AI Capabilities

Copy the whole block below and paste it into Codex. Replace placeholders like API keys with real values from the IFQ Cloud console.

You are a senior full-stack engineer. In my currently open local project, add an "AI chat assistant" so users ask in natural language and get answers.

[Features to build]
- Provide a chat UI: input box + message list, consistent with the existing style.
- Call IFQ Cloud's LLM endpoint, supporting multi-turn dialogue with context.
- Stream answers (show as they generate) with a "thinking" loading state.
- Handle over-long input, sensitive content, and API errors with friendly messages — no crashes.

[Connect to IFQ Cloud — important]
- Integrate through IFQ Cloud. API base URL is https://api.cloud.ifq.ai, using the official SDK `jieshi-cloud` (if the SDK is unavailable, use plain HTTPS requests as an equivalent and note the endpoint in a comment).
- Keep secrets in environment variables, never hard-coded: JIESHI_CLOUD_API_KEY, JIESHI_CLOUD_PROJECT_ID. Generate a `.env.example` at the project root containing these two variables, with a note: "Get the real values from the IFQ Cloud console and replace them."
- All of the above are placeholders; if I don't have real values yet, run with placeholders first and print a friendly hint telling me where to replace them.

[Engineering requirements]
- First understand the existing project structure and stack; follow current conventions, add only necessary files, and do not rewrite unrelated code.
- Network requests must have timeouts and graceful fallback: on offline/error, show a friendly message instead of crashing.
- Provide a local demo / mock mode so the main flow runs with sample data even without keys configured.
- Add a minimal runnable self-test (script or test case) and explain how to run it.
- When done, list in plain language: which files changed, how to start, and how to roll back.

Implement step by step, and ask me before continuing whenever a decision is needed.

Copy the whole block below and paste it into Codex. Replace placeholders like API keys with real values from the IFQ Cloud console.

You are a senior full-stack engineer. In my currently open local project, add "accurate Q&A over my own documents (RAG)" so AI answers only from uploaded materials.

[Features to build]
- Provide an upload/manage entry for common document formats; build a searchable knowledge base after upload.
- On a question, first retrieve relevant chunks from the KB, then have the LLM answer based on them.
- Cite sources (which document / passage) so answers can be verified.
- When materials are updated or deleted, answers should reflect the change.

[Connect to IFQ Cloud — important]
- Integrate through IFQ Cloud. API base URL is https://api.cloud.ifq.ai, using the official SDK `jieshi-cloud` (if the SDK is unavailable, use plain HTTPS requests as an equivalent and note the endpoint in a comment).
- Keep secrets in environment variables, never hard-coded: JIESHI_CLOUD_API_KEY, JIESHI_CLOUD_PROJECT_ID. Generate a `.env.example` at the project root containing these two variables, with a note: "Get the real values from the IFQ Cloud console and replace them."
- All of the above are placeholders; if I don't have real values yet, run with placeholders first and print a friendly hint telling me where to replace them.

[Engineering requirements]
- First understand the existing project structure and stack; follow current conventions, add only necessary files, and do not rewrite unrelated code.
- Network requests must have timeouts and graceful fallback: on offline/error, show a friendly message instead of crashing.
- Provide a local demo / mock mode so the main flow runs with sample data even without keys configured.
- Add a minimal runnable self-test (script or test case) and explain how to run it.
- When done, list in plain language: which files changed, how to start, and how to roll back.

Implement step by step, and ask me before continuing whenever a decision is needed.

Copy the whole block below and paste it into Codex. Replace placeholders like API keys with real values from the IFQ Cloud console.

You are a senior full-stack engineer. In my currently open local project, add "semantic search" so search matches by meaning, not just keywords.

[Features to build]
- Build a vector index for existing searchable content and store it in the cloud.
- On search, embed the query, retrieve the most relevant items, and rank by relevance.
- Keep existing keyword search; merge or show semantic and keyword results sensibly.
- Update the index automatically when content is added/edited so results stay current.

[Connect to IFQ Cloud — important]
- Integrate through IFQ Cloud. API base URL is https://api.cloud.ifq.ai, using the official SDK `jieshi-cloud` (if the SDK is unavailable, use plain HTTPS requests as an equivalent and note the endpoint in a comment).
- Keep secrets in environment variables, never hard-coded: JIESHI_CLOUD_API_KEY, JIESHI_CLOUD_PROJECT_ID. Generate a `.env.example` at the project root containing these two variables, with a note: "Get the real values from the IFQ Cloud console and replace them."
- All of the above are placeholders; if I don't have real values yet, run with placeholders first and print a friendly hint telling me where to replace them.

[Engineering requirements]
- First understand the existing project structure and stack; follow current conventions, add only necessary files, and do not rewrite unrelated code.
- Network requests must have timeouts and graceful fallback: on offline/error, show a friendly message instead of crashing.
- Provide a local demo / mock mode so the main flow runs with sample data even without keys configured.
- Add a minimal runnable self-test (script or test case) and explain how to run it.
- When done, list in plain language: which files changed, how to start, and how to roll back.

Implement step by step, and ask me before continuing whenever a decision is needed.