mirror of
https://github.com/AmruthPillai/Reactive-Resume.git
synced 2026-06-22 04:11:55 +10:00
Amruth Pillai
6d8d8f6e55
* chore(ai): remove local AI store now that providers live server-side
The Zustand-based useAIStore has been replaced by the server-side
aiProviders oRPC router (encrypted credentials persisted in DB).
Delete the dead store + tests, drop the ./store export, and remove
zustand/immer deps which are no longer referenced anywhere in
packages/ai/src/.
* feat(agent): archive/delete actions and read-only state for agent threads
- Backend: mark archived threads as read-only in threads.get and reject
messages.send with CONFLICT when the thread is archived.
- Frontend: render archived threads in the sidebar with muted styling and
an Archived badge; add a per-thread dropdown menu in the chat header
with Archive (non-destructive) and Delete (with confirmation); show a
read-only banner above the message list that disambiguates archived
vs. missing-resource causes; suppress the Retry and Stop buttons in
read-only mode.
- Tests: new packages/api/src/services/agent.test.ts covering the
archived-thread isReadOnly flag and the archived-thread send refusal.
* fix(agent): abort run on archive and verify ownership before deleting thread
- threads.archive: before flipping status, abort any in-flight run controller
and clear the active-run state on the thread; cleanup failures are logged
but do not block the status update.
- threads.delete: assert thread ownership via getThread before destructive
work so an authenticated user cannot wipe another user's attachment rows
by passing a foreign threadId.
Adds focused tests for both behaviors.
* feat(agent): display patch diffs and surface revert conflicts
Render apply_resume_patch tool messages with a status-aware card (applied/
reverted/conflicted), expandable operation list, and a Revert button that
correctly handles RESUME_VERSION_CONFLICT responses. Adds unit tests for
the inverse-patch builder and the agentService.actions.revert flow.
* chore(agent): remove out-of-scope attachment tests accidentally added in Task 6
The Task 6 commit (73ef1acca) accidentally re-introduced three attachment-
related tests that belong to a separate task:
- `buildAttachmentModelParts > converts text, image, supported binary, and
unsupported attachments into model parts`
- `agentService.messages.send > persists the user message with file UI parts
and links selected attachments to it` (was failing — the `ToolLoopAgent`
mock is not callable as a constructor)
- `agentService.messages.send > rejects attachments that are missing, foreign,
or already linked before persisting a message`
These were likely re-added during a stash recovery and were not requested
for Task 6, whose scope was limited to the `agentService.actions.revert`
flow. Remove them along with the helpers/fixtures (`buildAttachment`,
`buildActiveThread`, `selectWhereResult`, `selectOrderByResult`) that they
were the only consumers of. `selectLimitResult` is preserved because it is
used by the revert tests.
* chore(agent): configure runtime dependencies
* feat(db): add agent workspace schema
* feat(api): add agent backend services
* feat(web): add agent workspace UI
* chore(agent): remove legacy builder assistant
* test(agent): make agent stream mocks constructible
* chore(web): remove unused resume replacement hook
* feat(api): add unsafe AI base URL flag
* chore(dev): expose local services in compose
* fix(web): normalize resume preview gaps
* feat(api): improve agent tool handling
* feat(web): polish agent workspace UI
* chore: update dependencies
* fix(api,web): address PR review feedback for agent workspace
Security/correctness:
- Restrict AI provider URLs to http/https even in unsafe mode
- Stop exposing Redis on host network by default
- Make .env.local optional and drop app profile in compose.dev.yml
- Store agent attachments with private ACL on S3
- Reset provider test status when provider/model/baseURL changes
- Decouple non-agent AI endpoints from REDIS_URL requirement
- Fix JSON Patch add inverse for existing object members
- Wrap resume patch + agent action insert in db transaction
- Validate partialMessage at runtime and rate-limit attachment uploads
- Add unique index on agent_messages (thread_id, sequence)
UX/bugs:
- Mark agent thread route as ssr: false and guard SSE chunk parsing
- Show config-specific banner only on known configuration error
- Gate AI provider checks behind loading state in resume import
- Fix relative-time formatter blank gap between 45-59 seconds
- Clarify thread delete confirmation message
Polish:
- Raise ENCRYPTION_SECRET minimum to 32 characters
- Bucket AI rate limits by resumeId/threadId/messageId
- Trim form values before submitting AI provider config
- Use single key identifier and nullish-coalesce baseURL display
* fix: address ai agent review feedback
* fix: preserve mobile agent chat state
* docs: add ai agent workspace guides
* feat: introduce design system for Reactive Resume
94 lines
3.2 KiB
Plaintext
94 lines
3.2 KiB
Plaintext
---
|
|
title: "Using AI in the builder"
|
|
description: "Learn how to run resume analysis and use the AI Resume Assistant to review proposed resume changes before applying them."
|
|
---
|
|
|
|
Reactive Resume includes two AI-assisted builder workflows:
|
|
|
|
- **Resume Analysis** gives you a score, strengths, and prioritized suggestions.
|
|
- **AI Resume Assistant** proposes specific edits that you can accept or reject.
|
|
|
|
<Info>
|
|
These features require a tested and enabled AI provider in **Dashboard -> Settings -> Integrations**. For setup, see
|
|
[Using Artificial Intelligence](/guides/using-ai).
|
|
</Info>
|
|
|
|
## Run a resume analysis
|
|
|
|
Use resume analysis when you want a broad review before making changes.
|
|
|
|
<Steps>
|
|
<Step title="Open your resume in the builder">
|
|
Go to the dashboard and open the resume you want to review.
|
|
</Step>
|
|
|
|
<Step title="Open the Resume Analysis section">
|
|
In the right sidebar, select **Resume Analysis**.
|
|
|
|
<Frame caption="Resume Analysis section in the builder">
|
|
<img
|
|
src="/images/guides/using-ai-in-the-builder/screenshot-1.webp"
|
|
alt="Resume Analysis section showing the AI setup prompt in the builder sidebar"
|
|
/>
|
|
</Frame>
|
|
</Step>
|
|
|
|
<Step title="Click Analyze Resume">
|
|
Reactive Resume sends the current resume data to your configured AI provider.
|
|
</Step>
|
|
|
|
<Step title="Review the results">
|
|
Review the overall score, scorecard, strengths, and suggestions.
|
|
</Step>
|
|
</Steps>
|
|
|
|
Use the analysis as guidance, not as a final verdict. The best resume still depends on the job, industry, and audience.
|
|
|
|
## Open the AI Resume Assistant
|
|
|
|
Click the assistant button in the builder dock to open the assistant.
|
|
|
|
On desktop, the assistant opens as a movable, resizable panel. On smaller screens, it opens as a full-height sheet.
|
|
|
|
If AI is unavailable, the builder shows a link to **Integrations** so you can configure it.
|
|
|
|
## Ask for targeted changes
|
|
|
|
The assistant works best when you ask for specific, incremental changes.
|
|
|
|
Good prompts:
|
|
|
|
- "Rewrite my summary for a senior frontend engineer role."
|
|
- "Tighten the bullets in my most recent job."
|
|
- "Add measurable impact to my project descriptions."
|
|
- "Adapt this resume for the job description below."
|
|
|
|
Avoid asking it to rewrite everything at once unless you are prepared to review many changes.
|
|
|
|
## Review proposals before applying them
|
|
|
|
When the assistant proposes edits, Reactive Resume shows a review card with:
|
|
|
|
- a proposal title and summary;
|
|
- badges for the proposed operations;
|
|
- before and after previews;
|
|
- the raw JSON Patch for users who want to inspect the exact operations.
|
|
|
|
You can:
|
|
|
|
- **Accept** one proposal;
|
|
- **Reject** one proposal;
|
|
- move between proposals with **Prev** and **Next**;
|
|
- **Accept all** or **Reject all** from the split-button menu.
|
|
|
|
<Warning>
|
|
Review AI proposals before accepting them. AI can introduce wording that is inaccurate, too generic, or not aligned
|
|
with your actual experience.
|
|
</Warning>
|
|
|
|
## When a proposal cannot be applied
|
|
|
|
A proposal can fail if the resume changed after the assistant generated it, if the resume is locked, or if the proposed patch no longer matches the current resume data.
|
|
|
|
If that happens, ask the assistant to regenerate the change from the latest version of the resume.
|