Vibecode QuillBot
track this build5 phases, 16 steps, beginner friendly0%YES · one-shottable
A paraphraser/summarizer/grammar wrapper over an LLM and LanguageTool is easy to build; the paid app wins on UX, extensions, plagiarism workflows, and bundled tools.
the project pack5 files · written for this build, step by step
You are building a lean indie version of QuillBot. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== README.md ===== # QuillBot · indie build Build a local paraphrasing desk with protected facts and visible alternatives. Estimated effort: **multi-day**. Work `BUILD_PLAN.md` top to bottom · every phase ends in a check that has to pass before the next one starts. ## Stack | Part | Choice | Why | | --- | --- | --- | | Runtime | Python 3.12+ and Flask | A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. | | Storage | SQLite through Python sqlite3 | Local ownership with explicit transactions and a portable backup path. | | Interface | Jinja HTML templates, CSS and vanilla JavaScript | Implement the specified screens directly with labelled controls and progressive enhancement. | | Verification | Python unittest and browser acceptance fixtures | Check invariants and the actual user workflow before the next phase. | | Generation | Ollama local HTTP API | A backend-only adapter with a configurable installed local model and visible failure states. | ## Before you start Have every one of these ready. The plan assumes them from step one. - [ ] **Python 3.12 or newer and a terminal** · Python is free; this local prototype requires no hosting subscription. - Why: The local backend, tests and storage use Python. - Get it: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. - Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. - [ ] **A current desktop browser and text editor** · No paid service required for this local step. - Why: You need to view the local interface and edit generated project files. - Get it: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. - Verify: You can create a text file in the project folder and open browser developer tools. - [ ] **QuillBot acceptance sample** · No paid service required for this local step. - Why: This fixture makes the first end-to-end check reproducible. - Get it: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. - Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. - [ ] **Confirm the bounded replacement** · No paid service required for this local step. - Why: The full commercial product is larger than this guide. - Get it: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. - Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. - [ ] **Ollama with an explicitly local model** · No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Why: Generation requires a running model; ordinary editing remains usable while it is unavailable. - Get it: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. - Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. ## Quick start ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` Then copy `.env.example` to `.env` and fill in the values it documents. ## Honest limits This build deliberately does not replace: - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync If one of those is essential to you, that is the reason to keep paying for QuillBot, and the README should say so rather than pretend. ===== BRIEF.md ===== # Build brief · QuillBot The one-shot brief this plan expands. `BUILD_PLAN.md` (or `MILESTONES.md`) is the same sequence broken into steps and checks; where the two disagree, the plan wins. Build me a local paraphrasing desk with protected facts and visible alternatives as a bounded replacement for QuillBot. Build it in phases in the order below. Do not write the whole product in one pass. Finish the current phase, run its Done when checks, fix failures, then continue. Indie mode completes Phases 1-5. Phase 6 is required before shared or public deployment. ### Stack (fixed, do not substitute) - Runtime: Python 3.12+ and Flask. A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. - Storage: SQLite through Python sqlite3. Local ownership with explicit transactions and a portable backup path. - Interface: Jinja HTML templates, CSS and vanilla JavaScript. Implement the specified screens directly with labelled controls and progressive enhancement. - Verification: Python unittest and browser acceptance fixtures. Check invariants and the actual user workflow before the next phase. - Generation: Ollama local HTTP API. A backend-only adapter with a configurable installed local model and visible failure states. ### Data model (create this before Phase 1) - documents(id,title,text,revision) - requests(id,document_id,revision,mode,protected_json) - candidates(id,request_id,text,model,state) - glossary(term,replacement) - decisions(id,candidate_id,action,at) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. ### Prerequisites and configuration - Python 3.12 or newer and a terminal: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. Cost: Python is free; this local prototype requires no hosting subscription. - A current desktop browser and text editor: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. Verify: You can create a text file in the project folder and open browser developer tools. Cost: No paid service required for this local step. - QuillBot acceptance sample: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. Cost: No paid service required for this local step. - Confirm the bounded replacement: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. Cost: No paid service required for this local step. - Ollama with an explicitly local model: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. Cost: No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Configuration: DATA_DIR, SECRET_KEY, APP_MODE, SITE_URL, OLLAMA_URL, LOCAL_MODEL. Ship .env.example, replace placeholders and exclude secrets from git. ### Phase 1 · Local foundation and data contract Build: Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. - Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Commands, after creating the named files: `python -m venv .venv`; `python -m pip install Flask Flask-WTF python-dotenv waitress tzdata`; `python -m pip freeze > requirements.txt`; `python -m flask --app app run --host 127.0.0.1`. - For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Commands, after creating the named files: `python manage.py init`; `python manage.py seed`. - Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. - Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Commands, after creating the named files: `python scripts/model_probe.py`. - Trap: The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. Done when: The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. Restarting preserves the seeded records or canonical files; running init again deletes nothing. A cross-origin state-changing request to an admin route is refused. Do not build yet: Do not start source and constraints until these checks pass. ### Phase 2 · Source and constraints Build: Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Paraphrasing is not a way to manufacture facts or erase the need to credit a source. Done when: The preview shows the exact selected text and protected tokens before generation. An empty selection cannot trigger a paid or local inference request. Do not build yet: Do not start generate alternatives until these checks pass. ### Phase 3 · Generate alternatives Build: Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Render a word diff for each candidate and label failed constraints instead of silently repairing them. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Token preservation is a mechanical check; a human still needs to check whether meaning changed. Done when: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. A model outage leaves the source and selection intact. Do not build yet: Do not start accept and export until these checks pass. ### Phase 4 · Accept and export Build: Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Export original, accepted text and decision history in JSON plus a plain-text final document. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. Done when: Accepting alternative two leaves alternative one recorded but unapplied. Undo restores the exact original paragraph. Do not build yet: Do not start portable delivery and clean-start proof until these checks pass. ### Phase 5 · Portable delivery and clean-start proof Build: Finish the QuillBot replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. - Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. - Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Commands, after creating the named files: `python -m pip install -r requirements.txt`; `python -m unittest discover -s test`. - Trap: Export without an import or restore rehearsal is not verified portability. Done when: A new folder reaches the documented fixture outcome using only README instructions. A backup restored in isolation preserves the proof data and can be opened. Do not build yet: Do not start operate and share with access controls until these checks pass. ### Phase 6 · Operate and share with access controls (product-builder only) Build: Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. - Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. - Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Commands, after creating the named files: `waitress-serve --listen=127.0.0.1:5000 app:app`. - Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. - Trap: Product mode is additional engineering, not a switch that makes a local prototype production-ready. Done when: An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. Do not build yet: Do not add new providers or vendor-scale features until the release gates are recorded. ### Out of scope (and why) - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions: retain the paid product if this capability is essential; it is outside this bounded build. - plagiarism/AI detector workflows: retain the paid product if this capability is essential; it is outside this bounded build. - rewrite modes: retain the paid product if this capability is essential; it is outside this bounded build. - history: retain the paid product if this capability is essential; it is outside this bounded build. - polish: retain the paid product if this capability is essential; it is outside this bounded build. - account sync: retain the paid product if this capability is essential; it is outside this bounded build. ### README must contain - Exact install, configure, initialize, start, test and recovery commands for a clean folder. - The schema, fixture, acceptance results, private data locations and export format. - Every prerequisite and secret source, actual running costs and deliberately excluded capabilities. - An honest distinction between tests actually run and checks still awaiting real credentials or deployment. - Dependency documentation reviewed 2026-09-05: https://flask.palletsprojects.com/en/stable/installation/ ; https://docs.python.org/3/library/sqlite3.html ; https://flask-wtf.readthedocs.io/en/1.2.x/csrf/ ; https://docs.pylonsproject.org/projects/waitress/en/stable/usage.html ; https://docs.ollama.com/api/chat ; https://docs.ollama.com/cloud. Recheck before upgrading; freeze the versions actually tested. ===== AGENTS.md ===== # Agent instructions · QuillBot indie build - Read `README.md` and `BUILD_PLAN.md` before writing code. The stack is fixed: Python 3.12+ and Flask, SQLite through Python sqlite3, Jinja HTML templates, CSS and vanilla JavaScript, Python unittest and browser acceptance fixtures, Ollama local HTTP API. Do not substitute. - Work one phase at a time, in order. Do not start a phase until every "Done when" item of the previous one passes. - Prefer the fewest moving parts that satisfy the step. No frameworks, services or dependencies the plan does not name. - Secrets live in `.env`, never in source or logs. Keep `.env.example` current when a variable is introduced. - Do not invent cryptography, security guarantees, APIs or compliance claims. - Add a focused test for every destructive, security-sensitive or data-loss path the plan names. - Run the project checks before declaring a phase complete, and record any deliberate shortcut in the README under "Tradeoffs". ## Known traps - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Token preservation is a mechanical check; a human still needs to check whether meaning changed. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - Export without an import or restore rehearsal is not verified portability. ===== BUILD_PLAN.md ===== # Build plan · QuillBot Build a local paraphrasing desk with protected facts and visible alternatives. Phases are in dependency order. Each ends in a "Done when" list; treat an unticked item as a blocker, not a note. ## Phase 1 · Local foundation and data contract Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. ### Steps 1. Create and start the local application Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Files: `app.py`, `requirements.txt`, `.env.example`, `.gitignore` ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` 2. Implement storage and seed the named fixture For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Files: `schema.sql`, `db.py`, `manage.py`, `fixtures/README.md` ```sh python manage.py init python manage.py seed ``` 3. Protect the local request boundary Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. Files: `app.py`, `templates/base.html`, `test/test_foundation.py` 4. Verify the selected local model Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Files: `providers/local_model.py`, `scripts/model_probe.py` ```sh python scripts/model_probe.py ``` ### Done when - [ ] The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. - [ ] Restarting preserves the seeded records or canonical files; running init again deletes nothing. - [ ] A cross-origin state-changing request to an admin route is refused. ### Watch out - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. ## Phase 2 · Source and constraints Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. ### Steps 1. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Files: `features/source_and_constraints.py`, `templates/source_and_constraints.html` 2. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Files: `features/source_and_constraints.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_source_and_constraints.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] An empty selection cannot trigger a paid or local inference request. ### Watch out - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. ## Phase 3 · Generate alternatives Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. ### Steps 1. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Files: `features/generate_alternatives.py`, `templates/generate_alternatives.html` 2. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Files: `features/generate_alternatives.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_generate_alternatives.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] A model outage leaves the source and selection intact. ### Watch out - Token preservation is a mechanical check; a human still needs to check whether meaning changed. ## Phase 4 · Accept and export Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. ### Steps 1. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Files: `features/accept_and_export.py`, `templates/accept_and_export.html` 2. Export original, accepted text and decision history in JSON plus a plain-text final document. Export original, accepted text and decision history in JSON plus a plain-text final document. Files: `features/accept_and_export.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_accept_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] Undo restores the exact original paragraph. ### Watch out - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the QuillBot replacement with a documented first-run path and a recoverable export. ### Steps 1. Write the user-facing runbook Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. Files: `README.md`, `.env.example` 2. Create and rehearse a recoverable backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Files: `OPERATIONS.md`, `scripts/backup.py` 3. Reproduce the first-run experience Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Files: `README.md`, `verification.md` ```sh python -m pip install -r requirements.txt python -m unittest discover -s test ``` ### Done when - [ ] A new folder reaches the documented fixture outcome using only README instructions. - [ ] A backup restored in isolation preserves the proof data and can be opened. ### Watch out - Export without an import or restore rehearsal is not verified portability. ## Not in this build - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync ## After v1, if you want it - Extend accept and export only after the fixture and recovery checks pass. - Before adding another integration, document its credentials, limits, cost and failure behavior with primary-source links. ===== .env.example ===== # Copy to .env and fill in. Never commit .env; this file documents it. # Required. A new private folder this application creates on first run; never serve it as static files. DATA_DIR=./data/quillbot # Required · secret. Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. SECRET_KEY=replace-with-a-random-secret # Required. Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. APP_MODE=indie # Required. The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. SITE_URL=http://127.0.0.1:5000 # Required. Keep the inference service bound to loopback; the backend calls it, never the public browser. OLLAMA_URL=http://127.0.0.1:11434 # Required. Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. LOCAL_MODEL=replace-with-installed-local-model
You are building a lean indie version of QuillBot. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== README.md ===== # QuillBot · indie build Build a local paraphrasing desk with protected facts and visible alternatives. Estimated effort: **multi-day**. Work `BUILD_PLAN.md` top to bottom · every phase ends in a check that has to pass before the next one starts. ## Stack | Part | Choice | Why | | --- | --- | --- | | Runtime | Python 3.12+ and Flask | A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. | | Storage | SQLite through Python sqlite3 | Local ownership with explicit transactions and a portable backup path. | | Interface | Jinja HTML templates, CSS and vanilla JavaScript | Implement the specified screens directly with labelled controls and progressive enhancement. | | Verification | Python unittest and browser acceptance fixtures | Check invariants and the actual user workflow before the next phase. | | Generation | Ollama local HTTP API | A backend-only adapter with a configurable installed local model and visible failure states. | ## Before you start Have every one of these ready. The plan assumes them from step one. - [ ] **Python 3.12 or newer and a terminal** · Python is free; this local prototype requires no hosting subscription. - Why: The local backend, tests and storage use Python. - Get it: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. - Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. - [ ] **A current desktop browser and text editor** · No paid service required for this local step. - Why: You need to view the local interface and edit generated project files. - Get it: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. - Verify: You can create a text file in the project folder and open browser developer tools. - [ ] **QuillBot acceptance sample** · No paid service required for this local step. - Why: This fixture makes the first end-to-end check reproducible. - Get it: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. - Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. - [ ] **Confirm the bounded replacement** · No paid service required for this local step. - Why: The full commercial product is larger than this guide. - Get it: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. - Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. - [ ] **Ollama with an explicitly local model** · No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Why: Generation requires a running model; ordinary editing remains usable while it is unavailable. - Get it: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. - Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. ## Quick start ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` Then copy `.env.example` to `.env` and fill in the values it documents. ## Honest limits This build deliberately does not replace: - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync If one of those is essential to you, that is the reason to keep paying for QuillBot, and the README should say so rather than pretend. ===== BRIEF.md ===== # Build brief · QuillBot The one-shot brief this plan expands. `BUILD_PLAN.md` (or `MILESTONES.md`) is the same sequence broken into steps and checks; where the two disagree, the plan wins. Build me a local paraphrasing desk with protected facts and visible alternatives as a bounded replacement for QuillBot. Build it in phases in the order below. Do not write the whole product in one pass. Finish the current phase, run its Done when checks, fix failures, then continue. Indie mode completes Phases 1-5. Phase 6 is required before shared or public deployment. ### Stack (fixed, do not substitute) - Runtime: Python 3.12+ and Flask. A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. - Storage: SQLite through Python sqlite3. Local ownership with explicit transactions and a portable backup path. - Interface: Jinja HTML templates, CSS and vanilla JavaScript. Implement the specified screens directly with labelled controls and progressive enhancement. - Verification: Python unittest and browser acceptance fixtures. Check invariants and the actual user workflow before the next phase. - Generation: Ollama local HTTP API. A backend-only adapter with a configurable installed local model and visible failure states. ### Data model (create this before Phase 1) - documents(id,title,text,revision) - requests(id,document_id,revision,mode,protected_json) - candidates(id,request_id,text,model,state) - glossary(term,replacement) - decisions(id,candidate_id,action,at) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. ### Prerequisites and configuration - Python 3.12 or newer and a terminal: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. Cost: Python is free; this local prototype requires no hosting subscription. - A current desktop browser and text editor: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. Verify: You can create a text file in the project folder and open browser developer tools. Cost: No paid service required for this local step. - QuillBot acceptance sample: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. Cost: No paid service required for this local step. - Confirm the bounded replacement: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. Cost: No paid service required for this local step. - Ollama with an explicitly local model: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. Cost: No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Configuration: DATA_DIR, SECRET_KEY, APP_MODE, SITE_URL, OLLAMA_URL, LOCAL_MODEL. Ship .env.example, replace placeholders and exclude secrets from git. ### Phase 1 · Local foundation and data contract Build: Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. - Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Commands, after creating the named files: `python -m venv .venv`; `python -m pip install Flask Flask-WTF python-dotenv waitress tzdata`; `python -m pip freeze > requirements.txt`; `python -m flask --app app run --host 127.0.0.1`. - For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Commands, after creating the named files: `python manage.py init`; `python manage.py seed`. - Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. - Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Commands, after creating the named files: `python scripts/model_probe.py`. - Trap: The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. Done when: The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. Restarting preserves the seeded records or canonical files; running init again deletes nothing. A cross-origin state-changing request to an admin route is refused. Do not build yet: Do not start source and constraints until these checks pass. ### Phase 2 · Source and constraints Build: Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Paraphrasing is not a way to manufacture facts or erase the need to credit a source. Done when: The preview shows the exact selected text and protected tokens before generation. An empty selection cannot trigger a paid or local inference request. Do not build yet: Do not start generate alternatives until these checks pass. ### Phase 3 · Generate alternatives Build: Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Render a word diff for each candidate and label failed constraints instead of silently repairing them. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Token preservation is a mechanical check; a human still needs to check whether meaning changed. Done when: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. A model outage leaves the source and selection intact. Do not build yet: Do not start accept and export until these checks pass. ### Phase 4 · Accept and export Build: Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Export original, accepted text and decision history in JSON plus a plain-text final document. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. Done when: Accepting alternative two leaves alternative one recorded but unapplied. Undo restores the exact original paragraph. Do not build yet: Do not start portable delivery and clean-start proof until these checks pass. ### Phase 5 · Portable delivery and clean-start proof Build: Finish the QuillBot replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. - Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. - Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Commands, after creating the named files: `python -m pip install -r requirements.txt`; `python -m unittest discover -s test`. - Trap: Export without an import or restore rehearsal is not verified portability. Done when: A new folder reaches the documented fixture outcome using only README instructions. A backup restored in isolation preserves the proof data and can be opened. Do not build yet: Do not start operate and share with access controls until these checks pass. ### Phase 6 · Operate and share with access controls (product-builder only) Build: Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. - Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. - Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Commands, after creating the named files: `waitress-serve --listen=127.0.0.1:5000 app:app`. - Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. - Trap: Product mode is additional engineering, not a switch that makes a local prototype production-ready. Done when: An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. Do not build yet: Do not add new providers or vendor-scale features until the release gates are recorded. ### Out of scope (and why) - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions: retain the paid product if this capability is essential; it is outside this bounded build. - plagiarism/AI detector workflows: retain the paid product if this capability is essential; it is outside this bounded build. - rewrite modes: retain the paid product if this capability is essential; it is outside this bounded build. - history: retain the paid product if this capability is essential; it is outside this bounded build. - polish: retain the paid product if this capability is essential; it is outside this bounded build. - account sync: retain the paid product if this capability is essential; it is outside this bounded build. ### README must contain - Exact install, configure, initialize, start, test and recovery commands for a clean folder. - The schema, fixture, acceptance results, private data locations and export format. - Every prerequisite and secret source, actual running costs and deliberately excluded capabilities. - An honest distinction between tests actually run and checks still awaiting real credentials or deployment. - Dependency documentation reviewed 2026-09-05: https://flask.palletsprojects.com/en/stable/installation/ ; https://docs.python.org/3/library/sqlite3.html ; https://flask-wtf.readthedocs.io/en/1.2.x/csrf/ ; https://docs.pylonsproject.org/projects/waitress/en/stable/usage.html ; https://docs.ollama.com/api/chat ; https://docs.ollama.com/cloud. Recheck before upgrading; freeze the versions actually tested. ===== AGENTS.md ===== # Agent instructions · QuillBot indie build - Read `README.md` and `BUILD_PLAN.md` before writing code. The stack is fixed: Python 3.12+ and Flask, SQLite through Python sqlite3, Jinja HTML templates, CSS and vanilla JavaScript, Python unittest and browser acceptance fixtures, Ollama local HTTP API. Do not substitute. - Work one phase at a time, in order. Do not start a phase until every "Done when" item of the previous one passes. - Prefer the fewest moving parts that satisfy the step. No frameworks, services or dependencies the plan does not name. - Secrets live in `.env`, never in source or logs. Keep `.env.example` current when a variable is introduced. - Do not invent cryptography, security guarantees, APIs or compliance claims. - Add a focused test for every destructive, security-sensitive or data-loss path the plan names. - Run the project checks before declaring a phase complete, and record any deliberate shortcut in the README under "Tradeoffs". ## Known traps - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Token preservation is a mechanical check; a human still needs to check whether meaning changed. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - Export without an import or restore rehearsal is not verified portability. ===== BUILD_PLAN.md ===== # Build plan · QuillBot Build a local paraphrasing desk with protected facts and visible alternatives. Phases are in dependency order. Each ends in a "Done when" list; treat an unticked item as a blocker, not a note. ## Phase 1 · Local foundation and data contract Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. ### Steps 1. Create and start the local application Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Files: `app.py`, `requirements.txt`, `.env.example`, `.gitignore` ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` 2. Implement storage and seed the named fixture For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Files: `schema.sql`, `db.py`, `manage.py`, `fixtures/README.md` ```sh python manage.py init python manage.py seed ``` 3. Protect the local request boundary Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. Files: `app.py`, `templates/base.html`, `test/test_foundation.py` 4. Verify the selected local model Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Files: `providers/local_model.py`, `scripts/model_probe.py` ```sh python scripts/model_probe.py ``` ### Done when - [ ] The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. - [ ] Restarting preserves the seeded records or canonical files; running init again deletes nothing. - [ ] A cross-origin state-changing request to an admin route is refused. ### Watch out - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. ## Phase 2 · Source and constraints Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. ### Steps 1. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Files: `features/source_and_constraints.py`, `templates/source_and_constraints.html` 2. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Files: `features/source_and_constraints.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_source_and_constraints.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] An empty selection cannot trigger a paid or local inference request. ### Watch out - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. ## Phase 3 · Generate alternatives Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. ### Steps 1. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Files: `features/generate_alternatives.py`, `templates/generate_alternatives.html` 2. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Files: `features/generate_alternatives.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_generate_alternatives.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] A model outage leaves the source and selection intact. ### Watch out - Token preservation is a mechanical check; a human still needs to check whether meaning changed. ## Phase 4 · Accept and export Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. ### Steps 1. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Files: `features/accept_and_export.py`, `templates/accept_and_export.html` 2. Export original, accepted text and decision history in JSON plus a plain-text final document. Export original, accepted text and decision history in JSON plus a plain-text final document. Files: `features/accept_and_export.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_accept_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] Undo restores the exact original paragraph. ### Watch out - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the QuillBot replacement with a documented first-run path and a recoverable export. ### Steps 1. Write the user-facing runbook Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. Files: `README.md`, `.env.example` 2. Create and rehearse a recoverable backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Files: `OPERATIONS.md`, `scripts/backup.py` 3. Reproduce the first-run experience Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Files: `README.md`, `verification.md` ```sh python -m pip install -r requirements.txt python -m unittest discover -s test ``` ### Done when - [ ] A new folder reaches the documented fixture outcome using only README instructions. - [ ] A backup restored in isolation preserves the proof data and can be opened. ### Watch out - Export without an import or restore rehearsal is not verified portability. ## Not in this build - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync ## After v1, if you want it - Extend accept and export only after the fixture and recovery checks pass. - Before adding another integration, document its credentials, limits, cost and failure behavior with primary-source links. ===== .env.example ===== # Copy to .env and fill in. Never commit .env; this file documents it. # Required. A new private folder this application creates on first run; never serve it as static files. DATA_DIR=./data/quillbot # Required · secret. Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. SECRET_KEY=replace-with-a-random-secret # Required. Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. APP_MODE=indie # Required. The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. SITE_URL=http://127.0.0.1:5000 # Required. Keep the inference service bound to loopback; the backend calls it, never the public browser. OLLAMA_URL=http://127.0.0.1:11434 # Required. Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. LOCAL_MODEL=replace-with-installed-local-model
You are building a production product version of QuillBot. Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt. ===== PRODUCT.md ===== # QuillBot · product brief ## Problem A paraphraser/summarizer/grammar wrapper over an LLM and LanguageTool is easy to build; the paid app wins on UX, extensions, plagiarism workflows, and bundled tools. ## Product outcome An operated version of a local paraphrasing desk with protected facts and visible alternatives, with authorized access, restore evidence and honest scope limits. ## Target user A builder who needs a maintainable product foundation, not a one-off demo. ## Required capabilities - LLM API - LanguageTool or grammar API - browser extension if in-app writing is needed ## Explicit non-goals for v1 - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync ## Success criteria - The preview shows the exact selected text and protected tokens before generation. - A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - Accepting alternative two leaves alternative one recorded but unapplied. - A private-data authorization check passes using a second identity. - An off-host restore drill has a date, observed result and recovery time in OPERATIONS.md. - README names the excluded vendor capabilities and actual provider/hosting costs. ===== BRIEF.md ===== # Build brief · QuillBot The one-shot brief this plan expands. `BUILD_PLAN.md` (or `MILESTONES.md`) is the same sequence broken into steps and checks; where the two disagree, the plan wins. Build me a local paraphrasing desk with protected facts and visible alternatives as a bounded replacement for QuillBot. Build it in phases in the order below. Do not write the whole product in one pass. Finish the current phase, run its Done when checks, fix failures, then continue. Indie mode completes Phases 1-5. Phase 6 is required before shared or public deployment. ### Stack (fixed, do not substitute) - Runtime: Python 3.12+ and Flask. A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. - Storage: SQLite through Python sqlite3. Local ownership with explicit transactions and a portable backup path. - Interface: Jinja HTML templates, CSS and vanilla JavaScript. Implement the specified screens directly with labelled controls and progressive enhancement. - Verification: Python unittest and browser acceptance fixtures. Check invariants and the actual user workflow before the next phase. - Generation: Ollama local HTTP API. A backend-only adapter with a configurable installed local model and visible failure states. ### Data model (create this before Phase 1) - documents(id,title,text,revision) - requests(id,document_id,revision,mode,protected_json) - candidates(id,request_id,text,model,state) - glossary(term,replacement) - decisions(id,candidate_id,action,at) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. ### Prerequisites and configuration - Python 3.12 or newer and a terminal: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. Cost: Python is free; this local prototype requires no hosting subscription. - A current desktop browser and text editor: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. Verify: You can create a text file in the project folder and open browser developer tools. Cost: No paid service required for this local step. - QuillBot acceptance sample: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. Cost: No paid service required for this local step. - Confirm the bounded replacement: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. Cost: No paid service required for this local step. - Ollama with an explicitly local model: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. Cost: No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Configuration: DATA_DIR, SECRET_KEY, APP_MODE, SITE_URL, OLLAMA_URL, LOCAL_MODEL. Ship .env.example, replace placeholders and exclude secrets from git. ### Phase 1 · Local foundation and data contract Build: Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. - Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Commands, after creating the named files: `python -m venv .venv`; `python -m pip install Flask Flask-WTF python-dotenv waitress tzdata`; `python -m pip freeze > requirements.txt`; `python -m flask --app app run --host 127.0.0.1`. - For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Commands, after creating the named files: `python manage.py init`; `python manage.py seed`. - Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. - Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Commands, after creating the named files: `python scripts/model_probe.py`. - Trap: The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. Done when: The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. Restarting preserves the seeded records or canonical files; running init again deletes nothing. A cross-origin state-changing request to an admin route is refused. Do not build yet: Do not start source and constraints until these checks pass. ### Phase 2 · Source and constraints Build: Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Paraphrasing is not a way to manufacture facts or erase the need to credit a source. Done when: The preview shows the exact selected text and protected tokens before generation. An empty selection cannot trigger a paid or local inference request. Do not build yet: Do not start generate alternatives until these checks pass. ### Phase 3 · Generate alternatives Build: Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Render a word diff for each candidate and label failed constraints instead of silently repairing them. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Token preservation is a mechanical check; a human still needs to check whether meaning changed. Done when: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. A model outage leaves the source and selection intact. Do not build yet: Do not start accept and export until these checks pass. ### Phase 4 · Accept and export Build: Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Export original, accepted text and decision history in JSON plus a plain-text final document. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. Done when: Accepting alternative two leaves alternative one recorded but unapplied. Undo restores the exact original paragraph. Do not build yet: Do not start portable delivery and clean-start proof until these checks pass. ### Phase 5 · Portable delivery and clean-start proof Build: Finish the QuillBot replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. - Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. - Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Commands, after creating the named files: `python -m pip install -r requirements.txt`; `python -m unittest discover -s test`. - Trap: Export without an import or restore rehearsal is not verified portability. Done when: A new folder reaches the documented fixture outcome using only README instructions. A backup restored in isolation preserves the proof data and can be opened. Do not build yet: Do not start operate and share with access controls until these checks pass. ### Phase 6 · Operate and share with access controls (product-builder only) Build: Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. - Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. - Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Commands, after creating the named files: `waitress-serve --listen=127.0.0.1:5000 app:app`. - Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. - Trap: Product mode is additional engineering, not a switch that makes a local prototype production-ready. Done when: An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. Do not build yet: Do not add new providers or vendor-scale features until the release gates are recorded. ### Out of scope (and why) - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions: retain the paid product if this capability is essential; it is outside this bounded build. - plagiarism/AI detector workflows: retain the paid product if this capability is essential; it is outside this bounded build. - rewrite modes: retain the paid product if this capability is essential; it is outside this bounded build. - history: retain the paid product if this capability is essential; it is outside this bounded build. - polish: retain the paid product if this capability is essential; it is outside this bounded build. - account sync: retain the paid product if this capability is essential; it is outside this bounded build. ### README must contain - Exact install, configure, initialize, start, test and recovery commands for a clean folder. - The schema, fixture, acceptance results, private data locations and export format. - Every prerequisite and secret source, actual running costs and deliberately excluded capabilities. - An honest distinction between tests actually run and checks still awaiting real credentials or deployment. - Dependency documentation reviewed 2026-09-05: https://flask.palletsprojects.com/en/stable/installation/ ; https://docs.python.org/3/library/sqlite3.html ; https://flask-wtf.readthedocs.io/en/1.2.x/csrf/ ; https://docs.pylonsproject.org/projects/waitress/en/stable/usage.html ; https://docs.ollama.com/api/chat ; https://docs.ollama.com/cloud. Recheck before upgrading; freeze the versions actually tested. ===== ARCHITECTURE.md ===== # Architecture · QuillBot ## Stack | Part | Choice | Why | | --- | --- | --- | | Runtime | Python 3.12+ and Flask | A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. | | Storage | SQLite through Python sqlite3 | Local ownership with explicit transactions and a portable backup path. | | Interface | Jinja HTML templates, CSS and vanilla JavaScript | Implement the specified screens directly with labelled controls and progressive enhancement. | | Verification | Python unittest and browser acceptance fixtures | Check invariants and the actual user workflow before the next phase. | | Generation | Ollama local HTTP API | A backend-only adapter with a configurable installed local model and visible failure states. | ## Modules Each module has one owner concern and a documented way to replace it. | Module | Owns | How to replace it | | --- | --- | --- | | Data and identity | documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at) | Keep stable ids and a versioned repository interface; migrate storage behind it with a fixture round-trip. | | Source and constraints | Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. | Keep the acceptance contract: The preview shows the exact selected text and protected tokens before generation. Replace only this module after replaying its fixture; preserve ids and existing records. | | Generate alternatives | Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. | Keep the acceptance contract: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Replace only this module after replaying its fixture; preserve ids and existing records. | | Accept and export | Apply only the selected candidate if the original revision matches; offer undo as a new revision. | Keep the acceptance contract: Accepting alternative two leaves alternative one recorded but unapplied. Replace only this module after replaying its fixture; preserve ids and existing records. | | Operations | Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. | Change host or backup destination only after an isolated restore and authorization check. | ## Configuration Every runtime setting is an environment variable documented in `.env.example`, validated at startup, with a safe local default wherever one exists. - `DATA_DIR` · required · A new private folder this application creates on first run; never serve it as static files. - `SECRET_KEY` · required, secret · Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. - `APP_MODE` · required · Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. - `SITE_URL` · required · The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. - `OLLAMA_URL` · required · Keep the inference service bound to loopback; the backend calls it, never the public browser. - `LOCAL_MODEL` · required · Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. ## Production baseline - Security: least privilege, input validation at every boundary, secret redaction in logs, rate limits on abuse-prone paths, no invented security primitives. - Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore procedures that have been exercised. - Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, timeouts. - Observability: structured logs with request or operation ids, an error-tracking hook, and health and readiness checks where a server exists. - Quality: unit tests for domain rules, integration tests at module boundaries, one end-to-end test of the critical path. ## Decision records For each dependency in the stack table, keep a short note: why it was chosen, its failure mode, and how it is replaced. Do not add infrastructure until a requirement in `PRODUCT.md` justifies it. ===== AGENTS.md ===== # Agent instructions · QuillBot product build - Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code. The stack is fixed: Python 3.12+ and Flask, SQLite through Python sqlite3, Jinja HTML templates, CSS and vanilla JavaScript, Python unittest and browser acceptance fixtures, Ollama local HTTP API. - Implement milestone by milestone from `MILESTONES.md`; keep each change reviewable and leave the application runnable at every commit. - Treat authentication, payments, encryption, imports, webhooks and destructive actions as high-risk boundaries when present. - Never invent cryptography or silently weaken a requirement to make a check pass. - Put every external service behind an interface with a deterministic fake for tests. - Add migrations and rollback or recovery notes for every persistent data change. - Log useful operational context without credentials, tokens, passwords or personal data. - Update documentation and run every check before completing a milestone. ## Known traps - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Token preservation is a mechanical check; a human still needs to check whether meaning changed. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - Export without an import or restore rehearsal is not verified portability. - Product mode is additional engineering, not a switch that makes a local prototype production-ready. ===== MILESTONES.md ===== # Delivery milestones · QuillBot Estimated effort: **multi-day** for the indie phases; the production-only milestones add the trust and operability layer. ## M1 · Local foundation and data contract Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. ### Steps 1. Create and start the local application Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Files: `app.py`, `requirements.txt`, `.env.example`, `.gitignore` ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` 2. Implement storage and seed the named fixture For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Files: `schema.sql`, `db.py`, `manage.py`, `fixtures/README.md` ```sh python manage.py init python manage.py seed ``` 3. Protect the local request boundary Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. Files: `app.py`, `templates/base.html`, `test/test_foundation.py` 4. Verify the selected local model Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Files: `providers/local_model.py`, `scripts/model_probe.py` ```sh python scripts/model_probe.py ``` ### Done when - [ ] The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. - [ ] Restarting preserves the seeded records or canonical files; running init again deletes nothing. - [ ] A cross-origin state-changing request to an admin route is refused. ### Watch out - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. ## M2 · Source and constraints Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. ### Steps 1. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Files: `features/source_and_constraints.py`, `templates/source_and_constraints.html` 2. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Files: `features/source_and_constraints.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_source_and_constraints.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] An empty selection cannot trigger a paid or local inference request. ### Watch out - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. ## M3 · Generate alternatives Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. ### Steps 1. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Files: `features/generate_alternatives.py`, `templates/generate_alternatives.html` 2. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Files: `features/generate_alternatives.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_generate_alternatives.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] A model outage leaves the source and selection intact. ### Watch out - Token preservation is a mechanical check; a human still needs to check whether meaning changed. ## M4 · Accept and export Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. ### Steps 1. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Files: `features/accept_and_export.py`, `templates/accept_and_export.html` 2. Export original, accepted text and decision history in JSON plus a plain-text final document. Export original, accepted text and decision history in JSON plus a plain-text final document. Files: `features/accept_and_export.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_accept_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] Undo restores the exact original paragraph. ### Watch out - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. ## M5 · Portable delivery and clean-start proof Finish the QuillBot replacement with a documented first-run path and a recoverable export. ### Steps 1. Write the user-facing runbook Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. Files: `README.md`, `.env.example` 2. Create and rehearse a recoverable backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Files: `OPERATIONS.md`, `scripts/backup.py` 3. Reproduce the first-run experience Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Files: `README.md`, `verification.md` ```sh python -m pip install -r requirements.txt python -m unittest discover -s test ``` ### Done when - [ ] A new folder reaches the documented fixture outcome using only README instructions. - [ ] A backup restored in isolation preserves the proof data and can be opened. ### Watch out - Export without an import or restore rehearsal is not verified portability. ## M6 · Operate and share with access controls (production only) Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. ### Steps 1. Establish owner access before exposure Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. Files: `ARCHITECTURE.md`, `OPERATIONS.md` 2. Deploy a monitored service Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Files: `Caddyfile`, `OPERATIONS.md` ```sh waitress-serve --listen=127.0.0.1:5000 app:app ``` 3. Rehearse loss and recovery Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. Files: `OPERATIONS.md`, `release-checklist.md` ### Done when - [ ] An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. - [ ] A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. - [ ] Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. ### Watch out - Product mode is additional engineering, not a switch that makes a local prototype production-ready. ===== OPERATIONS.md ===== # Operations · QuillBot ## Backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. ## Restore Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Do a restore drill before the first real user, and write the date here when it passes. ## Monitoring Check HTTP availability, free disk, backup age and domain failures for Source and constraints, Generate alternatives, Accept and export. Alert without logging private payloads. ## Incident checklist Pause outbound jobs and public intake as appropriate, preserve redacted diagnostics, restore an isolated verified backup, rotate affected credentials and reconcile uncertain effects before reopening. 1. Contain the issue without destroying evidence or user data. 2. Record the timeline and affected scope. 3. Rotate exposed secrets and revoke compromised sessions or credentials. 4. Restore from a verified backup when needed. 5. Document the root cause, the remediation and the regression test. ## Release gate - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] A private-data authorization check passes using a second identity. - [ ] An off-host restore drill has a date, observed result and recovery time in OPERATIONS.md. - [ ] README names the excluded vendor capabilities and actual provider/hosting costs. ## Launch constraint Do not market omitted QuillBot capabilities as implemented. The non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered. ===== .env.example ===== # Copy to .env and fill in. Never commit .env; this file documents it. # Required. A new private folder this application creates on first run; never serve it as static files. DATA_DIR=./data/quillbot # Required · secret. Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. SECRET_KEY=replace-with-a-random-secret # Required. Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. APP_MODE=indie # Required. The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. SITE_URL=http://127.0.0.1:5000 # Required. Keep the inference service bound to loopback; the backend calls it, never the public browser. OLLAMA_URL=http://127.0.0.1:11434 # Required. Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. LOCAL_MODEL=replace-with-installed-local-model
README.md
# QuillBot · indie build Build a local paraphrasing desk with protected facts and visible alternatives. Estimated effort: **multi-day**. Work `BUILD_PLAN.md` top to bottom · every phase ends in a check that has to pass before the next one starts. ## Stack | Part | Choice | Why | | --- | --- | --- | | Runtime | Python 3.12+ and Flask | A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. | | Storage | SQLite through Python sqlite3 | Local ownership with explicit transactions and a portable backup path. | | Interface | Jinja HTML templates, CSS and vanilla JavaScript | Implement the specified screens directly with labelled controls and progressive enhancement. | | Verification | Python unittest and browser acceptance fixtures | Check invariants and the actual user workflow before the next phase. | | Generation | Ollama local HTTP API | A backend-only adapter with a configurable installed local model and visible failure states. | ## Before you start Have every one of these ready. The plan assumes them from step one. - [ ] **Python 3.12 or newer and a terminal** · Python is free; this local prototype requires no hosting subscription. - Why: The local backend, tests and storage use Python. - Get it: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. - Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. - [ ] **A current desktop browser and text editor** · No paid service required for this local step. - Why: You need to view the local interface and edit generated project files. - Get it: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. - Verify: You can create a text file in the project folder and open browser developer tools. - [ ] **QuillBot acceptance sample** · No paid service required for this local step. - Why: This fixture makes the first end-to-end check reproducible. - Get it: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. - Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. - [ ] **Confirm the bounded replacement** · No paid service required for this local step. - Why: The full commercial product is larger than this guide. - Get it: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. - Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. - [ ] **Ollama with an explicitly local model** · No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Why: Generation requires a running model; ordinary editing remains usable while it is unavailable. - Get it: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. - Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. ## Quick start ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` Then copy `.env.example` to `.env` and fill in the values it documents. ## Honest limits This build deliberately does not replace: - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync If one of those is essential to you, that is the reason to keep paying for QuillBot, and the README should say so rather than pretend.
BRIEF.md
# Build brief · QuillBot The one-shot brief this plan expands. `BUILD_PLAN.md` (or `MILESTONES.md`) is the same sequence broken into steps and checks; where the two disagree, the plan wins. Build me a local paraphrasing desk with protected facts and visible alternatives as a bounded replacement for QuillBot. Build it in phases in the order below. Do not write the whole product in one pass. Finish the current phase, run its Done when checks, fix failures, then continue. Indie mode completes Phases 1-5. Phase 6 is required before shared or public deployment. ### Stack (fixed, do not substitute) - Runtime: Python 3.12+ and Flask. A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. - Storage: SQLite through Python sqlite3. Local ownership with explicit transactions and a portable backup path. - Interface: Jinja HTML templates, CSS and vanilla JavaScript. Implement the specified screens directly with labelled controls and progressive enhancement. - Verification: Python unittest and browser acceptance fixtures. Check invariants and the actual user workflow before the next phase. - Generation: Ollama local HTTP API. A backend-only adapter with a configurable installed local model and visible failure states. ### Data model (create this before Phase 1) - documents(id,title,text,revision) - requests(id,document_id,revision,mode,protected_json) - candidates(id,request_id,text,model,state) - glossary(term,replacement) - decisions(id,candidate_id,action,at) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. ### Prerequisites and configuration - Python 3.12 or newer and a terminal: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. Cost: Python is free; this local prototype requires no hosting subscription. - A current desktop browser and text editor: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. Verify: You can create a text file in the project folder and open browser developer tools. Cost: No paid service required for this local step. - QuillBot acceptance sample: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. Cost: No paid service required for this local step. - Confirm the bounded replacement: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. Cost: No paid service required for this local step. - Ollama with an explicitly local model: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. Cost: No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Configuration: DATA_DIR, SECRET_KEY, APP_MODE, SITE_URL, OLLAMA_URL, LOCAL_MODEL. Ship .env.example, replace placeholders and exclude secrets from git. ### Phase 1 · Local foundation and data contract Build: Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. - Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Commands, after creating the named files: `python -m venv .venv`; `python -m pip install Flask Flask-WTF python-dotenv waitress tzdata`; `python -m pip freeze > requirements.txt`; `python -m flask --app app run --host 127.0.0.1`. - For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Commands, after creating the named files: `python manage.py init`; `python manage.py seed`. - Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. - Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Commands, after creating the named files: `python scripts/model_probe.py`. - Trap: The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. Done when: The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. Restarting preserves the seeded records or canonical files; running init again deletes nothing. A cross-origin state-changing request to an admin route is refused. Do not build yet: Do not start source and constraints until these checks pass. ### Phase 2 · Source and constraints Build: Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Paraphrasing is not a way to manufacture facts or erase the need to credit a source. Done when: The preview shows the exact selected text and protected tokens before generation. An empty selection cannot trigger a paid or local inference request. Do not build yet: Do not start generate alternatives until these checks pass. ### Phase 3 · Generate alternatives Build: Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Render a word diff for each candidate and label failed constraints instead of silently repairing them. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Token preservation is a mechanical check; a human still needs to check whether meaning changed. Done when: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. A model outage leaves the source and selection intact. Do not build yet: Do not start accept and export until these checks pass. ### Phase 4 · Accept and export Build: Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Export original, accepted text and decision history in JSON plus a plain-text final document. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. Done when: Accepting alternative two leaves alternative one recorded but unapplied. Undo restores the exact original paragraph. Do not build yet: Do not start portable delivery and clean-start proof until these checks pass. ### Phase 5 · Portable delivery and clean-start proof Build: Finish the QuillBot replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. - Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. - Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Commands, after creating the named files: `python -m pip install -r requirements.txt`; `python -m unittest discover -s test`. - Trap: Export without an import or restore rehearsal is not verified portability. Done when: A new folder reaches the documented fixture outcome using only README instructions. A backup restored in isolation preserves the proof data and can be opened. Do not build yet: Do not start operate and share with access controls until these checks pass. ### Phase 6 · Operate and share with access controls (product-builder only) Build: Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. - Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. - Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Commands, after creating the named files: `waitress-serve --listen=127.0.0.1:5000 app:app`. - Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. - Trap: Product mode is additional engineering, not a switch that makes a local prototype production-ready. Done when: An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. Do not build yet: Do not add new providers or vendor-scale features until the release gates are recorded. ### Out of scope (and why) - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions: retain the paid product if this capability is essential; it is outside this bounded build. - plagiarism/AI detector workflows: retain the paid product if this capability is essential; it is outside this bounded build. - rewrite modes: retain the paid product if this capability is essential; it is outside this bounded build. - history: retain the paid product if this capability is essential; it is outside this bounded build. - polish: retain the paid product if this capability is essential; it is outside this bounded build. - account sync: retain the paid product if this capability is essential; it is outside this bounded build. ### README must contain - Exact install, configure, initialize, start, test and recovery commands for a clean folder. - The schema, fixture, acceptance results, private data locations and export format. - Every prerequisite and secret source, actual running costs and deliberately excluded capabilities. - An honest distinction between tests actually run and checks still awaiting real credentials or deployment. - Dependency documentation reviewed 2026-09-05: https://flask.palletsprojects.com/en/stable/installation/ ; https://docs.python.org/3/library/sqlite3.html ; https://flask-wtf.readthedocs.io/en/1.2.x/csrf/ ; https://docs.pylonsproject.org/projects/waitress/en/stable/usage.html ; https://docs.ollama.com/api/chat ; https://docs.ollama.com/cloud. Recheck before upgrading; freeze the versions actually tested.
AGENTS.md
# Agent instructions · QuillBot indie build - Read `README.md` and `BUILD_PLAN.md` before writing code. The stack is fixed: Python 3.12+ and Flask, SQLite through Python sqlite3, Jinja HTML templates, CSS and vanilla JavaScript, Python unittest and browser acceptance fixtures, Ollama local HTTP API. Do not substitute. - Work one phase at a time, in order. Do not start a phase until every "Done when" item of the previous one passes. - Prefer the fewest moving parts that satisfy the step. No frameworks, services or dependencies the plan does not name. - Secrets live in `.env`, never in source or logs. Keep `.env.example` current when a variable is introduced. - Do not invent cryptography, security guarantees, APIs or compliance claims. - Add a focused test for every destructive, security-sensitive or data-loss path the plan names. - Run the project checks before declaring a phase complete, and record any deliberate shortcut in the README under "Tradeoffs". ## Known traps - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Token preservation is a mechanical check; a human still needs to check whether meaning changed. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - Export without an import or restore rehearsal is not verified portability.
BUILD_PLAN.md
# Build plan · QuillBot Build a local paraphrasing desk with protected facts and visible alternatives. Phases are in dependency order. Each ends in a "Done when" list; treat an unticked item as a blocker, not a note. ## Phase 1 · Local foundation and data contract Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. ### Steps 1. Create and start the local application Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Files: `app.py`, `requirements.txt`, `.env.example`, `.gitignore` ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` 2. Implement storage and seed the named fixture For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Files: `schema.sql`, `db.py`, `manage.py`, `fixtures/README.md` ```sh python manage.py init python manage.py seed ``` 3. Protect the local request boundary Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. Files: `app.py`, `templates/base.html`, `test/test_foundation.py` 4. Verify the selected local model Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Files: `providers/local_model.py`, `scripts/model_probe.py` ```sh python scripts/model_probe.py ``` ### Done when - [ ] The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. - [ ] Restarting preserves the seeded records or canonical files; running init again deletes nothing. - [ ] A cross-origin state-changing request to an admin route is refused. ### Watch out - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. ## Phase 2 · Source and constraints Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. ### Steps 1. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Files: `features/source_and_constraints.py`, `templates/source_and_constraints.html` 2. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Files: `features/source_and_constraints.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_source_and_constraints.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] An empty selection cannot trigger a paid or local inference request. ### Watch out - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. ## Phase 3 · Generate alternatives Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. ### Steps 1. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Files: `features/generate_alternatives.py`, `templates/generate_alternatives.html` 2. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Files: `features/generate_alternatives.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_generate_alternatives.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] A model outage leaves the source and selection intact. ### Watch out - Token preservation is a mechanical check; a human still needs to check whether meaning changed. ## Phase 4 · Accept and export Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. ### Steps 1. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Files: `features/accept_and_export.py`, `templates/accept_and_export.html` 2. Export original, accepted text and decision history in JSON plus a plain-text final document. Export original, accepted text and decision history in JSON plus a plain-text final document. Files: `features/accept_and_export.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_accept_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] Undo restores the exact original paragraph. ### Watch out - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the QuillBot replacement with a documented first-run path and a recoverable export. ### Steps 1. Write the user-facing runbook Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. Files: `README.md`, `.env.example` 2. Create and rehearse a recoverable backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Files: `OPERATIONS.md`, `scripts/backup.py` 3. Reproduce the first-run experience Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Files: `README.md`, `verification.md` ```sh python -m pip install -r requirements.txt python -m unittest discover -s test ``` ### Done when - [ ] A new folder reaches the documented fixture outcome using only README instructions. - [ ] A backup restored in isolation preserves the proof data and can be opened. ### Watch out - Export without an import or restore rehearsal is not verified portability. ## Not in this build - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync ## After v1, if you want it - Extend accept and export only after the fixture and recovery checks pass. - Before adding another integration, document its credentials, limits, cost and failure behavior with primary-source links.
.env.example
# Copy to .env and fill in. Never commit .env; this file documents it. # Required. A new private folder this application creates on first run; never serve it as static files. DATA_DIR=./data/quillbot # Required · secret. Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. SECRET_KEY=replace-with-a-random-secret # Required. Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. APP_MODE=indie # Required. The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. SITE_URL=http://127.0.0.1:5000 # Required. Keep the inference service bound to loopback; the backend calls it, never the public browser. OLLAMA_URL=http://127.0.0.1:11434 # Required. Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. LOCAL_MODEL=replace-with-installed-local-model
PRODUCT.md
# QuillBot · product brief ## Problem A paraphraser/summarizer/grammar wrapper over an LLM and LanguageTool is easy to build; the paid app wins on UX, extensions, plagiarism workflows, and bundled tools. ## Product outcome An operated version of a local paraphrasing desk with protected facts and visible alternatives, with authorized access, restore evidence and honest scope limits. ## Target user A builder who needs a maintainable product foundation, not a one-off demo. ## Required capabilities - LLM API - LanguageTool or grammar API - browser extension if in-app writing is needed ## Explicit non-goals for v1 - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions - plagiarism/AI detector workflows - rewrite modes - history - polish - account sync ## Success criteria - The preview shows the exact selected text and protected tokens before generation. - A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - Accepting alternative two leaves alternative one recorded but unapplied. - A private-data authorization check passes using a second identity. - An off-host restore drill has a date, observed result and recovery time in OPERATIONS.md. - README names the excluded vendor capabilities and actual provider/hosting costs.
BRIEF.md
# Build brief · QuillBot The one-shot brief this plan expands. `BUILD_PLAN.md` (or `MILESTONES.md`) is the same sequence broken into steps and checks; where the two disagree, the plan wins. Build me a local paraphrasing desk with protected facts and visible alternatives as a bounded replacement for QuillBot. Build it in phases in the order below. Do not write the whole product in one pass. Finish the current phase, run its Done when checks, fix failures, then continue. Indie mode completes Phases 1-5. Phase 6 is required before shared or public deployment. ### Stack (fixed, do not substitute) - Runtime: Python 3.12+ and Flask. A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. - Storage: SQLite through Python sqlite3. Local ownership with explicit transactions and a portable backup path. - Interface: Jinja HTML templates, CSS and vanilla JavaScript. Implement the specified screens directly with labelled controls and progressive enhancement. - Verification: Python unittest and browser acceptance fixtures. Check invariants and the actual user workflow before the next phase. - Generation: Ollama local HTTP API. A backend-only adapter with a configurable installed local model and visible failure states. ### Data model (create this before Phase 1) - documents(id,title,text,revision) - requests(id,document_id,revision,mode,protected_json) - candidates(id,request_id,text,model,state) - glossary(term,replacement) - decisions(id,candidate_id,action,at) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. ### Prerequisites and configuration - Python 3.12 or newer and a terminal: Install Python from python.org. Open a terminal in a new empty project folder. On Windows, use py -3 where this guide says python if python is not on PATH; on macOS/Linux use python3 if needed. Create .venv and activate it before installing packages. Verify: python --version reports 3.12+ and python -c "import sqlite3" succeeds. Cost: Python is free; this local prototype requires no hosting subscription. - A current desktop browser and text editor: Use an installed Chrome, Firefox or Edge browser. Open the empty project folder in your editor; open the terminal there, not in this catalog repository. Verify: You can create a text file in the project folder and open browser developer tools. Cost: No paid service required for this local step. - QuillBot acceptance sample: Create synthetic sample data before implementation: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Save it under fixtures/ with the expected results in fixtures/README.md; use no real credentials or customer records. Verify: The fixture files and expected outcomes exist and can be inspected without a vendor account. Cost: No paid service required for this local step. - Confirm the bounded replacement: The deliverable is a local paraphrasing desk with protected facts and visible alternatives. Read every exclusion below. Indie mode runs locally; any public or shared use requires the product access and deployment gates first. Verify: You can name the primary workflow and the vendor features this version deliberately leaves out. Cost: No paid service required for this local step. - Ollama with an explicitly local model: Install Ollama from the official site, choose a locally runnable model from its library that fits available RAM, download it, and copy its exact installed name into LOCAL_MODEL. Use the documented local-only configuration, exclude cloud model names, and record model license, download size and tested memory use. Verify: ollama list shows the chosen model; a short local prompt succeeds with network access disabled after download. Cost: No cloud inference fee for this local configuration; you supply disk space, compute and electricity. - Configuration: DATA_DIR, SECRET_KEY, APP_MODE, SITE_URL, OLLAMA_URL, LOCAL_MODEL. Ship .env.example, replace placeholders and exclude secrets from git. ### Phase 1 · Local foundation and data contract Build: Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. - Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Commands, after creating the named files: `python -m venv .venv`; `python -m pip install Flask Flask-WTF python-dotenv waitress tzdata`; `python -m pip freeze > requirements.txt`; `python -m flask --app app run --host 127.0.0.1`. - For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Commands, after creating the named files: `python manage.py init`; `python manage.py seed`. - Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. - Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Commands, after creating the named files: `python scripts/model_probe.py`. - Trap: The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. Done when: The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. Restarting preserves the seeded records or canonical files; running init again deletes nothing. A cross-origin state-changing request to an admin route is refused. Do not build yet: Do not start source and constraints until these checks pass. ### Phase 2 · Source and constraints Build: Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. - Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Paraphrasing is not a way to manufacture facts or erase the need to credit a source. Done when: The preview shows the exact selected text and protected tokens before generation. An empty selection cannot trigger a paid or local inference request. Do not build yet: Do not start generate alternatives until these checks pass. ### Phase 3 · Generate alternatives Build: Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. - Render a word diff for each candidate and label failed constraints instead of silently repairing them. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Token preservation is a mechanical check; a human still needs to check whether meaning changed. Done when: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. A model outage leaves the source and selection intact. Do not build yet: Do not start accept and export until these checks pass. ### Phase 4 · Accept and export Build: Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Apply only the selected candidate if the original revision matches; offer undo as a new revision. - Export original, accepted text and decision history in JSON plus a plain-text final document. - Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Commands, after creating the named files: `python -m unittest discover -s test`. - Trap: Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. Done when: Accepting alternative two leaves alternative one recorded but unapplied. Undo restores the exact original paragraph. Do not build yet: Do not start portable delivery and clean-start proof until these checks pass. ### Phase 5 · Portable delivery and clean-start proof Build: Finish the QuillBot replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. - Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. - Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Commands, after creating the named files: `python -m pip install -r requirements.txt`; `python -m unittest discover -s test`. - Trap: Export without an import or restore rehearsal is not verified portability. Done when: A new folder reaches the documented fixture outcome using only README instructions. A backup restored in isolation preserves the proof data and can be opened. Do not build yet: Do not start operate and share with access controls until these checks pass. ### Phase 6 · Operate and share with access controls (product-builder only) Build: Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. - Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. - Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Commands, after creating the named files: `waitress-serve --listen=127.0.0.1:5000 app:app`. - Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. - Trap: Product mode is additional engineering, not a switch that makes a local prototype production-ready. Done when: An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. Do not build yet: Do not add new providers or vendor-scale features until the release gates are recorded. ### Out of scope (and why) - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - This is a local paraphrasing desk with protected facts and visible alternatives; full QuillBot feature parity, vendor hosting and support are not included. - browser/Word extensions: retain the paid product if this capability is essential; it is outside this bounded build. - plagiarism/AI detector workflows: retain the paid product if this capability is essential; it is outside this bounded build. - rewrite modes: retain the paid product if this capability is essential; it is outside this bounded build. - history: retain the paid product if this capability is essential; it is outside this bounded build. - polish: retain the paid product if this capability is essential; it is outside this bounded build. - account sync: retain the paid product if this capability is essential; it is outside this bounded build. ### README must contain - Exact install, configure, initialize, start, test and recovery commands for a clean folder. - The schema, fixture, acceptance results, private data locations and export format. - Every prerequisite and secret source, actual running costs and deliberately excluded capabilities. - An honest distinction between tests actually run and checks still awaiting real credentials or deployment. - Dependency documentation reviewed 2026-09-05: https://flask.palletsprojects.com/en/stable/installation/ ; https://docs.python.org/3/library/sqlite3.html ; https://flask-wtf.readthedocs.io/en/1.2.x/csrf/ ; https://docs.pylonsproject.org/projects/waitress/en/stable/usage.html ; https://docs.ollama.com/api/chat ; https://docs.ollama.com/cloud. Recheck before upgrading; freeze the versions actually tested.
ARCHITECTURE.md
# Architecture · QuillBot ## Stack | Part | Choice | Why | | --- | --- | --- | | Runtime | Python 3.12+ and Flask | A small local HTTP application with readable server-side handlers and no JavaScript build pipeline. | | Storage | SQLite through Python sqlite3 | Local ownership with explicit transactions and a portable backup path. | | Interface | Jinja HTML templates, CSS and vanilla JavaScript | Implement the specified screens directly with labelled controls and progressive enhancement. | | Verification | Python unittest and browser acceptance fixtures | Check invariants and the actual user workflow before the next phase. | | Generation | Ollama local HTTP API | A backend-only adapter with a configurable installed local model and visible failure states. | ## Modules Each module has one owner concern and a documented way to replace it. | Module | Owns | How to replace it | | --- | --- | --- | | Data and identity | documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at) | Keep stable ids and a versioned repository interface; migrate storage behind it with a fixture round-trip. | | Source and constraints | Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. | Keep the acceptance contract: The preview shows the exact selected text and protected tokens before generation. Replace only this module after replaying its fixture; preserve ids and existing records. | | Generate alternatives | Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. | Keep the acceptance contract: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Replace only this module after replaying its fixture; preserve ids and existing records. | | Accept and export | Apply only the selected candidate if the original revision matches; offer undo as a new revision. | Keep the acceptance contract: Accepting alternative two leaves alternative one recorded but unapplied. Replace only this module after replaying its fixture; preserve ids and existing records. | | Operations | Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. | Change host or backup destination only after an isolated restore and authorization check. | ## Configuration Every runtime setting is an environment variable documented in `.env.example`, validated at startup, with a safe local default wherever one exists. - `DATA_DIR` · required · A new private folder this application creates on first run; never serve it as static files. - `SECRET_KEY` · required, secret · Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. - `APP_MODE` · required · Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. - `SITE_URL` · required · The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. - `OLLAMA_URL` · required · Keep the inference service bound to loopback; the backend calls it, never the public browser. - `LOCAL_MODEL` · required · Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. ## Production baseline - Security: least privilege, input validation at every boundary, secret redaction in logs, rate limits on abuse-prone paths, no invented security primitives. - Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore procedures that have been exercised. - Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, timeouts. - Observability: structured logs with request or operation ids, an error-tracking hook, and health and readiness checks where a server exists. - Quality: unit tests for domain rules, integration tests at module boundaries, one end-to-end test of the critical path. ## Decision records For each dependency in the stack table, keep a short note: why it was chosen, its failure mode, and how it is replaced. Do not add infrastructure until a requirement in `PRODUCT.md` justifies it.
AGENTS.md
# Agent instructions · QuillBot product build - Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code. The stack is fixed: Python 3.12+ and Flask, SQLite through Python sqlite3, Jinja HTML templates, CSS and vanilla JavaScript, Python unittest and browser acceptance fixtures, Ollama local HTTP API. - Implement milestone by milestone from `MILESTONES.md`; keep each change reviewable and leave the application runnable at every commit. - Treat authentication, payments, encryption, imports, webhooks and destructive actions as high-risk boundaries when present. - Never invent cryptography or silently weaken a requirement to make a check pass. - Put every external service behind an interface with a deterministic fake for tests. - Add migrations and rollback or recovery notes for every persistent data change. - Log useful operational context without credentials, tokens, passwords or personal data. - Update documentation and run every check before completing a milestone. ## Known traps - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. - Token preservation is a mechanical check; a human still needs to check whether meaning changed. - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. - Export without an import or restore rehearsal is not verified portability. - Product mode is additional engineering, not a switch that makes a local prototype production-ready.
MILESTONES.md
# Delivery milestones · QuillBot Estimated effort: **multi-day** for the indie phases; the production-only milestones add the trust and operability layer. ## M1 · Local foundation and data contract Create the runnable local foundation for a local paraphrasing desk with protected facts and visible alternatives, including the real schema and acceptance fixture. ### Steps 1. Create and start the local application Run the venv command first, then stop and activate it before running the remaining commands. Use your OS instructions: Windows .venv\Scripts\activate.bat in cmd, or .venv\Scripts\Activate.ps1 in PowerShell; macOS/Linux source .venv/bin/activate. Then install the listed packages. Create app.py exposing app, load .env with python-dotenv, and add a /healthz route. Freeze tested dependency versions to requirements.txt. Create .env manually from .env.example; replace SECRET_KEY before launch. Files: `app.py`, `requirements.txt`, `.env.example`, `.gitignore` ```sh python -m venv .venv python -m pip install Flask Flask-WTF python-dotenv waitress tzdata python -m pip freeze > requirements.txt python -m flask --app app run --host 127.0.0.1 ``` 2. Implement storage and seed the named fixture For database-backed state create schema.sql and db.py using this model: documents(id,title,text,revision); requests(id,document_id,revision,mode,protected_json); candidates(id,request_id,text,model,state); glossary(term,replacement); decisions(id,candidate_id,action,at). Add the auxiliary relationships explicitly used in later phases; use stable ids, foreign keys, parameterized values and transactions. For canonical files use atomic replacement and hashes instead. Implement python manage.py init and python manage.py seed to create only synthetic data: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Re-running init must not erase data. Files: `schema.sql`, `db.py`, `manage.py`, `fixtures/README.md` ```sh python manage.py init python manage.py seed ``` 3. Protect the local request boundary Install Flask-WTF CSRF protection for forms and same-origin fetches, validate Host and Origin against SITE_URL, bound inputs and escape output. Deliberately public intake endpoints get bounded validation and rate limits; signed provider webhooks use signature checks instead of browser CSRF tokens. All other admin routes stay local until product authentication exists. When a later phase tests viewer/member permissions, implement the users, hashed passwords, expiring server sessions and role checks in this foundation first; product mode must never use a fabricated identity from request input. Add error, empty, keyboard-focus and retry states now. Files: `app.py`, `templates/base.html`, `test/test_foundation.py` 4. Verify the selected local model Create providers/local_model.py with a POST /api/chat adapter using the configured local model and stream:false. Validate structured output, bound input/output, set a timeout and reject cloud models or non-loopback inference URLs. Add a probe that sends one harmless prompt and a test double for deterministic tests. Missing model setup must disable generation with a specific error while leaving editing usable. Files: `providers/local_model.py`, `scripts/model_probe.py` ```sh python scripts/model_probe.py ``` ### Done when - [ ] The documented start command serves /healthz and the initial screen at http://127.0.0.1:5000. - [ ] Restarting preserves the seeded records or canonical files; running init again deletes nothing. - [ ] A cross-origin state-changing request to an admin route is refused. ### Watch out - The Flask development server is for local development only. Loopback binding alone does not replace CSRF and origin validation. ## M2 · Source and constraints Source and constraints for QuillBot: Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. ### Steps 1. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Create a plain-text editor with selected-span rewriting and standard/shorter/formal modes. Files: `features/source_and_constraints.py`, `templates/source_and_constraints.html` 2. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Let the user mark names, dates, numbers and quotations as protected; retain the original selection and revision. Files: `features/source_and_constraints.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: The preview shows the exact selected text and protected tokens before generation. Then check: An empty selection cannot trigger a paid or local inference request. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_source_and_constraints.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] An empty selection cannot trigger a paid or local inference request. ### Watch out - Paraphrasing is not a way to manufacture facts or erase the need to credit a source. ## M3 · Generate alternatives Generate alternatives for QuillBot: Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. ### Steps 1. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Call the local model for two bounded alternatives and validate required protected tokens before showing them as usable. Files: `features/generate_alternatives.py`, `templates/generate_alternatives.html` 2. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Render a word diff for each candidate and label failed constraints instead of silently repairing them. Files: `features/generate_alternatives.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. Then check: A model outage leaves the source and selection intact. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_generate_alternatives.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] A model outage leaves the source and selection intact. ### Watch out - Token preservation is a mechanical check; a human still needs to check whether meaning changed. ## M4 · Accept and export Accept and export for QuillBot: Apply only the selected candidate if the original revision matches; offer undo as a new revision. ### Steps 1. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Apply only the selected candidate if the original revision matches; offer undo as a new revision. Files: `features/accept_and_export.py`, `templates/accept_and_export.html` 2. Export original, accepted text and decision history in JSON plus a plain-text final document. Export original, accepted text and decision history in JSON plus a plain-text final document. Files: `features/accept_and_export.py` 3. Exercise the acceptance fixture Use A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Check: Accepting alternative two leaves alternative one recorded but unapplied. Then check: Undo restores the exact original paragraph. Add a focused regression for the failure case under test/ using a temporary database or folder and fake external services; also perform the visible workflow in a browser. Files: `test/test_accept_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] Undo restores the exact original paragraph. ### Watch out - Plagiarism detection, proprietary paraphrase quality and across-app extensions are excluded. ## M5 · Portable delivery and clean-start proof Finish the QuillBot replacement with a documented first-run path and a recoverable export. ### Steps 1. Write the user-facing runbook Document prerequisites, every configuration variable, data locations and the three domain workflows: Source and constraints; Generate alternatives; Accept and export. Include the exclusions, actual costs and source check date 2026-09-05. Commands shown earlier that reference project files are files the builder must implement before running them. Files: `README.md`, `.env.example` 2. Create and rehearse a recoverable backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Files: `OPERATIONS.md`, `scripts/backup.py` 3. Reproduce the first-run experience Use a new folder and only README instructions to reach the fixture outcome. Install from requirements.txt, initialize storage, run the tests and exercise the UI at 375px and 1280px; use keyboard-only controls and inspect browser errors. Record exactly what passed; do not mark unrun checks complete. Files: `README.md`, `verification.md` ```sh python -m pip install -r requirements.txt python -m unittest discover -s test ``` ### Done when - [ ] A new folder reaches the documented fixture outcome using only README instructions. - [ ] A backup restored in isolation preserves the proof data and can be opened. ### Watch out - Export without an import or restore rehearsal is not verified portability. ## M6 · Operate and share with access controls (production only) Product-builder only: make a local paraphrasing desk with protected facts and visible alternatives operable for its stated audience before allowing remote access. ### Steps 1. Establish owner access before exposure Add owner/member/viewer authorization as appropriate, password hashes through Werkzeug, expiring server-side sessions, CSRF and login rate limits. Add users, sessions and audit schema migrations plus an owner-init command prompting securely for its password. Enforce ownership on every private read/write/download and fail closed when product setup is incomplete. Existing learner or admin identities must use this same boundary. Files: `ARCHITECTURE.md`, `OPERATIONS.md` 2. Deploy a monitored service Serve app:app with Waitress on loopback behind Caddy HTTPS. Configure trusted proxy headers narrowly, Secure/HttpOnly/SameSite cookies, upload limits, request ids and structured logs without private content. Run background jobs as a separate supervised process when the domain workflow requires them. Files: `Caddyfile`, `OPERATIONS.md` ```sh waitress-serve --listen=127.0.0.1:5000 app:app ``` 3. Rehearse loss and recovery Add a scheduled encrypted off-host backup using this procedure: Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. Monitor health, disk space, failed jobs and backup age. Stop the service to test an alert; rehearse recovery with outbound effects disabled and record recovery time. Rotate any exposed credentials and require reconciliation before resuming queues. Files: `OPERATIONS.md`, `release-checklist.md` ### Done when - [ ] An unauthenticated visitor cannot read private records, download private files or mutate the admin surface. - [ ] A viewer cannot mutate data by making a direct request, and guessed ids cannot cross ownership boundaries. - [ ] Stopping the service triggers the configured alert and the latest off-host backup restores the fixture in isolation. ### Watch out - Product mode is additional engineering, not a switch that makes a local prototype production-ready.
OPERATIONS.md
# Operations · QuillBot ## Backup Use sqlite3.Connection.backup for the database in DATA_DIR and pause writers while taking the matching attachment snapshot. Keep schema version, hashes and a manifest for quillbot. ## Restore Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A paragraph containing a person name, a date and a monetary amount that must survive rewriting. Compare ids/counts and open the result before recording the restore date. Never test a restore over the only live copy. Do a restore drill before the first real user, and write the date here when it passes. ## Monitoring Check HTTP availability, free disk, backup age and domain failures for Source and constraints, Generate alternatives, Accept and export. Alert without logging private payloads. ## Incident checklist Pause outbound jobs and public intake as appropriate, preserve redacted diagnostics, restore an isolated verified backup, rotate affected credentials and reconcile uncertain effects before reopening. 1. Contain the issue without destroying evidence or user data. 2. Record the timeline and affected scope. 3. Rotate exposed secrets and revoke compromised sessions or credentials. 4. Restore from a verified backup when needed. 5. Document the root cause, the remediation and the regression test. ## Release gate - [ ] The preview shows the exact selected text and protected tokens before generation. - [ ] A candidate that changes the monetary amount is flagged and cannot be accepted as constraint-passing. - [ ] Accepting alternative two leaves alternative one recorded but unapplied. - [ ] A private-data authorization check passes using a second identity. - [ ] An off-host restore drill has a date, observed result and recovery time in OPERATIONS.md. - [ ] README names the excluded vendor capabilities and actual provider/hosting costs. ## Launch constraint Do not market omitted QuillBot capabilities as implemented. The non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.
.env.example
# Copy to .env and fill in. Never commit .env; this file documents it. # Required. A new private folder this application creates on first run; never serve it as static files. DATA_DIR=./data/quillbot # Required · secret. Generate with python -c "import secrets; print(secrets.token_hex(32))" and save only in .env. SECRET_KEY=replace-with-a-random-secret # Required. Use indie for loopback-only personal work. Product mode must refuse to start until owner login and the deployment gates are configured. APP_MODE=indie # Required. The origin used for local forms and links; replace with the chosen HTTPS origin in product mode. SITE_URL=http://127.0.0.1:5000 # Required. Keep the inference service bound to loopback; the backend calls it, never the public browser. OLLAMA_URL=http://127.0.0.1:11434 # Required. Copy the exact non-cloud name from ollama list; preflight must reject this placeholder. LOCAL_MODEL=replace-with-installed-local-model
$ choose a build depth, inspect the files, then open the complete pack in your agent
They pay because it is available where they write and has purpose-built controls.
xbrowser/Word extensions
xplagiarism/AI detector workflows
xrewrite modes
xhistory
xpolish
xaccount sync
share on X ↗"I just replaced QuillBot ($19.95/mo) with one prompt"
Don't feel like building it? These folks already made it free.
Page AssistA browser sidebar that reads the page, rewrites the selection, and saves custom actions; your local model does the thinking.open source↗
Writing ToolsSelect text anywhere, hit a hotkey, and fix, rewrite, summarize, or obey a custom instruction without opening another tab.open source↗
WitsySystem-wide selected-text commands, reusable experts, a scratchpad, and document context; bring the model and skip the subscription.open source↗all 4 free alternatives to QuillBot →· no votes, no pay-to-list · just what's real
QuillBot pricing
| plan | monthly | annual (per mo) | what you get |
|---|---|---|---|
| free | $0 | $0 | 125 words/paraphrase; 1,200 words/summarization input; 20 AI Chat queries/day; 10 AI-detector scans/day up to 1,200 words; 3 image generations/day; 10 MB Flow storage. |
| premium | $19.95 | $8.33 | Unlimited paraphraser, AI Chat, and AI-detector use; 6,000 words/summarization input; 25,000 plagiarism words/month; 300 images/month; 100 MB Flow storage. |
| team 2-10 seats | — | $8.65/user | 2-10 seats; all Premium features; writer-management dashboard; centralized billing. |
| team 11-50 seats | — | $7.69/user | 11-50 seats; all Premium features; writer-management dashboard; centralized billing. |
| team 51+ seats | — | $6.73/user | 51+ seats; all Premium features; writer-management dashboard; centralized billing. |
free tier125 words/paraphrase; 1,200-word summarizer; 20 AI Chat queries/day; 10 AI-detector scans/day; 3 images/day
billingindividual Premium is monthly, 3-month, or annual; Team is annual-only
hidden costsPremium's 25,000 monthly plagiarism words do not roll over. Extra packs cost $2.45 for 6,250 words, $8.95 for 25,000, or $19.95 for 62,500; purchased packs roll over until used.
verified 2026-08-12 · source ↗
Vibecode QuillBot
Yes. A competent AI coding agent (Claude Code, Codex, Cursor) can build a usable personal QuillBot replacement in one session with the prompt on this page. It runs on your own machine or server with no subscription.
How much does QuillBot cost?
QuillBot costs about $19.95/month (Premium, checked 2026-07-30), which is $239.39999999999998 per year. That's what you save by replacing it with one prompt.
What do I lose by replacing QuillBot?
Honestly: browser/Word extensions; plagiarism/AI detector workflows; rewrite modes; history; polish; account sync. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to QuillBot?
Yes: Page Assist (A browser sidebar that reads the page, rewrites the selection, and saves custom actions; your local model does the thinking.) Writing Tools (Select text anywhere, hit a hotkey, and fix, rewrite, summarize, or obey a custom instruction without opening another tab.) Witsy (System-wide selected-text commands, reusable experts, a scratchpad, and document context; bring the model and skip the subscription.) All 4 curated free alternatives are at vibecodeit.com/quillbot/alternatives. The prompt is for when you want it exactly your way.