refactor: rename the application package to docsgpt

The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.

Kept for one release:
- A top-level application package whose meta-path finder resolves
  application.x.y to the already-imported docsgpt.x.y object, so old imports
  and entry points (celery -A application.app.celery,
  uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
  docsgpt.* task on start-up, so messages queued by the previous release still
  run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
  the previous release wrote are left unread instead of firing twice.

The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.

docsgpt/api/answer/services/compression/threshold_checker.py

@@ -0,0 +1,111 @@
+"""Compression threshold checking logic."""
+
+import logging
+from typing import Any, Dict
+
+from docsgpt.core.model_utils import get_token_limit
+from docsgpt.core.settings import settings
+from docsgpt.api.answer.services.compression.token_counter import TokenCounter
+
+logger = logging.getLogger(__name__)
+
+
+class CompressionThresholdChecker:
+    """Determines if compression is needed based on token thresholds."""
+
+    def __init__(self, threshold_percentage: float = None):
+        """
+        Initialize threshold checker.
+
+        Args:
+            threshold_percentage: Percentage of context to use as threshold
+                                 (defaults to settings.COMPRESSION_THRESHOLD_PERCENTAGE)
+        """
+        self.threshold_percentage = (
+            threshold_percentage or settings.COMPRESSION_THRESHOLD_PERCENTAGE
+        )
+
+    def should_compress(
+        self,
+        conversation: Dict[str, Any],
+        model_id: str,
+        current_query_tokens: int = 500,
+        user_id: str | None = None,
+    ) -> bool:
+        """
+        Determine if compression is needed.
+
+        Args:
+            conversation: Full conversation document
+            model_id: Target model for this request
+            current_query_tokens: Estimated tokens for current query
+            user_id: Owner — needed so per-user BYOM custom-model UUIDs
+                resolve when looking up the context window.
+
+        Returns:
+            True if tokens >= threshold% of context window
+        """
+        try:
+            # What the next turn will replay: summary + queries after the
+            # last compression point, or the raw history when never compressed.
+            total_tokens = TokenCounter.count_effective_conversation_tokens(conversation)
+            total_tokens += current_query_tokens
+
+            # Get context window limit for model
+            context_limit = get_token_limit(model_id, user_id=user_id)
+
+            # Calculate threshold
+            threshold = int(context_limit * self.threshold_percentage)
+
+            compression_needed = total_tokens >= threshold
+            percentage_used = (total_tokens / context_limit) * 100
+
+            if compression_needed:
+                logger.warning(
+                    f"COMPRESSION TRIGGERED: {total_tokens} tokens / {context_limit} limit "
+                    f"({percentage_used:.1f}% used, threshold: {self.threshold_percentage * 100:.0f}%)"
+                )
+            else:
+                logger.info(
+                    f"Compression check: {total_tokens}/{context_limit} tokens "
+                    f"({percentage_used:.1f}% used, threshold: {self.threshold_percentage * 100:.0f}%) - No compression needed"
+                )
+
+            return compression_needed
+
+        except Exception as e:
+            logger.error(f"Error checking compression need: {str(e)}", exc_info=True)
+            return False
+
+    def check_message_tokens(
+        self, messages: list, model_id: str, user_id: str | None = None
+    ) -> bool:
+        """
+        Check if message list exceeds threshold.
+
+        Args:
+            messages: List of message dicts
+            model_id: Target model
+            user_id: Owner — needed so per-user BYOM custom-model UUIDs
+                resolve when looking up the context window.
+
+        Returns:
+            True if at or above threshold
+        """
+        try:
+            current_tokens = TokenCounter.count_message_tokens(messages)
+            context_limit = get_token_limit(model_id, user_id=user_id)
+            threshold = int(context_limit * self.threshold_percentage)
+
+            if current_tokens >= threshold:
+                logger.warning(
+                    f"Message context limit approaching: {current_tokens}/{context_limit} tokens "
+                    f"({(current_tokens/context_limit)*100:.1f}%)"
+                )
+                return True
+
+            return False
+
+        except Exception as e:
+            logger.error(f"Error checking message tokens: {str(e)}", exc_info=True)
+            return False