jobagent 1.0.5__tar.gz

jobagent-1.0.5/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Yaswanth Asapu
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

jobagent-1.0.5/MANIFEST.in

@@ -0,0 +1,25 @@
+include README.md
+include LICENSE
+include requirements.txt
+include pyproject.toml
+include config/candidate_profile.template.json
+
+# Exclude sensitive, local-only, and private data
+exclude .env
+exclude .env.*
+exclude applications.db
+exclude sharepoint_screen.png
+exclude AmazonCartMobileApp
+exclude jobagent.bat
+exclude jobagent.ps1
+exclude config/candidate_profile.json
+exclude config/agent_memory.json
+exclude config/resume.pdf
+
+recursive-exclude .browser_context *
+recursive-exclude screenshots *
+recursive-exclude tests *
+recursive-exclude .pytest_cache *
+recursive-exclude desktopapplication *
+recursive-exclude * __pycache__
+recursive-exclude * *.py[co]

jobagent-1.0.5/PKG-INFO

@@ -0,0 +1,198 @@
+Metadata-Version: 2.4
+Name: jobagent
+Version: 1.0.5
+Summary: Autonomous Multi-Platform AI Job Application Agent for LinkedIn and Naukri
+Author-email: Yaswanth Asapu <yaswanth901@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/yaswanth901/jobagent
+Keywords: job-application,job-agent,linkedin,naukri,automation,playwright,ai,gemini
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Office/Business
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: playwright>=1.40.0
+Requires-Dist: pydantic>=2.5.0
+Requires-Dist: pydantic-settings>=2.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: SQLAlchemy>=2.0.0
+Requires-Dist: aiosqlite>=0.19.0
+Requires-Dist: httpx>=0.25.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: reportlab>=4.0.0
+Requires-Dist: pypdf>=3.0.0
+Requires-Dist: google-genai>=0.1.0
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
+Provides-Extra: all
+Requires-Dist: google-genai>=0.1.0; extra == "all"
+Requires-Dist: openai>=1.0.0; extra == "all"
+Dynamic: license-file
+
+# Hybrid Browser AI Agent for LinkedIn Easy Apply
+
+A Python-based browser automation AI agent built with **Playwright**, a **Finite State Machine (FSM)**, **Page Object Model (POM)**, and an **LLM-driven Semantic Matching & Form Interpretation Engine** with a strict **Human-in-the-Loop (HITL)** approval gate.
+
+---
+
+## Architecture Overview
+
+```
+d:\Gravity\
+├── config/
+│   ├── candidate_profile.json  # Single source of truth for candidate data
+│   └── settings.py             # Pydantic BaseSettings (.env loader)
+├── models/
+│   ├── profile.py              # Pydantic models for Candidate Profile
+│   ├── job.py                  # JobCardSummary and JobDetails schemas
+│   ├── evaluation.py           # MatchBreakdown and JobEvaluationResult schemas
+│   ├── form.py                 # FormField, FormStep, ApplicationSummary schemas
+│   └── application.py          # Database ApplicationRecord and Status
+├── services/
+│   ├── profile_loader.py       # Profile reader & dynamic field calculation
+│   ├── db_service.py           # SQLite/PostgreSQL persistence & deduplication
+│   ├── llm_service.py          # Multi-backend LLM client & NLP heuristic engine
+│   └── resume_service.py       # Resume path manager & reportlab PDF generator
+├── automation/
+│   └── pages/
+│       ├── base_page.py        # Playwright POM base with anti-detection & typing jitter
+│       ├── login_page.py       # Auth state verification & manual checkpoint polling
+│       ├── job_search_page.py  # Easy Apply search navigation & job card extraction
+│       ├── job_details_page.py # Description extraction & Easy Apply launcher
+│       └── easy_apply_modal.py # Modal step traversal, dynamic filling, review
+├── agents/
+│   ├── job_evaluator.py        # LLM semantic fit scorer & experience analysis
+│   ├── form_agent.py           # Dynamic form question interpreter & HITL routing
+│   └── fsm_runner.py           # Finite State Machine orchestrator
+├── tests/                      # Pytest automated test suite
+├── main.py                     # Rich CLI runner & dashboard
+├── requirements.txt            # Python dependencies
+└── .env.example                # Example environment variables
+```
+
+---
+
+## Finite State Machine (FSM) Lifecycle
+
+```mermaid
+stateDiagram-v2
+    [*] --> INIT
+    INIT --> LAUNCH_BROWSER: Load profile & init database
+    LAUNCH_BROWSER --> CHECK_LOGIN: Launch persistent Chromium context
+    CHECK_LOGIN --> CHECK_LOGIN: Pause & wait if CAPTCHA / 2FA / Login needed
+    CHECK_LOGIN --> SEARCH_JOBS: Authenticated
+    SEARCH_JOBS --> EXTRACT_CARDS: Search with f_AL=true (Easy Apply)
+    EXTRACT_CARDS --> EVALUATE_FIT: Filter out applied jobs
+    EVALUATE_FIT --> NEXT_JOB: Score < min_score OR Experience Reject
+    EVALUATE_FIT --> FILL_FORM: Score >= min_score -> Launch Modal
+    FILL_FORM --> AWAIT_APPROVAL: Reached final review step
+    AWAIT_APPROVAL --> SUBMIT: User Approved [y]
+    AWAIT_APPROVAL --> NEXT_JOB: User Skipped [n]
+    SUBMIT --> TRACK: Click submit
+    TRACK --> NEXT_JOB: Persist to applications.db
+    NEXT_JOB --> EXTRACT_CARDS: Next unapplied card
+    NEXT_JOB --> [*]: Max jobs reached or finished
+```
+
+---
+
+## Key Features & Adherence to Requirements
+
+1. **Finite State Machine & Page Object Model**:
+   - Clean separation between Playwright UI interactions (`automation/pages/`), agent decision logic (`agents/`), data storage (`services/`), and schema contracts (`models/`).
+
+2. **Stealth & Persistent Browser Context**:
+   - Uses Chromium in non-headless mode by default (`HEADLESS=false`).
+   - Uses persistent profile directory (`.browser_context/`) to preserve cookies, sessions, and tokens.
+   - **Zero Credential Storage**: LinkedIn passwords are never stored in code, `.env`, or logs.
+   - **No Automated Solvers**: If LinkedIn prompts with 2FA, OTP, or CAPTCHA, the agent halts, prints an alert to the terminal, and waits for manual completion in the open browser before resuming.
+
+3. **Candidate Profile as Single Source of Truth**:
+   - Located at `config/candidate_profile.json`.
+   - All downstream calculations (compensation, experience years, notice period, skill lookups) dynamically read from this profile without hardcoded values.
+
+4. **Semantic LLM Fit Scoring**:
+   - Evaluates:
+     - **Experience Match**: Candidate has 4 years; if job asks for 5–8 years, score is downgraded proportionally; if >8 years or Director/Lead, hard rejection.
+     - **Skill Match**: Semantic clustering recognizing synonyms (e.g. RestAssured/Postman <-> API testing, Selenium/Playwright <-> Web automation).
+     - **Role Match**: Checks relevance against preferred roles (QA Automation Engineer, SDET, etc.).
+   - Skips postings when `overall_score < minimum_match_score` (70%).
+
+5. **Dynamic Form Filling**:
+   - Maps standard personal details, current/expected CTC, 60 days notice period, and skill-specific experience years.
+   - Handles dropdowns, radio groups, and file uploads.
+   - Flags sensitive/ambiguous declarations (clearance, disability, citizenship) for explicit HITL prompt.
+
+6. **Human-in-the-Loop (HITL) Gate**:
+   - Pauses on the final review step of the modal.
+   - Renders a Rich summary table (Job Title, Company, Match Score, File Uploaded).
+   - Requires explicit user approval (`[y] Approve & Submit / [n] Skip / [q] Quit`) before clicking the submit button.
+
+7. **Application Tracking & Deduplication**:
+   - Async SQLite database (`applications.db`) with an `applications` table.
+   - Queries by `job_id` or `job_url` + `company` before opening any job card to avoid duplicates.
+
+---
+
+## Installation & Setup
+
+1. **Install Dependencies**:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. **Initialize Playwright Browser**:
+   ```bash
+   playwright install chromium
+   ```
+
+3. **Configure Environment (Optional)**:
+   ```bash
+   cp .env.example .env
+   ```
+   Add your `OPENAI_API_KEY` or `GEMINI_API_KEY` if you want live cloud LLM reasoning. If left empty, the built-in deterministic NLP extraction and semantic scoring engine will run offline automatically.
+
+---
+
+## Usage Guide
+
+### 1. Dry Run (Recommended for testing without submitting)
+Simulates the workflow, extracts cards, computes fit scores, fills forms up to the final review step, and tests the HITL prompt without submitting:
+```bash
+python main.py --keyword "QA Automation Engineer" --location "Hyderabad" --max-jobs 3 --dry-run
+```
+
+### 2. Live Apply Mode
+Executes the live workflow with non-headless browser:
+```bash
+python main.py --keyword "SDET" --location "Hyderabad" --min-score 70 --max-jobs 5
+```
+
+### 3. CLI Command Options
+```
+--keyword      Job title or search keyword (default: "QA Automation Engineer")
+--location     Search location (default: "Hyderabad")
+--max-jobs     Maximum applications to process (default: 10)
+--min-score    Minimum fit score required to proceed (default: 70.0)
+--headless     Run Chromium in headless mode (default: False)
+--dry-run      Fill forms to review step without clicking final submit
+--auto-approve Bypass interactive HITL prompt at review step
+--profile      Custom path to candidate_profile.json
+--log-level    Logging level [DEBUG, INFO, WARNING, ERROR] (default: INFO)
+```
+
+---
+
+## Running the Automated Test Suite
+
+Execute pytest across all test modules:
+```bash
+pytest tests/ -v
+```

jobagent-1.0.5/README.md

@@ -0,0 +1,160 @@
+# Hybrid Browser AI Agent for LinkedIn Easy Apply
+
+A Python-based browser automation AI agent built with **Playwright**, a **Finite State Machine (FSM)**, **Page Object Model (POM)**, and an **LLM-driven Semantic Matching & Form Interpretation Engine** with a strict **Human-in-the-Loop (HITL)** approval gate.
+
+---
+
+## Architecture Overview
+
+```
+d:\Gravity\
+├── config/
+│   ├── candidate_profile.json  # Single source of truth for candidate data
+│   └── settings.py             # Pydantic BaseSettings (.env loader)
+├── models/
+│   ├── profile.py              # Pydantic models for Candidate Profile
+│   ├── job.py                  # JobCardSummary and JobDetails schemas
+│   ├── evaluation.py           # MatchBreakdown and JobEvaluationResult schemas
+│   ├── form.py                 # FormField, FormStep, ApplicationSummary schemas
+│   └── application.py          # Database ApplicationRecord and Status
+├── services/
+│   ├── profile_loader.py       # Profile reader & dynamic field calculation
+│   ├── db_service.py           # SQLite/PostgreSQL persistence & deduplication
+│   ├── llm_service.py          # Multi-backend LLM client & NLP heuristic engine
+│   └── resume_service.py       # Resume path manager & reportlab PDF generator
+├── automation/
+│   └── pages/
+│       ├── base_page.py        # Playwright POM base with anti-detection & typing jitter
+│       ├── login_page.py       # Auth state verification & manual checkpoint polling
+│       ├── job_search_page.py  # Easy Apply search navigation & job card extraction
+│       ├── job_details_page.py # Description extraction & Easy Apply launcher
+│       └── easy_apply_modal.py # Modal step traversal, dynamic filling, review
+├── agents/
+│   ├── job_evaluator.py        # LLM semantic fit scorer & experience analysis
+│   ├── form_agent.py           # Dynamic form question interpreter & HITL routing
+│   └── fsm_runner.py           # Finite State Machine orchestrator
+├── tests/                      # Pytest automated test suite
+├── main.py                     # Rich CLI runner & dashboard
+├── requirements.txt            # Python dependencies
+└── .env.example                # Example environment variables
+```
+
+---
+
+## Finite State Machine (FSM) Lifecycle
+
+```mermaid
+stateDiagram-v2
+    [*] --> INIT
+    INIT --> LAUNCH_BROWSER: Load profile & init database
+    LAUNCH_BROWSER --> CHECK_LOGIN: Launch persistent Chromium context
+    CHECK_LOGIN --> CHECK_LOGIN: Pause & wait if CAPTCHA / 2FA / Login needed
+    CHECK_LOGIN --> SEARCH_JOBS: Authenticated
+    SEARCH_JOBS --> EXTRACT_CARDS: Search with f_AL=true (Easy Apply)
+    EXTRACT_CARDS --> EVALUATE_FIT: Filter out applied jobs
+    EVALUATE_FIT --> NEXT_JOB: Score < min_score OR Experience Reject
+    EVALUATE_FIT --> FILL_FORM: Score >= min_score -> Launch Modal
+    FILL_FORM --> AWAIT_APPROVAL: Reached final review step
+    AWAIT_APPROVAL --> SUBMIT: User Approved [y]
+    AWAIT_APPROVAL --> NEXT_JOB: User Skipped [n]
+    SUBMIT --> TRACK: Click submit
+    TRACK --> NEXT_JOB: Persist to applications.db
+    NEXT_JOB --> EXTRACT_CARDS: Next unapplied card
+    NEXT_JOB --> [*]: Max jobs reached or finished
+```
+
+---
+
+## Key Features & Adherence to Requirements
+
+1. **Finite State Machine & Page Object Model**:
+   - Clean separation between Playwright UI interactions (`automation/pages/`), agent decision logic (`agents/`), data storage (`services/`), and schema contracts (`models/`).
+
+2. **Stealth & Persistent Browser Context**:
+   - Uses Chromium in non-headless mode by default (`HEADLESS=false`).
+   - Uses persistent profile directory (`.browser_context/`) to preserve cookies, sessions, and tokens.
+   - **Zero Credential Storage**: LinkedIn passwords are never stored in code, `.env`, or logs.
+   - **No Automated Solvers**: If LinkedIn prompts with 2FA, OTP, or CAPTCHA, the agent halts, prints an alert to the terminal, and waits for manual completion in the open browser before resuming.
+
+3. **Candidate Profile as Single Source of Truth**:
+   - Located at `config/candidate_profile.json`.
+   - All downstream calculations (compensation, experience years, notice period, skill lookups) dynamically read from this profile without hardcoded values.
+
+4. **Semantic LLM Fit Scoring**:
+   - Evaluates:
+     - **Experience Match**: Candidate has 4 years; if job asks for 5–8 years, score is downgraded proportionally; if >8 years or Director/Lead, hard rejection.
+     - **Skill Match**: Semantic clustering recognizing synonyms (e.g. RestAssured/Postman <-> API testing, Selenium/Playwright <-> Web automation).
+     - **Role Match**: Checks relevance against preferred roles (QA Automation Engineer, SDET, etc.).
+   - Skips postings when `overall_score < minimum_match_score` (70%).
+
+5. **Dynamic Form Filling**:
+   - Maps standard personal details, current/expected CTC, 60 days notice period, and skill-specific experience years.
+   - Handles dropdowns, radio groups, and file uploads.
+   - Flags sensitive/ambiguous declarations (clearance, disability, citizenship) for explicit HITL prompt.
+
+6. **Human-in-the-Loop (HITL) Gate**:
+   - Pauses on the final review step of the modal.
+   - Renders a Rich summary table (Job Title, Company, Match Score, File Uploaded).
+   - Requires explicit user approval (`[y] Approve & Submit / [n] Skip / [q] Quit`) before clicking the submit button.
+
+7. **Application Tracking & Deduplication**:
+   - Async SQLite database (`applications.db`) with an `applications` table.
+   - Queries by `job_id` or `job_url` + `company` before opening any job card to avoid duplicates.
+
+---
+
+## Installation & Setup
+
+1. **Install Dependencies**:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. **Initialize Playwright Browser**:
+   ```bash
+   playwright install chromium
+   ```
+
+3. **Configure Environment (Optional)**:
+   ```bash
+   cp .env.example .env
+   ```
+   Add your `OPENAI_API_KEY` or `GEMINI_API_KEY` if you want live cloud LLM reasoning. If left empty, the built-in deterministic NLP extraction and semantic scoring engine will run offline automatically.
+
+---
+
+## Usage Guide
+
+### 1. Dry Run (Recommended for testing without submitting)
+Simulates the workflow, extracts cards, computes fit scores, fills forms up to the final review step, and tests the HITL prompt without submitting:
+```bash
+python main.py --keyword "QA Automation Engineer" --location "Hyderabad" --max-jobs 3 --dry-run
+```
+
+### 2. Live Apply Mode
+Executes the live workflow with non-headless browser:
+```bash
+python main.py --keyword "SDET" --location "Hyderabad" --min-score 70 --max-jobs 5
+```
+
+### 3. CLI Command Options
+```
+--keyword      Job title or search keyword (default: "QA Automation Engineer")
+--location     Search location (default: "Hyderabad")
+--max-jobs     Maximum applications to process (default: 10)
+--min-score    Minimum fit score required to proceed (default: 70.0)
+--headless     Run Chromium in headless mode (default: False)
+--dry-run      Fill forms to review step without clicking final submit
+--auto-approve Bypass interactive HITL prompt at review step
+--profile      Custom path to candidate_profile.json
+--log-level    Logging level [DEBUG, INFO, WARNING, ERROR] (default: INFO)
+```
+
+---
+
+## Running the Automated Test Suite
+
+Execute pytest across all test modules:
+```bash
+pytest tests/ -v
+```

jobagent-1.0.5/agents/__init__.py

@@ -0,0 +1,10 @@
+from .job_evaluator import JobEvaluator
+from .form_agent import FormAgent
+from .fsm_runner import FSMRunner, WorkflowState
+
+__all__ = [
+    "JobEvaluator",
+    "FormAgent",
+    "FSMRunner",
+    "WorkflowState",
+]