DSML1: Setup Updates

.devcontainer/Dockerfile

@@ -0,0 +1,9 @@
+FROM mcr.microsoft.com/devcontainers/python:3.10
+
+COPY zscaler-bundle.pem /tmp/zscaler.pem
+RUN if [ -s /tmp/zscaler.pem ]; then \
+      cp /tmp/zscaler.pem /usr/local/share/ca-certificates/zscaler.crt && \
+      update-ca-certificates; \
+    fi && rm -f /tmp/zscaler.pem
+
+RUN find /etc/apt /usr/share/keyrings -name "*yarn*" -delete 2>/dev/null || true

.devcontainer/devcontainer-lock.json

@@ -0,0 +1,9 @@
+{
+  "features": {
+    "ghcr.io/devcontainers/features/docker-in-docker:3": {
+      "version": "3.0.1",
+      "resolved": "ghcr.io/devcontainers/features/docker-in-docker@sha256:ca2508495b01ba29eba93e8153772a2daa65eaa86471cc6863fe2a3d21933df9",
+      "integrity": "sha256:ca2508495b01ba29eba93e8153772a2daa65eaa86471cc6863fe2a3d21933df9"
+    }
+  }
+}

.devcontainer/devcontainer.json

@@ -1,7 +1,7 @@
 {
 	"name": "MLE Interview",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
-	"image": "mcr.microsoft.com/devcontainers/python:1-3.10",
+	"build": { "dockerfile": "Dockerfile" },
+	"initializeCommand": "cp ~/.ssl/zscaler-bundle.pem .devcontainer/zscaler-bundle.pem 2>/dev/null || touch .devcontainer/zscaler-bundle.pem",
 	"customizations": {
 		"vscode": {
 			"settings": {
@@ -14,7 +14,7 @@
 						"source.organizeImports.ruff": true,
 						"source.organizeImports": true
 					}
-				},
+				}
 			},
 			"extensions": [
 				"charliermarsh.ruff",
@@ -29,7 +29,10 @@
 		}
 	},
 	"features": {
-		"ghcr.io/devcontainers/features/docker-in-docker": {}
+		"ghcr.io/devcontainers/features/docker-in-docker:3": {
+			"moby": false,
+			"disableIp6tables": true
+		}
 	},
 	"postCreateCommand": "make setup"
-}
+}

.gitignore

@@ -1,3 +1,6 @@
+# Zscaler cert (machine-specific, copied by initializeCommand)
+.devcontainer/zscaler-bundle.pem
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

INTERVIEW.md

@@ -1,28 +1,153 @@
-
 ## Coding Challenge
 
-You can refer to Google or relevant documentation to guide you in addressing the issues below. 
-You are not allowed to use ChatGPT, Copilot, or any similar tools for assistance. 
+You are working on a user interest recommendation system. It consists of:
+
+- A **TensorFlow model** trained on user content interactions, served via TF Serving (Docker)
+- A **Flask API** that fetches user features, calls the model, and returns ranked interests
+- A **feature store** backed by CSV files
+
+There are **7 tasks** to complete. Tasks 1, 3, 4, 5 and 6 each have a failing test that tells you what to fix. Tasks 2 and 7 are verified by running the app. You can refer to Google or relevant documentation — no AI-assisted coding tools.
+
+---
+
+### Running the tests
+
+**Every task has its own command** — `make test-1` through `make test-7`. Run only the one for the task you are on:
+
+```
+make test-4
+```
+
+`make test` runs everything at once. Avoid it until the end: tests for tasks you have not reached yet will fail and bury the output you care about.
+
+**Read the last few lines of the output.** Each test failure ends with the assertion message that names exactly what is wrong, for example:
+
+```
+E   AssertionError: Incorrect number of interests
+```
+
+That message is the whole signal — you do not need to read the traceback above it.
+
+**The tests are correct.** Nearly every fix belongs in the source code, in `api/` or `model/` — not in `tests/`. **Task 4 is the only exception:** `top_k` has to be passed into the request as a query parameter, so that test does change.
+
+---
+
+### Terminal setup (do this before task 4)
+
+Once the model is trained and served, you'll need **two terminals** running simultaneously inside the container:
+
+| Terminal | Command | Purpose |
+|---|---|---|
+| 1 | `make serve-model` | TF Serving on port 8501 |
+| 2 | `make serve-api` | Flask API on port 5005 |
+
+Keep both running while working on tasks 4–7.
+
+---
+
+### Tasks
+
+**1. Fix model training**
+
+Run `make test-1`. The test fails.
+
+Find and fix the bug in the model code, then verify:
+```
+make test-1
+```
+
+Once passing, train the model and start the model server (leave it running):
+```
+make train
+make serve-model
+```
+
+---
+
+**2. Fix the API startup**
+
+Run `make serve-api`. The Flask application fails to start.
+
+Find and fix the bug, then start the server again and leave it running in its terminal:
+```
+make serve-api
+```
+
+From a second terminal, verify:
+```
+make test-2
+```
+
+---
+
+**3. Fix the probability scores**
+
+The model's serving function returns raw logit scores, not probabilities. These values are not bounded between 0 and 1 and cannot be meaningfully compared or filtered.
+
+Find where the issue originates and fix it so that the scores returned represent proper probability values. There are two valid approaches — both are acceptable.
+
+Verify:
+```
+make test-3
+```
+
+This test exercises the model in memory. For the **served** model to return probabilities too, re-run `make train` and restart `make serve-model`.
+
+---
+
+**4. Fix the interests count**
+
+With both servers running, run `make test-4`. It fails with:
+```
+AssertionError: Incorrect number of interests
+```
+
+The test asks for 15 interests but never tells the API how many it wants. Make the request send `top_k`, and make sure the API honours it. Verify:
+```
+make test-4
+```
+
+This is the one task where you edit a test.
+
+---
+
+**5. Fix response time**
+
+With both servers running, run `make test-5`. It fails with:
+```
+AssertionError: Request greater than 1 second
+```
+
+Find the performance bottleneck and fix it. Verify:
+```
+make test-5
+```
+
+---
+
+**6. Add probability to the response**
+
+With both servers running, run `make test-6`. It fails with:
+```
+AssertionError: Interest object missing 'probability': ...
+```
 
-1. **Model Training Error Resolution:**
-   - Begin by executing `make test` to identify any issues during model training.
-   - After passing the `TestModel::test_model_build` test, use `make train` followed by `make serve-model` to train and serve the model, preparing it for upcoming steps.
+Update the API response so each interest includes a `probability` field. Verify:
+```
+make test-6
+```
 
-2. **API Startup Issue Fix:**
-   - Resolve the Flask API startup issue with `make serve-api`.
-   - Run `make serve-api` to start a development Flask server, then open a new terminal window without shutting down the server.
+---
 
-3. **Data Return and Interests Length Correction:**
-   - Execute `make test` and resolve the `TestInterestsAPI::test_basic_response - AssertionError: Incorrect number of interests` test.
-   - Ensure the return data structure and interests array length meet the specifications, adjusting the API as necessary.
+**7. Add probability threshold filtering**
 
-4. **Response Time Optimization:**
-   - Run `make test` and fix the `TestInterestsAPI::test_basic_response - AssertionError: Request greater than 1 second` test.
-   - Enhance the API to achieve a response time of one second or less.
+Implement a feature that lets API clients filter results by a minimum probability score. For example:
 
-5. **Probability Field Inclusion:**
-   - Perform `make test` and correct the `TestInterestsAPI::test_with_probability` test.
-   - Update the API response to incorporate a 'probability' field.
+```
+GET /interests/<user_handle>?min_probability=0.5
+```
 
-6. **Probability Score Filtering Implementation:**
-   - Create a feature allowing API clients to filter results by probability score, enabling users to specify a probability threshold for more targeted results.
+Should return only interests with probability ≥ 0.5. There is no automated test for this task — check the response yourself:
+```
+make test-7
+```

Makefile

@@ -1,14 +1,66 @@
+PYTEST = TF_CPP_MIN_LOG_LEVEL=3 pytest
+HANDLE ?= e337a675-46f5-437e-aa72-5d43643b5461
+
+.PHONY: help setup serve-api serve-model ping-model train test \
+	test-1 test-2 test-3 test-4 test-5 test-6 test-7
+
+help:
+	@printf 'Setup and servers\n'
+	@printf '  make setup        Install dependencies\n'
+	@printf '  make train        Train the model and export it to serving/\n'
+	@printf '  make serve-model  Start TF Serving on port 8501\n'
+	@printf '  make serve-api    Start the Flask API on port 5005\n'
+	@printf '  make ping-model   Check that TF Serving has loaded the model\n'
+	@printf '\nInterview tasks (run only the target for the task you are on)\n'
+	@printf '  make test-1       Task 1: model build\n'
+	@printf '  make test-2       Task 2: API starts up\n'
+	@printf '  make test-3       Task 3: probability scores\n'
+	@printf '  make test-4       Task 4: interests count\n'
+	@printf '  make test-5       Task 5: response time\n'
+	@printf '  make test-6       Task 6: probability in the response\n'
+	@printf '  make test-7       Task 7: min_probability filtering\n'
+	@printf '  make test         Every test at once (expect noise until all tasks are done)\n'
+
 setup:
 	pip install -r requirements.txt
 
 serve-api:
 	python -m flask --app api/app run --debug --port 5005 --host 0.0.0.0
-	
+
 serve-model:
 	docker compose up tf-serving
 
+ping-model:
+	curl -s http://localhost:8501/v1/models/interests-model | python3 -m json.tool
+
 train:
 	TF_CPP_MIN_LOG_LEVEL=3 python -m model.main
 
 test:
-	TF_CPP_MIN_LOG_LEVEL=3 pytest ./tests -p no:warnings
+	$(PYTEST)
+
+test-1:
+	$(PYTEST) tests/test_model.py::TestModel::test_model_build
+
+# No automated test — the API only starts once the bug is fixed.
+test-2:
+	@curl -fs http://localhost:5005/ \
+		&& printf '\nPASS: the API is up\n' \
+		|| printf 'FAIL: the API is not reachable on port 5005 (see task 2)\n'
+
+test-3:
+	$(PYTEST) tests/test_model.py::TestModel::test_probability_scores
+
+test-4:
+	$(PYTEST) tests/test_app.py::TestInterestsAPI::test_interests_count
+
+test-5:
+	$(PYTEST) tests/test_app.py::TestInterestsAPI::test_response_time
+
+test-6:
+	$(PYTEST) tests/test_app.py::TestInterestsAPI::test_with_probability_threshold
+
+# No automated test — read the response and check every probability is >= 0.5.
+test-7:
+	@curl -fsS "http://localhost:5005/interests/$(HANDLE)?min_probability=0.5" \
+		| python3 -m json.tool