Release notes generator script

.github/workflows/release_notes.yml

@@ -0,0 +1,38 @@
+name: Deploy Release Notes Function
+
+on: workflow_dispatch
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Google Cloud Auth
+        id: auth
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: ${{ secrets.GCP_SA_CREDENTIALS }}
+
+      - name: Set up gcloud
+        uses: google-github-actions/setup-gcloud@v2
+
+      - name: Deploy to Cloud Functions
+        working-directory: functions/release_notes
+        run: |
+          gcloud functions deploy release-notes \
+            --gen2 \
+            --trigger-http \
+            --allow-unauthenticated \
+            --region=us-central1 \
+            --timeout=240 \
+            --memory=2Gi \
+            --runtime=python311 \
+            --entry-point=handle_release_notes \
+            --service-account=review-helper@moz-bugbug.iam.gserviceaccount.com \
+            --set-secrets=OPENAI_API_KEY=openai-api-key:latest

bugbug/generative_model_tool.py

@@ -147,6 +147,28 @@ def create_llm_from_args(args):
     return globals()[f"create_{args.llm}_llm"](**llm_creation_args)
 
 
+def create_llm_from_request(llm_name, request_args):
+    if llm_name not in AVAILABLE_LLMS:
+        raise NotImplementedError(f"LLM '{llm_name}' is not supported")
+
+    expected_args = AVAILABLE_LLMS[llm_name]
+    llm_creation_args = {}
+
+    for param_name in expected_args:
+        value = request_args.get(param_name)
+        if value is not None:
+            param = expected_args[param_name]
+            type_fn = (
+                param.annotation if param.annotation != inspect.Parameter.empty else str
+            )
+            try:
+                llm_creation_args[param_name] = type_fn(value)
+            except Exception:
+                llm_creation_args[param_name] = value
+
+    return globals()[f"create_{llm_name}_llm"](**llm_creation_args)
+
+
 def get_tokenizer(model_name):
     import tiktoken
 

bugbug/tools/release_notes.py

@@ -0,0 +1,250 @@
+import logging
+import re
+from itertools import batched
+from typing import Generator, Optional
+
+import requests
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+
+from bugbug import bugzilla, db
+
+KEYWORDS_TO_REMOVE = [
+    "Backed out",
+    "a=testonly",
+    "DONTBUILD",
+    "add tests",
+    "disable test",
+    "back out",
+    "backout",
+    "add test",
+    "added test",
+    "ignore-this-changeset",
+    "CLOSED TREE",
+    "nightly",
+]
+
+PRODUCT_OR_COMPONENT_TO_IGNORE = [
+    "Firefox Build System::Task Configuration",
+    "Developer Infrastructure::",
+]
+
+
+def get_previous_version(current_version: str) -> str:
+    match = re.search(r"(\d+)", current_version)
+    if not match:
+        raise ValueError("No number found in the version string")
+
+    number = match.group(0)
+    decremented_number = str(int(number) - 1)
+    return (
+        current_version[: match.start()]
+        + decremented_number
+        + current_version[match.end() :]
+    )
+
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+class ReleaseNotesCommitsSelector:
+    def __init__(self, chunk_size: int, llm: LLMChain):
+        self.chunk_size = chunk_size
+        self.bug_id_to_component = {}
+        db.download(bugzilla.BUGS_DB)
+        for bug in bugzilla.get_bugs():
+            self.bug_id_to_component[
+                bug["id"]
+            ] = f"{bug['product']}::{bug['component']}"
+        self.llm = llm
+        self.summarization_prompt = PromptTemplate(
+            input_variables=["input_text"],
+            template="""You are an expert in writing Firefox release notes. Your task is to analyze a list of commits and identify important user-facing changes. Follow these steps:
+
+1. Must Include Only Meaningful Changes:
+   - Only keep commits that significantly impact users and are strictly user-facing, such as:
+     - New features
+     - UI changes
+     - Major performance improvements
+     - Security patches (if user-facing)
+     - Web platform changes that affect how websites behave
+   - DO NOT include:
+     - Small bug fixes unless critical
+     - Internal code refactoring
+     - Test changes or documentation updates
+     - Developer tooling or CI/CD pipeline changes
+Again, only include changes that are STRICTLY USER-FACING.
+
+2. Output Format:
+   - Use simple, non-technical language suitable for release notes.
+   - Use the following strict format for each relevant commit, in CSV FORMAT:
+[Type of Change],Description of the change,Bug XXXX,Reason why the change is impactful for end users
+   - Possible types of change: [Feature], [Fix], [Performance], [Security], [UI], [DevTools], [Web Platform], etc.
+
+3. Be Aggressive in Filtering:
+    - If you're unsure whether a commit impacts end users, EXCLUDE it.
+    - Do not list developer-focused changes.
+
+4. Select Only the Top 10 Commits:
+    - If there are more than 10 relevant commits, choose the most impactful ones.
+
+5. Input:
+   Here is the chunk of commit logs you need to focus on:
+   {input_text}
+
+6. Output Requirements:
+   - Output must be raw CSV text—no formatting, no extra text.
+   - Do not wrap the output in triple backticks (` ``` `) or use markdown formatting.
+   - Do not include the words "CSV" or any headers—just the data.
+""",
+        )
+
+        self.summarization_chain = LLMChain(
+            llm=self.llm,
+            prompt=self.summarization_prompt,
+        )
+
+        self.cleanup_prompt = PromptTemplate(
+            input_variables=["combined_list"],
+            template="""Review the following list of release notes and remove anything that is not worthy of official release notes. Keep only changes that are meaningful, impactful, and directly relevant to end users, such as:
+- New features that users will notice and interact with.
+- Significant fixes that resolve major user-facing issues.
+- Performance improvements that make a clear difference in speed or responsiveness.
+- Accessibility enhancements that improve usability for a broad set of users.
+- Critical security updates that protect users from vulnerabilities.
+
+Strict Filtering Criteria - REMOVE the following:
+- Overly technical web platform changes (e.g., spec compliance tweaks, behind-the-scenes API adjustments).
+- Developer-facing features that have no direct user impact.
+- Minor UI refinements (e.g., button width adjustments, small animation tweaks).
+- Bug fixes that don’t impact most users.
+- Obscure web compatibility changes that apply only to edge-case websites.
+- Duplicate entries or similar changes that were already listed.
+
+Here is the list to filter:
+{combined_list}
+
+Instructions:
+- KEEP THE SAME FORMAT (do not change the structure of entries that remain).
+- REMOVE UNWORTHY ENTRIES ENTIRELY (do not rewrite them—just delete).
+- DO NOT ADD ANY TEXT BEFORE OR AFTER THE LIST.
+- The output must be only the cleaned-up list, formatted exactly the same way.
+""",
+        )
+
+        self.cleanup_chain = LLMChain(
+            llm=self.llm,
+            prompt=self.cleanup_prompt,
+        )
+
+    def batch_commit_logs(self, commit_log: str) -> list[str]:
+        return [
+            "\n".join(batch)
+            for batch in batched(commit_log.strip().split("\n"), self.chunk_size)
+        ]
+
+    def generate_commit_shortlist(self, commit_log_list: list[str]) -> list[str]:
+        commit_log_list_combined = "\n".join(commit_log_list)
+        chunks = self.batch_commit_logs(commit_log_list_combined)
+        return [
+            self.summarization_chain.run({"input_text": chunk}).strip()
+            for chunk in chunks
+        ]
+
+    def filter_irrelevant_commits(
+        self, commit_log_list: list[tuple[str, str, str]]
+    ) -> Generator[str, None, None]:
+        ignore_revs_url = "https://hg.mozilla.org/mozilla-central/raw-file/tip/.hg-annotate-ignore-revs"
+        response = requests.get(ignore_revs_url)
+        response.raise_for_status()
+        raw_commits_to_ignore = response.text.strip().splitlines()
+        hashes_to_ignore = {
+            line.split(" ", 1)[0]
+            for line in raw_commits_to_ignore
+            if re.search(r"Bug \d+", line, re.IGNORECASE)
+        }
+
+        for desc, author, node in commit_log_list:
+            bug_match = re.search(r"(Bug (\d+).*)", desc, re.IGNORECASE)
+            if (
+                not any(
+                    keyword.lower() in desc.lower() for keyword in KEYWORDS_TO_REMOVE
+                )
+                and bug_match
+                and re.search(r"\br=[^\s,]+", desc)
+                and author
+                != "Mozilla Releng Treescript <[email protected]>"
+                and node not in hashes_to_ignore
+            ):
+                bug_id = int(bug_match.group(2))
+
+                bug_component = self.bug_id_to_component.get(bug_id)
+                if bug_component and any(
+                    to_ignore in bug_component
+                    for to_ignore in PRODUCT_OR_COMPONENT_TO_IGNORE
+                ):
+                    continue
+                yield bug_match.group(1)
+
+    def get_commit_logs(self) -> Optional[list[tuple[str, str, str]]]:
+        url = f"https://hg.mozilla.org/releases/mozilla-release/json-pushes?fromchange={self.version1}&tochange={self.version2}&full=1"
+        response = requests.get(url)
+        response.raise_for_status()
+
+        data = response.json()
+        commit_log_list = [
+            (
+                changeset["desc"].strip(),
+                changeset.get("author", "").strip(),
+                changeset.get("node", "").strip(),
+            )
+            for push_data in data.values()
+            for changeset in push_data["changesets"]
+            if "desc" in changeset and changeset["desc"].strip()
+        ]
+
+        return commit_log_list if commit_log_list else None
+
+    def remove_duplicate_bugs(self, csv_text: str) -> str:
+        seen = set()
+        unique_lines = []
+        for line in csv_text.strip().splitlines():
+            parts = line.split(",", 3)
+            if len(parts) < 3:
+                continue
+            bug_id = parts[2].strip()
+            if bug_id not in seen:
+                seen.add(bug_id)
+                unique_lines.append(line)
+        return "\n".join(unique_lines)
+
+    def get_final_release_notes_commits(self, version: str) -> Optional[list[str]]:
+        self.version2 = version
+        self.version1 = get_previous_version(version)
+
+        logger.info(f"Generating commit shortlist for: {self.version2}")
+        commit_log_list = self.get_commit_logs()
+
+        if not commit_log_list:
+            return None
+
+        logger.info("Filtering irrelevant commits...")
+        filtered_commits = list(self.filter_irrelevant_commits(commit_log_list))
+
+        if not filtered_commits:
+            return None
+
+        logger.info("Generating commit shortlist...")
+        commit_shortlist = self.generate_commit_shortlist(filtered_commits)
+
+        if not commit_shortlist:
+            return None
+
+        logger.info("Refining commit shortlist...")
+        combined_list = "\n".join(commit_shortlist)
+        cleaned = self.cleanup_chain.run({"combined_list": combined_list}).strip()
+
+        logger.info("Removing duplicates...")
+        deduped = self.remove_duplicate_bugs(cleaned)
+        return deduped.splitlines()

functions/release_notes/main.py

@@ -0,0 +1,49 @@
+import logging
+import os
+
+import flask
+import functions_framework
+
+from bugbug import generative_model_tool
+from bugbug.tools.release_notes import ReleaseNotesCommitsSelector
+from bugbug.utils import get_secret
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+os.environ["OPENAI_API_KEY"] = get_secret("OPENAI_API_KEY")
+
+tool: ReleaseNotesCommitsSelector | None = None
+
+DEFAULT_LLM_NAME = "openai"
+DEFAULT_CHUNK_SIZE = 1000
+
+
+@functions_framework.http
+def handle_release_notes(request: flask.Request):
+    global tool
+
+    if request.method != "GET":
+        return "Only GET requests are allowed", 405
+
+    version = request.args.get("version")
+    if not version:
+        return "Missing 'version' query parameter", 400
+
+    if (
+        tool is None
+        or tool.llm_name != DEFAULT_LLM_NAME
+        or tool.chunk_size != DEFAULT_CHUNK_SIZE
+    ):
+        logger.info("Initializing new ReleaseNotesCommitsSelector...")
+        llm = generative_model_tool.create_llm_from_request(DEFAULT_LLM_NAME, {})
+        tool = ReleaseNotesCommitsSelector(chunk_size=DEFAULT_CHUNK_SIZE, llm=llm)
+        tool.llm_name = DEFAULT_LLM_NAME
+        tool.chunk_size = DEFAULT_CHUNK_SIZE
+
+    notes = tool.get_final_release_notes_commits(version=version)
+
+    if not notes:
+        return {"commits": []}, 200, {"Content-Type": "application/json"}
+
+    return {"commits": notes}, 200, {"Content-Type": "application/json"}

functions/release_notes/requirements.txt

@@ -0,0 +1,6 @@
+bugbug
+Flask==2.2.5
+functions-framework==3.5.0
+langchain
+openai
+requests