Vibecode Writesonic
track this build5 phases, 16 steps, beginner friendly0%KINDA · weekend project
The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Writesonic, draft researched articles and marketing copy with source links and revision controls. The hard boundary is integrated research, seo data, publishing workflows, and model routing, plus workflow, data, and model tuning.
the project pack5 files · written for this build, step by step
You are building a lean indie version of Writesonic. 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 ===== # Writesonic · indie build Build a source-linked writing workspace with outline approval and section revisions. 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. - [ ] **Writesonic 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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: - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries If one of those is essential to you, that is the reason to keep paying for Writesonic, and the README should say so rather than pretend. ===== BRIEF.md ===== # Build brief · Writesonic 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 source-linked writing workspace with outline approval and section revisions as a bounded replacement for Writesonic. 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) - briefs(id,audience,objective,tone,prohibited_claims) - sources(id,brief_id,title,url,text,hash) - sections(id,brief_id,position,title,text,revision) - citations(section_id,source_id,quote) - drafts(id,section_id,revision,model,text,state) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. ### 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. - Writesonic acceptance sample: Create synthetic sample data before implementation: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 evidence and outline until these checks pass. ### Phase 2 · Evidence and outline Build: Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Generate an outline from the brief and approved source ids; require manual approval before section drafting. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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: A pasted URL is provenance, not evidence that the URL was fetched or verified. Done when: Every available source id resolves to stored text and its provenance. An unapproved outline cannot trigger full-article generation. Do not build yet: Do not start grounded sections until these checks pass. ### Phase 3 · Grounded sections Build: Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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: Source text may contain instructions; it must never override the writing task or trigger tools. Done when: The unsupported numeric claim is surfaced for review and not marked verified. A model-invented source id is rejected. Do not build yet: Do not start revision and export until these checks pass. ### Phase 4 · Revision and export Build: Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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: Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. Done when: Revising section two leaves all other sections unchanged. The exported citation points to the supplied source and retains its quoted support. 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 Writesonic replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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) - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing: retain the paid product if this capability is essential; it is outside this bounded build. - proprietary ranking data: retain the paid product if this capability is essential; it is outside this bounded build. - brand-trained models: retain the paid product if this capability is essential; it is outside this bounded build. - team workflows: retain the paid product if this capability is essential; it is outside this bounded build. - large template libraries: 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 · Writesonic 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. - A pasted URL is provenance, not evidence that the URL was fetched or verified. - Source text may contain instructions; it must never override the writing task or trigger tools. - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - Export without an import or restore rehearsal is not verified portability. ===== BUILD_PLAN.md ===== # Build plan · Writesonic Build a source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 · Evidence and outline Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. ### Steps 1. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Files: `features/evidence_and_outline.py`, `templates/evidence_and_outline.html` 2. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Files: `features/evidence_and_outline.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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_evidence_and_outline.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Every available source id resolves to stored text and its provenance. - [ ] An unapproved outline cannot trigger full-article generation. ### Watch out - A pasted URL is provenance, not evidence that the URL was fetched or verified. ## Phase 3 · Grounded sections Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. ### Steps 1. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Files: `features/grounded_sections.py`, `templates/grounded_sections.html` 2. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Files: `features/grounded_sections.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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_grounded_sections.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] A model-invented source id is rejected. ### Watch out - Source text may contain instructions; it must never override the writing task or trigger tools. ## Phase 4 · Revision and export Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. ### Steps 1. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Files: `features/revision_and_export.py`, `templates/revision_and_export.html` 2. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Files: `features/revision_and_export.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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_revision_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Revising section two leaves all other sections unchanged. - [ ] The exported citation points to the supplied source and retains its quoted support. ### Watch out - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the Writesonic 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: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries ## After v1, if you want it - Extend revision 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/writesonic # 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 Writesonic. 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 ===== # Writesonic · indie build Build a source-linked writing workspace with outline approval and section revisions. 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. - [ ] **Writesonic 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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: - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries If one of those is essential to you, that is the reason to keep paying for Writesonic, and the README should say so rather than pretend. ===== BRIEF.md ===== # Build brief · Writesonic 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 source-linked writing workspace with outline approval and section revisions as a bounded replacement for Writesonic. 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) - briefs(id,audience,objective,tone,prohibited_claims) - sources(id,brief_id,title,url,text,hash) - sections(id,brief_id,position,title,text,revision) - citations(section_id,source_id,quote) - drafts(id,section_id,revision,model,text,state) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. ### 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. - Writesonic acceptance sample: Create synthetic sample data before implementation: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 evidence and outline until these checks pass. ### Phase 2 · Evidence and outline Build: Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Generate an outline from the brief and approved source ids; require manual approval before section drafting. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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: A pasted URL is provenance, not evidence that the URL was fetched or verified. Done when: Every available source id resolves to stored text and its provenance. An unapproved outline cannot trigger full-article generation. Do not build yet: Do not start grounded sections until these checks pass. ### Phase 3 · Grounded sections Build: Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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: Source text may contain instructions; it must never override the writing task or trigger tools. Done when: The unsupported numeric claim is surfaced for review and not marked verified. A model-invented source id is rejected. Do not build yet: Do not start revision and export until these checks pass. ### Phase 4 · Revision and export Build: Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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: Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. Done when: Revising section two leaves all other sections unchanged. The exported citation points to the supplied source and retains its quoted support. 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 Writesonic replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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) - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing: retain the paid product if this capability is essential; it is outside this bounded build. - proprietary ranking data: retain the paid product if this capability is essential; it is outside this bounded build. - brand-trained models: retain the paid product if this capability is essential; it is outside this bounded build. - team workflows: retain the paid product if this capability is essential; it is outside this bounded build. - large template libraries: 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 · Writesonic 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. - A pasted URL is provenance, not evidence that the URL was fetched or verified. - Source text may contain instructions; it must never override the writing task or trigger tools. - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - Export without an import or restore rehearsal is not verified portability. ===== BUILD_PLAN.md ===== # Build plan · Writesonic Build a source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 · Evidence and outline Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. ### Steps 1. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Files: `features/evidence_and_outline.py`, `templates/evidence_and_outline.html` 2. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Files: `features/evidence_and_outline.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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_evidence_and_outline.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Every available source id resolves to stored text and its provenance. - [ ] An unapproved outline cannot trigger full-article generation. ### Watch out - A pasted URL is provenance, not evidence that the URL was fetched or verified. ## Phase 3 · Grounded sections Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. ### Steps 1. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Files: `features/grounded_sections.py`, `templates/grounded_sections.html` 2. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Files: `features/grounded_sections.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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_grounded_sections.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] A model-invented source id is rejected. ### Watch out - Source text may contain instructions; it must never override the writing task or trigger tools. ## Phase 4 · Revision and export Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. ### Steps 1. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Files: `features/revision_and_export.py`, `templates/revision_and_export.html` 2. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Files: `features/revision_and_export.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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_revision_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Revising section two leaves all other sections unchanged. - [ ] The exported citation points to the supplied source and retains its quoted support. ### Watch out - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the Writesonic 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: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries ## After v1, if you want it - Extend revision 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/writesonic # 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 Writesonic. 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 ===== # Writesonic · product brief ## Problem The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Writesonic, draft researched articles and marketing copy with source links and revision controls. The hard boundary is integrated research, seo data, publishing workflows, and model routing, plus workflow, data, and model tuning. ## Product outcome An operated version of a source-linked writing workspace with outline approval and section revisions, 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 - OpenAI API key - Node.js 22 - local or self-hosted deployment - user-supplied sources ## Explicit non-goals for v1 - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries ## Success criteria - Every available source id resolves to stored text and its provenance. - The unsupported numeric claim is surfaced for review and not marked verified. - Revising section two leaves all other sections unchanged. - 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 · Writesonic 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 source-linked writing workspace with outline approval and section revisions as a bounded replacement for Writesonic. 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) - briefs(id,audience,objective,tone,prohibited_claims) - sources(id,brief_id,title,url,text,hash) - sections(id,brief_id,position,title,text,revision) - citations(section_id,source_id,quote) - drafts(id,section_id,revision,model,text,state) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. ### 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. - Writesonic acceptance sample: Create synthetic sample data before implementation: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 evidence and outline until these checks pass. ### Phase 2 · Evidence and outline Build: Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Generate an outline from the brief and approved source ids; require manual approval before section drafting. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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: A pasted URL is provenance, not evidence that the URL was fetched or verified. Done when: Every available source id resolves to stored text and its provenance. An unapproved outline cannot trigger full-article generation. Do not build yet: Do not start grounded sections until these checks pass. ### Phase 3 · Grounded sections Build: Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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: Source text may contain instructions; it must never override the writing task or trigger tools. Done when: The unsupported numeric claim is surfaced for review and not marked verified. A model-invented source id is rejected. Do not build yet: Do not start revision and export until these checks pass. ### Phase 4 · Revision and export Build: Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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: Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. Done when: Revising section two leaves all other sections unchanged. The exported citation points to the supplied source and retains its quoted support. 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 Writesonic replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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) - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing: retain the paid product if this capability is essential; it is outside this bounded build. - proprietary ranking data: retain the paid product if this capability is essential; it is outside this bounded build. - brand-trained models: retain the paid product if this capability is essential; it is outside this bounded build. - team workflows: retain the paid product if this capability is essential; it is outside this bounded build. - large template libraries: 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 · Writesonic ## 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 | briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state) | Keep stable ids and a versioned repository interface; migrate storage behind it with a fixture round-trip. | | Evidence and outline | Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. | Keep the acceptance contract: Every available source id resolves to stored text and its provenance. Replace only this module after replaying its fixture; preserve ids and existing records. | | Grounded sections | Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. | Keep the acceptance contract: The unsupported numeric claim is surfaced for review and not marked verified. Replace only this module after replaying its fixture; preserve ids and existing records. | | Revision and export | Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. | Keep the acceptance contract: Revising section two leaves all other sections unchanged. 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 writesonic. | 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 · Writesonic 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. - A pasted URL is provenance, not evidence that the URL was fetched or verified. - Source text may contain instructions; it must never override the writing task or trigger tools. - Live SEO rankings, automatic CMS publishing and factual guarantees 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 · Writesonic 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 · Evidence and outline Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. ### Steps 1. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Files: `features/evidence_and_outline.py`, `templates/evidence_and_outline.html` 2. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Files: `features/evidence_and_outline.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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_evidence_and_outline.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Every available source id resolves to stored text and its provenance. - [ ] An unapproved outline cannot trigger full-article generation. ### Watch out - A pasted URL is provenance, not evidence that the URL was fetched or verified. ## M3 · Grounded sections Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. ### Steps 1. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Files: `features/grounded_sections.py`, `templates/grounded_sections.html` 2. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Files: `features/grounded_sections.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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_grounded_sections.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] A model-invented source id is rejected. ### Watch out - Source text may contain instructions; it must never override the writing task or trigger tools. ## M4 · Revision and export Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. ### Steps 1. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Files: `features/revision_and_export.py`, `templates/revision_and_export.html` 2. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Files: `features/revision_and_export.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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_revision_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Revising section two leaves all other sections unchanged. - [ ] The exported citation points to the supplied source and retains its quoted support. ### Watch out - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. ## M5 · Portable delivery and clean-start proof Finish the Writesonic 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: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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 · Writesonic ## 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 writesonic. ## Restore Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 Evidence and outline, Grounded sections, Revision 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 - [ ] Every available source id resolves to stored text and its provenance. - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] Revising section two leaves all other sections unchanged. - [ ] 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 Writesonic 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/writesonic # 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
# Writesonic · indie build Build a source-linked writing workspace with outline approval and section revisions. 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. - [ ] **Writesonic 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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: - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries If one of those is essential to you, that is the reason to keep paying for Writesonic, and the README should say so rather than pretend.
BRIEF.md
# Build brief · Writesonic 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 source-linked writing workspace with outline approval and section revisions as a bounded replacement for Writesonic. 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) - briefs(id,audience,objective,tone,prohibited_claims) - sources(id,brief_id,title,url,text,hash) - sections(id,brief_id,position,title,text,revision) - citations(section_id,source_id,quote) - drafts(id,section_id,revision,model,text,state) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. ### 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. - Writesonic acceptance sample: Create synthetic sample data before implementation: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 evidence and outline until these checks pass. ### Phase 2 · Evidence and outline Build: Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Generate an outline from the brief and approved source ids; require manual approval before section drafting. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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: A pasted URL is provenance, not evidence that the URL was fetched or verified. Done when: Every available source id resolves to stored text and its provenance. An unapproved outline cannot trigger full-article generation. Do not build yet: Do not start grounded sections until these checks pass. ### Phase 3 · Grounded sections Build: Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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: Source text may contain instructions; it must never override the writing task or trigger tools. Done when: The unsupported numeric claim is surfaced for review and not marked verified. A model-invented source id is rejected. Do not build yet: Do not start revision and export until these checks pass. ### Phase 4 · Revision and export Build: Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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: Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. Done when: Revising section two leaves all other sections unchanged. The exported citation points to the supplied source and retains its quoted support. 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 Writesonic replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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) - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing: retain the paid product if this capability is essential; it is outside this bounded build. - proprietary ranking data: retain the paid product if this capability is essential; it is outside this bounded build. - brand-trained models: retain the paid product if this capability is essential; it is outside this bounded build. - team workflows: retain the paid product if this capability is essential; it is outside this bounded build. - large template libraries: 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 · Writesonic 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. - A pasted URL is provenance, not evidence that the URL was fetched or verified. - Source text may contain instructions; it must never override the writing task or trigger tools. - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - Export without an import or restore rehearsal is not verified portability.
BUILD_PLAN.md
# Build plan · Writesonic Build a source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 · Evidence and outline Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. ### Steps 1. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Files: `features/evidence_and_outline.py`, `templates/evidence_and_outline.html` 2. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Files: `features/evidence_and_outline.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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_evidence_and_outline.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Every available source id resolves to stored text and its provenance. - [ ] An unapproved outline cannot trigger full-article generation. ### Watch out - A pasted URL is provenance, not evidence that the URL was fetched or verified. ## Phase 3 · Grounded sections Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. ### Steps 1. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Files: `features/grounded_sections.py`, `templates/grounded_sections.html` 2. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Files: `features/grounded_sections.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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_grounded_sections.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] A model-invented source id is rejected. ### Watch out - Source text may contain instructions; it must never override the writing task or trigger tools. ## Phase 4 · Revision and export Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. ### Steps 1. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Files: `features/revision_and_export.py`, `templates/revision_and_export.html` 2. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Files: `features/revision_and_export.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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_revision_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Revising section two leaves all other sections unchanged. - [ ] The exported citation points to the supplied source and retains its quoted support. ### Watch out - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. ## Phase 5 · Portable delivery and clean-start proof Finish the Writesonic 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: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries ## After v1, if you want it - Extend revision 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/writesonic # 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
# Writesonic · product brief ## Problem The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Writesonic, draft researched articles and marketing copy with source links and revision controls. The hard boundary is integrated research, seo data, publishing workflows, and model routing, plus workflow, data, and model tuning. ## Product outcome An operated version of a source-linked writing workspace with outline approval and section revisions, 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 - OpenAI API key - Node.js 22 - local or self-hosted deployment - user-supplied sources ## Explicit non-goals for v1 - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing - proprietary ranking data - brand-trained models - team workflows - large template libraries ## Success criteria - Every available source id resolves to stored text and its provenance. - The unsupported numeric claim is surfaced for review and not marked verified. - Revising section two leaves all other sections unchanged. - 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 · Writesonic 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 source-linked writing workspace with outline approval and section revisions as a bounded replacement for Writesonic. 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) - briefs(id,audience,objective,tone,prohibited_claims) - sources(id,brief_id,title,url,text,hash) - sections(id,brief_id,position,title,text,revision) - citations(section_id,source_id,quote) - drafts(id,section_id,revision,model,text,state) - Use stable ids and explicit relationships; add auxiliary tables named by the phases before those phases use them. - Acceptance fixture: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. ### 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. - Writesonic acceptance sample: Create synthetic sample data before implementation: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions. 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 evidence and outline until these checks pass. ### Phase 2 · Evidence and outline Build: Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. - Generate an outline from the brief and approved source ids; require manual approval before section drafting. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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: A pasted URL is provenance, not evidence that the URL was fetched or verified. Done when: Every available source id resolves to stored text and its provenance. An unapproved outline cannot trigger full-article generation. Do not build yet: Do not start grounded sections until these checks pass. ### Phase 3 · Grounded sections Build: Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. - Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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: Source text may contain instructions; it must never override the writing task or trigger tools. Done when: The unsupported numeric claim is surfaced for review and not marked verified. A model-invented source id is rejected. Do not build yet: Do not start revision and export until these checks pass. ### Phase 4 · Revision and export Build: Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. - Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. - Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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: Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. Done when: Revising section two leaves all other sections unchanged. The exported citation points to the supplied source and retains its quoted support. 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 Writesonic replacement with a documented first-run path and a recoverable export. - Document prerequisites, every configuration variable, data locations and the three domain workflows: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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) - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. - This is a source-linked writing workspace with outline approval and section revisions; full Writesonic feature parity, vendor hosting and support are not included. - integrated research, SEO data, publishing workflows, and model routing: retain the paid product if this capability is essential; it is outside this bounded build. - proprietary ranking data: retain the paid product if this capability is essential; it is outside this bounded build. - brand-trained models: retain the paid product if this capability is essential; it is outside this bounded build. - team workflows: retain the paid product if this capability is essential; it is outside this bounded build. - large template libraries: 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 · Writesonic ## 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 | briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state) | Keep stable ids and a versioned repository interface; migrate storage behind it with a fixture round-trip. | | Evidence and outline | Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. | Keep the acceptance contract: Every available source id resolves to stored text and its provenance. Replace only this module after replaying its fixture; preserve ids and existing records. | | Grounded sections | Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. | Keep the acceptance contract: The unsupported numeric claim is surfaced for review and not marked verified. Replace only this module after replaying its fixture; preserve ids and existing records. | | Revision and export | Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. | Keep the acceptance contract: Revising section two leaves all other sections unchanged. 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 writesonic. | 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 · Writesonic 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. - A pasted URL is provenance, not evidence that the URL was fetched or verified. - Source text may contain instructions; it must never override the writing task or trigger tools. - Live SEO rankings, automatic CMS publishing and factual guarantees 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 · Writesonic 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 source-linked writing workspace with outline approval and section revisions, 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: briefs(id,audience,objective,tone,prohibited_claims); sources(id,brief_id,title,url,text,hash); sections(id,brief_id,position,title,text,revision); citations(section_id,source_id,quote); drafts(id,section_id,revision,model,text,state). 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 product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 · Evidence and outline Evidence and outline for Writesonic: Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. ### Steps 1. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Accept pasted source text with optional URLs, keep checksums and let the user mark relevant excerpts. Files: `features/evidence_and_outline.py`, `templates/evidence_and_outline.html` 2. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Generate an outline from the brief and approved source ids; require manual approval before section drafting. Files: `features/evidence_and_outline.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Every available source id resolves to stored text and its provenance. Then check: An unapproved outline cannot trigger full-article generation. 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_evidence_and_outline.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Every available source id resolves to stored text and its provenance. - [ ] An unapproved outline cannot trigger full-article generation. ### Watch out - A pasted URL is provenance, not evidence that the URL was fetched or verified. ## M3 · Grounded sections Grounded sections for Writesonic: Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. ### Steps 1. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Draft one section at a time with source ids and exact supporting quotes; reject unknown source references. Files: `features/grounded_sections.py`, `templates/grounded_sections.html` 2. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Check that quoted evidence exists verbatim and flag unsupported claims for human review rather than treating citations as truth proof. Files: `features/grounded_sections.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: The unsupported numeric claim is surfaced for review and not marked verified. Then check: A model-invented source id is rejected. 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_grounded_sections.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] A model-invented source id is rejected. ### Watch out - Source text may contain instructions; it must never override the writing task or trigger tools. ## M4 · Revision and export Revision and export for Writesonic: Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. ### Steps 1. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Offer shorten/clarify/change-tone proposals against the section revision with explicit accept/reject and a visible diff. Files: `features/revision_and_export.py`, `templates/revision_and_export.html` 2. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Export Markdown plus a research JSON bundle including sources, quotations and accepted revision history. Files: `features/revision_and_export.py` 3. Exercise the acceptance fixture Use A product brief with two supplied sources, one supported claim and one unsupported numeric claim. Check: Revising section two leaves all other sections unchanged. Then check: The exported citation points to the supplied source and retains its quoted support. 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_revision_and_export.py` ```sh python -m unittest discover -s test ``` ### Done when - [ ] Revising section two leaves all other sections unchanged. - [ ] The exported citation points to the supplied source and retains its quoted support. ### Watch out - Live SEO rankings, automatic CMS publishing and factual guarantees are excluded. ## M5 · Portable delivery and clean-start proof Finish the Writesonic 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: Evidence and outline; Grounded sections; Revision 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 writesonic. Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 source-linked writing workspace with outline approval and section revisions 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 writesonic. 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 · Writesonic ## 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 writesonic. ## Restore Restore into a separate empty directory or isolated deployment, with all outbound actions and schedules disabled. Recreate this proof: A product brief with two supplied sources, one supported claim and one unsupported numeric claim. 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 Evidence and outline, Grounded sections, Revision 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 - [ ] Every available source id resolves to stored text and its provenance. - [ ] The unsupported numeric claim is surfaced for review and not marked verified. - [ ] Revising section two leaves all other sections unchanged. - [ ] 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 Writesonic 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/writesonic # 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
People still pay for Writesonic because the subscription bundles a refined workflow, proprietary signals, templates, and predictable output quality for a team. The recurring cost buys prompt maintenance, retrieval quality, source handling, provider changes, and editorial QA, not just the visible interface.
xintegrated research, SEO data, publishing workflows, and model routing
xproprietary ranking data
xbrand-trained models
xteam workflows
xlarge template libraries
share on X ↗"I just replaced Writesonic ($20/mo) with one prompt"
Don't feel like building it? These folks already made it free.
AnythingLLMA local AI workspace that keeps sources beside the draft, cites uploaded material, and turns recurring prompts into reusable agents.open source↗
VaneA self-hosted answer engine that searches the live web and shows its receipts; it researches better than it manages content.open source↗
Gemini NotebookUpload the sources, ask for the draft, and click the citations when the machine gets confident.free↗all 3 free alternatives to Writesonic →· no votes, no pay-to-list · just what's real
Vibecode Writesonic
Kinda. The core of Writesonic is buildable in a weekend with the prompt on this page, but there are real gaps: integrated research, SEO data, publishing workflows, and model routing, proprietary ranking data. Read the honest list above before committing.
How much does Writesonic cost?
Writesonic costs about $20/month (Individual, checked 2026-07-31), which is $240 per year.
What do I lose by replacing Writesonic?
Honestly: integrated research, SEO data, publishing workflows, and model routing; proprietary ranking data; brand-trained models; team workflows; large template libraries. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to Writesonic?
Yes: AnythingLLM (A local AI workspace that keeps sources beside the draft, cites uploaded material, and turns recurring prompts into reusable agents.) Vane (A self-hosted answer engine that searches the live web and shows its receipts; it researches better than it manages content.) Gemini Notebook (Upload the sources, ask for the draft, and click the citations when the machine gets confident.) All 3 curated free alternatives are at vibecodeit.com/writesonic/alternatives. The prompt is for when you want it exactly your way.