not silently require a simultaneous Frontend and Backend deployment.
|
||
- Prefer backward-compatible transitions when deployments may occur independently.
|
||
- Include migration and rollback considerations for database, API, and configuration changes.
|
||
- Do not modernize legacy code as an unrelated side effect.
|
||
- Apply Classic ASP text-safety rules only when the project profile declares the `classic-asp` stack.
|
||
- Do not access or modify production data merely because the service is internal.
|
||
|
||
## TypeScript
|
||
|
||
- Treat the repository's current TypeScript version, `tsconfig` files, module system, path aliases, and package manager as authoritative.
|
||
- Preserve or strengthen existing strictness. Do not weaken compiler options or hide errors with broad `any`, `@ts-ignore`, or unsafe assertions.
|
||
- Prefer narrow domain types, discriminated unions, and explicit boundary types over duplicated or overly generic shapes.
|
||
- Validate untrusted runtime input even when a compile-time type exists.
|
||
- Keep imports, exports, aliases, and generated-code boundaries consistent with the repository.
|
||
- Do not introduce a JavaScript-to-TypeScript conversion outside the approved scope.
|
||
- Run the repository's focused type-check, lint, test, and build commands as applicable.
|
||
|
||
## React
|
||
|
||
- Treat the current React version, component style, state management, routing, styling, and test approach as authoritative.
|
||
- Do not perform unrelated class-to-hook, JavaScript-to-TypeScript, state-library, styling-system, or React-to-Next.js migrations.
|
||
- Keep components focused and follow the repository's established split between presentation, state, data access, and side effects.
|
||
- Keep effects dependency-correct and clean up subscriptions, timers, listeners, and in-flight work where applicable.
|
||
- Use stable semantic keys and preserve accessibility, loading, empty, error, disabled, and success states.
|
||
- Preserve public component props and shared UI contracts unless a coordinated breaking change is explicitly approved.
|
||
- Treat any planned Next.js migration as a separate policy and task; the current React application remains authoritative until that migration slice is approved.
|
||
|
||
## Next.js
|
||
|
||
- Treat the repository's current Next.js and React versions, routing model, rendering model, and package manager as authoritative.
|
||
- Preserve server and client component boundaries. Add `use client` only when browser APIs, state, effects, or client-only libraries require it.
|
||
- Keep secrets, privileged data access, and server-only modules out of client bundles.
|
||
- Preserve established route, layout, middleware, authentication, authorization, caching, revalidation, and error-handling conventions.
|
||
- Validate request parameters, payloads, headers, cookies, and external responses at runtime.
|
||
- Do not create new frontend TypeScript type or interface names ending in `Dto` or `DTO`. Use domain- or purpose-specific names such as `User`, `UserInput`, `UserRequest`, or `UserResponse`; do not rename existing types solely to enforce this rule outside the approved scope.
|
||
- Use the approved KRI frontend and UI contracts when the project profile includes them; do not copy shared implementations into an application.
|
||
- Avoid incidental routing-model or rendering-strategy migrations.
|
||
- Run the repository's focused lint, type-check, test, and production build commands as applicable.
|
||
|
||
## KriFrontCommon Consumer Contract
|
||
|
||
- Consume the published `@kri/common` package only through entry points declared by its `package.json` `exports` map.
|
||
- Do not import from `@kri/common/src/*`, `@kri/common/dist/*`, or another undeclared deep path.
|
||
- Prefer a public shared helper or an approved backward-compatible library addition over copying or forking shared behavior locally.
|
||
- Do not modify KriFrontCommon or another consumer repository unless it is explicitly included in the approved task scope.
|
||
|
||
### Required Shared References
|
||
|
||
Before each related task, read the current contents of every matching reference, even if it was read earlier in the session.
|
||
|
||
| Task scope | Required reference |
|
||
|---|---|
|
||
| Package entry points, runtime boundaries, HTTP, authentication, state, storage, environment, or optional peer integrations | `.agent-harness/references/kri-front-common/package-and-runtime.md` |
|
||
| React rendering performance, memoization, or React Compiler behavior | `.agent-harness/references/kri-front-common/react-compiler.md` |
|
||
| Package upgrade, dependency changes, lockfile, or verification | `.agent-harness/references/kri-front-common/change-and-verification.md` |
|
||
|
||
If a task spans multiple scopes, read every matching reference. Generated files under `.agent-harness/references/` are read-only copies; edit KriFrontCommon's `.agent/consumer.md` or `.agent/consumer-references/` and recompose instead.
|
||
|
||
## Noti-hub SMS Types
|
||
|
||
- `MessageType.SMS = 21`, `LMS = 22`, `MMS = 23`; `ChannelType.SMS = 2` is unchanged. `SMS_TYPE_ARRAY` and `SmsType` include all three.
|
||
- `LMS_MMS = 22` remains a deprecated source-compatibility alias for LMS only. It does not represent MMS. Enum reverse lookup for 22 returns LMS. Use numeric bulk-list paths; the server no longer accepts LMS_MMS in paths. Numeric 21/22/23 bulk-list requests all return the entire SMS channel, not type-filtered lists.
|
||
- Requests retain their existing URLs/body shapes. The server chooses the actual type per recipient after substitution: attachment -> MMS; otherwise title or UTF-8 body >= 90 bytes -> LMS; otherwise SMS.
|
||
- Refresh templates from the save response (`tmplatTy`); display actual delivery types from `sendTy`, not the template or result code. A bulk can contain multiple SMS types. LMS/MMS share result codes; use existing server result labels.
|
||
- SMS, LMS, MMS and KKO use cancellation code 9998. Verify with `npm run typecheck`, `npm run build`, and `node --test tests/noti-hub-sms.test.mjs`.
|
||
|
||
## Noti-hub Reservation Cancellation
|
||
|
||
- Import cancellation types, constants, and helpers from `@kri/common/noti-hub` only. They are runtime-neutral and require no optional peers.
|
||
- Individual current cancellation state is determined by resultCode via isReserveCanceledResult; bulk current state is cancellationStatus (NONE/PARTIAL/ALL). These describe current cancellation state, not cancellation eligibility. cancelDt and cancelUser are request history, not current state.
|
||
- SendResultInfo, SendInfo, and BulkSendInfo expose optional cancelable. Use isSendCancelable(item), which returns true only for cancelable === true, for cancellation eligibility; missing values from older responses are treated as false. Never infer eligibility from cancelDt, result labels, or result codes.
|
||
- cancelable reflects query-time state and may change before cancellation. Determine the final outcome from SendCancelResponse counts.
|
||
- sendIdx is the single-cancel identifier, not cmid. It is absent from the latest abbreviated report (/api/v1/report/last/send/...). Request sendIdx must be a positive integer; bulkSendKey is required and at most 32 characters.
|
||
- EMAIL_RESERVE_CANCELED_RESULT_CODE is 108 for EMAIL. SMS_KKO_RESERVE_CANCELED_RESULT_CODE is 9998 for SMS, LMS, MMS, and KKO. Unknown message types are not recognized as canceled.
|
||
- Display the server's resultViewLabel/resultLabel ("예약 취소"). There is no separate result-code list API.
|
||
- HTTP 200 can contain notCancelableCount. parseSendCancelResponse validates nonnegative integer counts and targetCount = canceledCount + alreadyCanceledCount + notCancelableCount, throwing TypeError on invalid data. Bulk targetCount counts currently registered detail rows; response canceledCount counts only cancellations made by that request.
|
||
- Existing response fields are unchanged; all added fields on existing types are optional. Verify with npm run typecheck and npm run build.
|
||
|
||
## HTTP Streaming
|
||
|
||
- `@kri/common/http` HTTP clients expose streamGet/streamPost/streamPut/streamPatch/streamDel, returning HttpStreamResponse (status, statusText, headers, url, nullable body).
|
||
- Streaming shares ordinary authentication, URL, body and HTTP-error policy. Read body incrementally; no automatic JSON/NDJSON/SSE parsing or reconnect is performed.
|
||
- Streaming options accept an external AbortSignal. Caller cancellation raises AbortError without an HTTP error notification. Cancel the body when it will not be consumed.
|
||
- timeoutMs covers connection/headers (and an HTTP error body); idleTimeoutMs covers inactivity after successful headers and resets on consumed chunks. Both default to the client's defaultTimeoutMs (60 seconds by default), and 0 disables that timer for streaming only.
|
||
- Mid-stream transport/time-out errors reach the body reader. HTTP error statuses use existing HttpError handlers before a stream is returned. A 204 response has body=null.
|
||
- See HTTP_STREAMING.md for examples and node --test tests/http-stream.test.mjs for focused validation after npm run build.
|
||
|
||
## KriUiRegistry Consumer Contract
|
||
|
||
When implementing or changing frontend UI, use this order:
|
||
|
||
1. Reuse an existing shared component in the project when it already meets the requirement.
|
||
2. Prefer an approved component from KriUiRegistry.
|
||
3. Otherwise, prefer a suitable shadcn/ui component.
|
||
4. Create a custom component only when the preceding options cannot meet the requirement safely.
|
||
|
||
### KriAutoComplete Search Scroll
|
||
|
||
- `kri-auto-complete` exposes `resetScrollOnSearch?: boolean` on `KriSingleSelect`, `KriMultiSelect`, and `MultiSelect`. It defaults to `false`, preserving existing behavior.
|
||
- When enabled, a search value change (including clearing it) resets the option list scroll to the top on the next animation frame in both `filter` and `inputOnly` modes. Async result updates alone do not trigger another reset.
|
||
|
||
### KriAutoComplete Option Tooltip
|
||
|
||
- `kri-auto-complete` exposes `optionTooltip?: 'singleLine' | 'wrap'` and `optionTooltipClassName?: string` on `KriSingleSelect`, `KriMultiSelect`, and `MultiSelect`. It is off by default, preserving existing behavior.
|
||
- When enabled, hovering an option shows its full `label` in a right-side tooltip. `singleLine` stays on one line until the available viewport width; `wrap` wraps at 28rem. The item depends on the shadcn `tooltip` component and provides its own `TooltipProvider`.
|
||
|
||
### KriAutoComplete Search Match
|
||
|
||
- `kri-auto-complete` exposes `searchMatch?: 'fuzzy' | 'contains'` on `KriSingleSelect`, `KriMultiSelect`, and `MultiSelect`. It defaults to `fuzzy` (cmdk's default subsequence scoring), preserving existing behavior.
|
||
- `contains` keeps only options whose label or value contains the search text as a case-insensitive substring, in the original option order. It applies only when `searchMode` is `filter`.
|
||
|
||
### KriEditor SMS Preview
|
||
|
||
- `changeSmsType` reports `SMS | LMS | MMS`. Update consumer callbacks to handle `MMS`; this widens the previous callback contract.
|
||
- Attachment presence (`smsHasAttachment`) takes priority and reports MMS. Otherwise a title or UTF-8 preview size >= `smsMaxBytes` (default 90) reports LMS; the remainder reports SMS. LMS/MMS share `lmsMaxBytes` (default 2000).
|
||
- UTF-8 byte counting includes `smsPreviewSuffix` and its separating newline, without storing the suffix in the body.
|
||
- This is a preview. Use the template-save response for saved `tmplatTy` and delivery-result `sendTy` for actual per-recipient type after server substitution. Registry updates require updating installed consumer copies.
|
||
|
||
### Required Shared References
|
||
|
||
Before each related task, read the current contents of every matching reference, even if it was read earlier in the session.
|
||
|
||
| Task scope | Required reference |
|
||
|---|---|
|
||
| Installing, upgrading, adapting, or verifying a registry component | `.agent-harness/references/kri-ui-registry/installation-and-adaptation.md` |
|
||
| KriEditor HTML, image-map, sanitizer, or WYSIWYG compatibility | `.agent-harness/references/kri-ui-registry/editor-html-compatibility.md` |
|
||
|
||
If a task spans multiple scopes, read every matching reference. Generated files under `.agent-harness/references/` are read-only copies; edit KriUiRegistry's `.agent/consumer.md` or `.agent/consumer-references/` and recompose instead.
|
||
|
||
# kart-front Project Instruction Router
|
||
|
||
## Required Project References
|
||
|
||
Before each related task, read the current contents of every matching reference below, even if it was read earlier in the session.
|
||
|
||
| Task scope | Required reference |
|
||
|---|---|
|
||
| Any substantive analysis, planning, implementation, debugging, review, or documentation work in this repository | `.agent/references/repository-rules.md` |
|
||
|
||
If a task spans multiple scopes, read every matching reference. Do not assume remembered content is current.
|
||
|
||
## Project Lifecycle (2026-10-21)
|
||
|
||
- The second migration phase is closed by user instruction. Migration handoff and progress documents have been retired; durable project rules and validation procedures live in `.agent/references/repository-rules.md`.
|
||
- Phase closure does not announce launch or certify unexecuted live verification. Treat the application as unlaunched until the user explicitly announces launch.
|
||
- Work on subsequent changes only within the user's requested scope; do not automatically resume the retired migration plan.
|
||
|
||
## Harness Workflow
|
||
|
||
- `AGENTS.md` and `CLAUDE.md` are generated outputs. Never edit them directly.
|
||
- Edit `.agent/project.md` only when routing changes. Store durable project detail in `.agent/references/`.
|
||
- A reference-only content change does not require recomposition when its route is unchanged. Run harness verification to validate routing and UTF-8.
|
||
- Recompose and verify after changing `.agent/project.md`, `.agent/profile.yml`, or another composed instruction source.
|