Flesh out CLAUDE.md with architecture, design notes, and dev reference

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

CLAUDE.md

@@ -0,0 +1,166 @@
+# CLAUDE.md — BLIGHT: CUE
+
+## Instructions for Claude
+
+- **Every commit**: Update the Changelog section below with a summary of what changed and bump the version number if appropriate.
+- **Every commit**: If the changes affect anything documented in README.md (trigger syntax, failure behavior, setup, project structure, AI provider info, etc.), update README.md in the same commit.
+
+---
+
+## Version
+
+**v1.2.0**
+
+---
+
+## Project Overview
+
+BLIGHT: CUE is a webhook listener that monitors Gitea repositories for markdown files containing `BLIGHT:` trigger lines. When a push arrives, it fetches the changed files, sends them to Google Gemini with the embedded instruction, replaces the trigger with the AI's response, and commits the result back — fully automated, no manual steps.
+
+It is one module in a larger ecosystem called **BLIGHT**, where independent modules communicate through Gitea repositories as a shared data layer.
+
+**Deployed on**: homelab at `/home/artanis/Documents/BLIGHT_CUE` as `blight-cue.service`
+**Gitea instance**: `https://gitea.bunny-wyvern.ts.net`
+**Default port**: `5010`
+
+---
+
+## Architecture
+
+```
+app.py              Flask webhook server — entry point, signature verification,
+                    background thread dispatch
+processor.py        Trigger scanning, inline vs document-scope processing,
+                    retry logic, AI response sanitization
+gitea_client.py     Gitea REST API wrapper — get_file / update_file
+config.py           Loads .env into module-level constants
+ai/
+  base.py           AIProvider ABC — complete() and complete_document()
+  gemini.py         Gemini 2.5 Flash-Lite implementation, two model instances
+                    (one system prompt per trigger type)
+```
+
+### Request flow
+
+1. Gitea POST → `/webhook`
+2. HMAC-SHA256 signature verified against `WEBHOOK_SECRET`
+3. Push payload parsed — owner, repo, branch, changed file paths extracted
+4. Background thread spawned; 200 returned immediately to Gitea
+5. For each `.md` file:
+   - Fetch content + SHA via Gitea API (`?ref=<branch>`)
+   - `processor.process_document()` — inline triggers first, doc-scope second
+   - If changed: commit back via Gitea API (same branch, SHA required)
+
+### Trigger types
+
+| Syntax | Scope | AI output replaces |
+|---|---|---|
+| `BLIGHT: <instruction>` | Inline | The trigger line only |
+| `BLIGHT:: <instruction>` | Document | The entire file content |
+
+Both are case-insensitive. Multiple triggers in one file: inline ones processed first in document order, then doc-scope ones sequentially (each sees the previous result).
+
+### Loop prevention
+
+All AI responses are passed through `_sanitize()` in `processor.py` before being written to the document. This replaces `BLIGHT:` with `BLIGHT&#58;`, preventing the service's own commits from triggering another processing cycle.
+
+---
+
+## Key Design Decisions
+
+- **Stateless**: no database, no persistent state between webhooks. Everything is derived from the Gitea API on demand.
+- **Background threads**: webhook returns 200 immediately; processing happens async. Gitea will not retry on timeout.
+- **SHA-based updates**: Gitea requires the current file SHA to update — prevents race conditions if two pushes arrive close together.
+- **Pluggable AI**: `AIProvider` ABC makes swapping backends a one-file change. Two methods required: `complete()` for inline, `complete_document()` for doc-scope.
+- **Gemini model**: `gemini-2.5-flash-lite` — chosen for cost-effectiveness. Two separate model instances are used, each with a different system prompt tuned for inline vs whole-document output.
+- **Self-update**: `_self_update()` in `app.py` runs `git pull --ff-only` on startup. Only executes under `__main__` (i.e. `python app.py`), not under a WSGI server.
+
+---
+
+## Environment Variables
+
+Loaded from `.env` via `python-dotenv`. See `.env.example`.
+
+| Variable | Required | Default | Notes |
+|---|---|---|---|
+| `GITEA_URL` | Yes | — | No trailing slash |
+| `GITEA_TOKEN` | Yes | — | Needs repo read/write |
+| `GEMINI_API_KEY` | Yes | — | From Google AI Studio |
+| `WEBHOOK_SECRET` | Yes | — | Must match Gitea webhook config |
+| `WEBHOOK_PORT` | No | `5010` | Port Flask binds to |
+
+---
+
+## Running Locally
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+cp .env.example .env   # fill in your values
+python app.py
+```
+
+---
+
+## Dependencies
+
+| Package | Purpose |
+|---|---|
+| `flask>=3.0.0` | Webhook HTTP server |
+| `python-dotenv>=1.0.0` | `.env` loading |
+| `requests>=2.31.0` | Gitea REST API calls |
+| `google-generativeai>=0.8.0` | Gemini SDK |
+
+---
+
+## Things to Keep in Mind
+
+- **No tests exist yet.** Be careful with changes to `processor.py` — the trigger regex and two-pass processing logic are easy to break subtly. When in doubt, trace through a concrete example mentally before changing.
+- **`_sanitize()` must stay on all AI return paths.** If new call sites are added to `_call_with_retry` or new retry functions are introduced, make sure sanitization is applied before returning.
+- **`gitea_client.update_file` requires `branch`** — never call it without a valid branch string or the write will go to the default branch silently.
+- **The `BLIGHT:` commit message prefix is intentional** — it makes BLIGHT: CUE's commits easy to identify in Gitea's history. Don't change it to something that wouldn't match `BLIGHT:` (the sanitizer would catch it but it's still confusing).
+- **`INLINE_PATTERN` uses a negative lookahead `(?!:)`** to exclude `BLIGHT::` from matching as an inline trigger. If you touch the regex, verify this still holds.
+- **Background threads are daemon threads** — they will be killed if the main process exits. Long-running AI calls on shutdown will be lost.
+
+---
+
+## Adding a New AI Provider
+
+1. Create `ai/<name>.py` and subclass `AIProvider` from `ai/base.py`.
+2. Implement both `complete(document, instruction)` and `complete_document(document, instruction)`.
+3. In `processor.py`, replace `GeminiProvider()` with your new class.
+4. Export it from `ai/__init__.py`.
+
+---
+
+## Changelog
+
+### v1.2.0
+- Fixed loop re-processing: AI responses are sanitized by replacing `BLIGHT:` with `BLIGHT&#58;` before being written to the document, preventing the service's own commits from triggering another processing cycle.
+- Branch awareness: branch is now extracted from `refs/heads/<branch>` in the push payload and passed to all Gitea read/write calls, so pushes to non-default branches are handled correctly.
+- Commit messages now include the file path (e.g. `BLIGHT: process triggers in notes/todo.md`).
+
+### v1.1.0
+- Added `BLIGHT::` (double colon) document-scope trigger syntax. Unlike `BLIGHT:` which replaces only the trigger line, `BLIGHT::` replaces the entire file content with the AI's rewritten document.
+- Multiple `BLIGHT::` triggers in one file are processed sequentially, each operating on the result of the previous.
+- Inline `BLIGHT:` triggers are always processed before `BLIGHT::` triggers.
+- Both trigger types are now case-insensitive (`blight:`, `BLIGHT:`, `Blight::`, etc. all match).
+- Failure comments updated to two-line format:
+  ```
+  <!-- BLIGHT_FAILED: <instruction> -->
+  <!-- BLIGHT_ERROR: <error message> -->
+  ```
+- Added `complete_document()` to `AIProvider` ABC and `GeminiProvider`, with a dedicated system prompt instructing the model to return the full rewritten document.
+
+### v1.0.0 — Initial release
+- Flask webhook server listening for Gitea push events.
+- HMAC-SHA256 signature verification on all incoming webhooks.
+- Scans changed `.md` files for `BLIGHT: <instruction>` trigger lines.
+- Sends full document + instruction to Google Gemini 2.5 Flash-Lite.
+- Replaces trigger line with AI response in-place and commits back to Gitea.
+- Retry logic: 3 attempts with exponential backoff (1s, 2s, 4s).
+- Processes webhooks in background threads to return 200 immediately.
+- Deduplicates file paths across multiple commits in a single push.
+- Self-updates on startup via `git pull --ff-only`.
+- Pluggable `AIProvider` ABC for swapping AI backends.

README.md

@@ -2,7 +2,7 @@
 
 A module in the **BLIGHT** ecosystem.
 
-BLIGHT: CUE monitors Gitea repositories containing markdown files. When a push is received, it scans changed files for `BLIGHT:` trigger lines, sends the surrounding document to an AI model along with the instruction, and writes the result back to the file in-place — fully automated.
+BLIGHT: CUE monitors Gitea repositories containing markdown files. When a push is received, it scans changed files for `BLIGHT:` trigger lines, sends the document to an AI model along with the instruction, and writes the result back to the file in-place — fully automated.
 
 ---
 
@@ -10,16 +10,25 @@ BLIGHT: CUE monitors Gitea repositories containing markdown files. When a push i
 
 1. You write a `BLIGHT:` trigger anywhere in a markdown file and push it to Gitea.
 2. Gitea sends a webhook POST to this server.
-3. The server fetches the file, finds all `BLIGHT:` triggers, and processes them one by one.
-4. Each trigger is replaced with the AI's response at the exact position of the trigger line.
-5. The updated file is committed back to the repo automatically.
+3. The server fetches the file, finds all `BLIGHT:` triggers, and processes them.
+4. Each trigger is replaced with the AI's response, then the updated file is committed back automatically.
 
 ### Trigger Syntax
 
+Triggers are case-insensitive — `BLIGHT:`, `blight:`, `Blight::`, etc. all work.
+
+**Inline trigger** — replaces only the trigger line with the AI's response:
+
 ```
 BLIGHT: <your instruction here>
 ```
 
+**Document-scope trigger** — replaces the entire file with the AI's rewritten version:
+
+```
+BLIGHT:: <your instruction here>
+```
+
 Examples:
 
 ```markdown
@@ -31,22 +40,30 @@ BLIGHT: Explain the key differences between は and が based on the paragraph a
 ```
 
 ```markdown
-BLIGHT: Spell check this entire document and list any errors found.
+BLIGHT: Write a conclusion paragraph for this document.
 ```
 
 ```markdown
-BLIGHT: Write a conclusion paragraph for this document.
+BLIGHT:: Spellcheck and lightly reformat this entire document.
 ```
 
+### Processing Order
+
+When a file contains multiple triggers:
+
+1. All inline (`BLIGHT:`) triggers are processed first, in document order.
+2. All document-scope (`BLIGHT::`) triggers are processed next, in document order — each one operates on the result of the previous.
+
 ### Failure Behavior
 
 If the AI call fails after 3 attempts, the trigger is replaced with:
 
 ```html
 <!-- BLIGHT_FAILED: your original instruction -->
+<!-- BLIGHT_ERROR: <error message> -->
 ```
 
-You can re-trigger processing by editing the file to restore the original `BLIGHT:` line and pushing again.
+You can re-trigger processing by editing the file to restore the original trigger line and pushing again.
 
 ---
 
@@ -224,12 +241,17 @@ from abc import ABC, abstractmethod
 
 class AIProvider(ABC):
     def complete(self, document: str, instruction: str) -> str:
+        """Return text to insert in place of an inline BLIGHT: trigger."""
+        ...
+
+    def complete_document(self, document: str, instruction: str) -> str:
+        """Return the full rewritten document for a BLIGHT:: trigger."""
         ...
 ```
 
 To add a new provider (e.g. OpenRouter):
 
-1. Create `ai/openrouter.py` and implement `AIProvider`.
+1. Create `ai/openrouter.py` and implement both methods of `AIProvider`.
 2. In `processor.py`, replace `GeminiProvider()` with your new class.
 
 ---