3.0.20

Merge remote-tracking branch 'origin/dev' into marcelwiegand-master
🐛(anthropic.ts): fix incorrect usage of 'typeof' operator for MODEL variable
2026-01-12 23:28:16 -05:00 · 2024-08-19 12:34:35 +03:00 · 2024-08-19 12:29:55 +03:00 · 2024-08-19 11:13:37 +02:00 · 2024-08-19 11:13:09 +02:00 · 2024-08-19 10:42:36 +03:00
44 changed files with 21906 additions and 3650 deletions
--- a/README.md
+++ b/README.md
@@ -58,7 +58,7 @@ git add <files...>
 oco
 ```

-Link to the GitMoji specification: https://gitmoji.dev/
+### Running locally with Ollama

 You can also run it with local model through ollama:

@@ -71,12 +71,29 @@ git add <files...>
 OCO_AI_PROVIDER='ollama' opencommit
 ```

+If you want to use a model other than mistral, you can do so by setting the `OCO_AI_PROVIDER` environment variable as follows:
+
+```sh
+OCO_AI_PROVIDER='ollama/llama3:8b' opencommit
+```
+
+if you have ollama that is set up in docker/ on another machine with GPUs (not locally), you can change the default endpoint url.
+You can do so by setting the `OCO_OLLAMA_API_URL` environment variable as follows:
+
+```sh
+OCO_OLLAMA_API_URL='http://192.168.1.10:11434/api/chat' opencommit
+```
+
+where 192.168.1.10 is example of endpoint URL, where you have ollama set up.
+
 ### Flags

 There are multiple optional flags that can be used with the `oco` command:

 #### Use Full GitMoji Specification

+Link to the GitMoji specification: https://gitmoji.dev/
+
 This flag can only be used if the `OCO_EMOJI` configuration item is set to `true`. This flag allows users to use all emojis in the GitMoji specification, By default, the GitMoji full specification is set to `false`, which only includes 10 emojis (🐛✨📝🚀✅♻️⬆️🔧🌐💡).
 This is due to limit the number of tokens sent in each request. However, if you would like to use the full GitMoji specification, you can use the `--fgm` flag.

@@ -84,6 +101,14 @@ This is due to limit the number of tokens sent in each request. However, if you
 oco --fgm
 ```

+#### Skip Commit Confirmation
+
+This flag allows users to automatically commit the changes without having to manually confirm the commit message. This is useful for users who want to streamline the commit process and avoid additional steps. To use this flag, you can run the following command:
+
+```
+oco --yes
+```
+
 ## Configuration

 ### Local per repo configuration
@@ -97,11 +122,12 @@ OCO_TOKENS_MAX_OUTPUT=<max response tokens (default: 500)>
 OCO_OPENAI_BASE_PATH=<may be used to set proxy path to OpenAI api>
 OCO_DESCRIPTION=<postface a message with ~3 sentences description of the changes>
 OCO_EMOJI=<boolean, add GitMoji>
-OCO_MODEL=<either 'gpt-4', 'gpt-4-turbo', 'gpt-3.5-turbo' (default), 'gpt-3.5-turbo-0125', 'gpt-4-1106-preview', 'gpt-4-turbo-preview' or 'gpt-4-0125-preview'>
+OCO_MODEL=<either 'gpt-4o', 'gpt-4', 'gpt-4-turbo', 'gpt-3.5-turbo' (default), 'gpt-3.5-turbo-0125', 'gpt-4-1106-preview', 'gpt-4-turbo-preview' or 'gpt-4-0125-preview'>
 OCO_LANGUAGE=<locale, scroll to the bottom to see options>
 OCO_MESSAGE_TEMPLATE_PLACEHOLDER=<message template placeholder, default: '$msg'>
 OCO_PROMPT_MODULE=<either conventional-commit or @commitlint, default: conventional-commit>
 OCO_ONE_LINE_COMMIT=<one line commit message, default: false>
+OCO_AI_PROVIDER=<anthropic, azure, ollama or ollama/model default ollama model: mistral>
 ```

 ### Global config for all repos
@@ -111,7 +137,7 @@ Local config still has more priority than Global config, but you may set `OCO_MO
 Simply set any of the variables above like this:

 ```sh
-oco config set OCO_MODEL=gpt-4
+oco config set OCO_MODEL=gpt-4o
 ```

 Configure [GitMoji](https://gitmoji.dev/) to preface a message.
@@ -128,7 +154,7 @@ oco config set OCO_EMOJI=false

 ### Switch to GPT-4 or other models

-By default, OpenCommit uses `gpt-3.5-turbo` model.
+By default, OpenCommit uses `gpt-4o` model.

 You may switch to GPT-4 which performs better, but costs ~x15 times more 🤠

@@ -139,16 +165,22 @@ oco config set OCO_MODEL=gpt-4
 or for as a cheaper option:

 ```sh
-oco config set OCO_MODEL=gpt-3.5-turbo
+oco config set OCO_MODEL=gpt-4o-mini
 ```

-or for GPT-4 Turbo (Preview) which is more capable, has knowledge of world events up to April 2023, a 128k context window and 2-3x cheaper vs GPT-4:
+### Switch to Azure OpenAI
+
+By default OpenCommit uses [OpenAI](https://openai.com).
+
+You could switch to [Azure OpenAI Service](https://learn.microsoft.com/azure/cognitive-services/openai/)🚀

 ```sh
-oco config set OCO_MODEL=gpt-4-0125-preview
+opencommit config set OCO_AI_PROVIDER=azure
 ```

-Make sure that you spell it `gpt-4` (lowercase) and that you have API access to the 4th model. Even if you have ChatGPT+, that doesn't necessarily mean that you have API access to GPT-4.
+Of course need to set 'OPENAI_API_KEY'. And also need to set the
+'OPENAI_BASE_PATH' for the endpoint and set the deployment name to
+'model'.

 ### Locale configuration

@@ -174,7 +206,7 @@ All available languages are currently listed in the [i18n](https://github.com/di
 Pushing to git is on by default but if you would like to turn it off just use:

 ```sh
-oc config set OCO_GITPUSH=false
+oco config set OCO_GITPUSH=false
 ```

 ### Switch to `@commitlint`
@@ -191,7 +223,7 @@ Replace `<module>` with either `conventional-commit` or `@commitlint`.

 #### Example:

-To switch to using th` '@commitlint` prompt module, run:
+To switch to using the `'@commitlint` prompt module, run:

 ```sh
 oco config set OCO_PROMPT_MODULE=@commitlint
@@ -359,7 +391,7 @@ jobs:
          OCO_OPENAI_BASE_PATH: ''
          OCO_DESCRIPTION: false
          OCO_EMOJI: false
-          OCO_MODEL: gpt-3.5-turbo
+          OCO_MODEL: gpt-4o
          OCO_LANGUAGE: en
          OCO_PROMPT_MODULE: conventional-commit
 ```
--- a/example.txt
+++ b/example.txt
--- a/out/cli.cjs
+++ b/out/cli.cjs
--- a/out/github-action.cjs
+++ b/out/github-action.cjs
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,20 +1,22 @@
 {
  "name": "opencommit",
-  "version": "3.0.15",
+  "version": "3.0.20",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "opencommit",
-      "version": "3.0.15",
+      "version": "3.0.20",
      "license": "MIT",
      "dependencies": {
        "@actions/core": "^1.10.0",
        "@actions/exec": "^1.1.1",
        "@actions/github": "^5.1.1",
        "@anthropic-ai/sdk": "^0.19.2",
+        "@azure/openai": "^1.0.0-beta.12",
        "@clack/prompts": "^0.6.1",
        "@dqbd/tiktoken": "^1.0.2",
+        "@google/generative-ai": "^0.11.4",
        "@octokit/webhooks-schemas": "^6.11.0",
        "@octokit/webhooks-types": "^6.11.0",
        "ai": "^2.2.14",
@@ -137,6 +139,126 @@
        "undici-types": "~5.26.4"
      }
    },
+    "node_modules/@azure-rest/core-client": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/@azure-rest/core-client/-/core-client-1.4.0.tgz",
+      "integrity": "sha512-ozTDPBVUDR5eOnMIwhggbnVmOrka4fXCs8n8mvUo4WLLc38kki6bAOByDoVZZPz/pZy2jMt2kwfpvy/UjALj6w==",
+      "dependencies": {
+        "@azure/abort-controller": "^2.0.0",
+        "@azure/core-auth": "^1.3.0",
+        "@azure/core-rest-pipeline": "^1.5.0",
+        "@azure/core-tracing": "^1.0.1",
+        "@azure/core-util": "^1.0.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/abort-controller": {
+      "version": "2.1.2",
+      "resolved": "https://registry.npmjs.org/@azure/abort-controller/-/abort-controller-2.1.2.tgz",
+      "integrity": "sha512-nBrLsEWm4J2u5LpAPjxADTlq3trDgVZZXHNKabeXZtpq3d3AbN/KGO82R87rdDz5/lYB024rtEf10/q0urNgsA==",
+      "dependencies": {
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/core-auth": {
+      "version": "1.7.2",
+      "resolved": "https://registry.npmjs.org/@azure/core-auth/-/core-auth-1.7.2.tgz",
+      "integrity": "sha512-Igm/S3fDYmnMq1uKS38Ae1/m37B3zigdlZw+kocwEhh5GjyKjPrXKO2J6rzpC1wAxrNil/jX9BJRqBshyjnF3g==",
+      "dependencies": {
+        "@azure/abort-controller": "^2.0.0",
+        "@azure/core-util": "^1.1.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/core-rest-pipeline": {
+      "version": "1.15.2",
+      "resolved": "https://registry.npmjs.org/@azure/core-rest-pipeline/-/core-rest-pipeline-1.15.2.tgz",
+      "integrity": "sha512-BmWfpjc/QXc2ipHOh6LbUzp3ONCaa6xzIssTU0DwH9bbYNXJlGUL6tujx5TrbVd/QQknmS+vlQJGrCq2oL1gZA==",
+      "dependencies": {
+        "@azure/abort-controller": "^2.0.0",
+        "@azure/core-auth": "^1.4.0",
+        "@azure/core-tracing": "^1.0.1",
+        "@azure/core-util": "^1.3.0",
+        "@azure/logger": "^1.0.0",
+        "http-proxy-agent": "^7.0.0",
+        "https-proxy-agent": "^7.0.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/core-sse": {
+      "version": "2.1.2",
+      "resolved": "https://registry.npmjs.org/@azure/core-sse/-/core-sse-2.1.2.tgz",
+      "integrity": "sha512-yf+pFIu8yCzXu9RbH2+8kp9vITIKJLHgkLgFNA6hxiDHK3fxeP596cHUj4c8Cm8JlooaUnYdHmF84KCZt3jbmw==",
+      "dependencies": {
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/core-tracing": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/@azure/core-tracing/-/core-tracing-1.1.2.tgz",
+      "integrity": "sha512-dawW9ifvWAWmUm9/h+/UQ2jrdvjCJ7VJEuCJ6XVNudzcOwm53BFZH4Q845vjfgoUAM8ZxokvVNxNxAITc502YA==",
+      "dependencies": {
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/core-util": {
+      "version": "1.9.0",
+      "resolved": "https://registry.npmjs.org/@azure/core-util/-/core-util-1.9.0.tgz",
+      "integrity": "sha512-AfalUQ1ZppaKuxPPMsFEUdX6GZPB3d9paR9d/TTL7Ow2De8cJaC7ibi7kWVlFAVPCYo31OcnGymc0R89DX8Oaw==",
+      "dependencies": {
+        "@azure/abort-controller": "^2.0.0",
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/logger": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/@azure/logger/-/logger-1.1.2.tgz",
+      "integrity": "sha512-l170uE7bsKpIU6B/giRc9i4NI0Mj+tANMMMxf7Zi/5cKzEqPayP7+X1WPrG7e+91JgY8N+7K7nF2WOi7iVhXvg==",
+      "dependencies": {
+        "tslib": "^2.6.2"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@azure/openai": {
+      "version": "1.0.0-beta.12",
+      "resolved": "https://registry.npmjs.org/@azure/openai/-/openai-1.0.0-beta.12.tgz",
+      "integrity": "sha512-qKblxr6oVa8GsyNzY+/Ub9VmEsPYKhBrUrPaNEQiM+qrxnBPVm9kaeqGFFb/U78Q2zOabmhF9ctYt3xBW0nWnQ==",
+      "dependencies": {
+        "@azure-rest/core-client": "^1.1.7",
+        "@azure/core-auth": "^1.4.0",
+        "@azure/core-rest-pipeline": "^1.13.0",
+        "@azure/core-sse": "^2.0.0",
+        "@azure/core-util": "^1.4.0",
+        "@azure/logger": "^1.0.3",
+        "tslib": "^2.4.0"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
    "node_modules/@babel/code-frame": {
      "version": "7.24.2",
      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.24.2.tgz",
@@ -930,6 +1052,14 @@
        "node": ">=14"
      }
    },
+    "node_modules/@google/generative-ai": {
+      "version": "0.11.4",
+      "resolved": "https://registry.npmjs.org/@google/generative-ai/-/generative-ai-0.11.4.tgz",
+      "integrity": "sha512-hlw+E9Prv9aUIQISRnLSXi4rukFqKe5WhxPvzBccTvIvXjw2BHMFOJWSC/Gq7WE0W+L/qRHGmYxopmx9qjrB9w==",
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
    "node_modules/@humanwhocodes/config-array": {
      "version": "0.11.14",
      "resolved": "https://registry.npmjs.org/@humanwhocodes/config-array/-/config-array-0.11.14.tgz",
@@ -2349,6 +2479,17 @@
        "node": ">=0.4.0"
      }
    },
+    "node_modules/agent-base": {
+      "version": "7.1.1",
+      "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-7.1.1.tgz",
+      "integrity": "sha512-H0TSyFNDMomMNJQBn8wFV5YC/2eJ+VXECwOadZJT554xP6cODZHPX3H9QMQECxvrgiSOP1pHjy1sMWQVYJOUOA==",
+      "dependencies": {
+        "debug": "^4.3.4"
+      },
+      "engines": {
+        "node": ">= 14"
+      }
+    },
    "node_modules/agentkeepalive": {
      "version": "4.5.0",
      "resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz",
@@ -3285,7 +3426,6 @@
      "version": "4.3.4",
      "resolved": "https://registry.npmjs.org/debug/-/debug-4.3.4.tgz",
      "integrity": "sha512-PRWFHuSU3eDtQJPvnNY7Jcket1j0t5OuOsFzPPzsekD52Zl8qUfFIPEiswXqIvHWGVHOgX+7G/vCNNhehwxfkQ==",
-      "dev": true,
      "dependencies": {
        "ms": "2.1.2"
      },
@@ -4742,6 +4882,30 @@
      "integrity": "sha512-H2iMtd0I4Mt5eYiapRdIDjp+XzelXQ0tFE4JS7YFwFevXXMmOp9myNrUvCg0D6ws8iqkRPBfKHgbwig1SmlLfg==",
      "dev": true
    },
+    "node_modules/http-proxy-agent": {
+      "version": "7.0.2",
+      "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-7.0.2.tgz",
+      "integrity": "sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==",
+      "dependencies": {
+        "agent-base": "^7.1.0",
+        "debug": "^4.3.4"
+      },
+      "engines": {
+        "node": ">= 14"
+      }
+    },
+    "node_modules/https-proxy-agent": {
+      "version": "7.0.4",
+      "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-7.0.4.tgz",
+      "integrity": "sha512-wlwpilI7YdjSkWaQ/7omYBMTliDcmCN8OLihO6I9B86g06lMyAoqgoDpV0XqoaPOKj+0DIdAvnsWfyAAhmimcg==",
+      "dependencies": {
+        "agent-base": "^7.0.2",
+        "debug": "4"
+      },
+      "engines": {
+        "node": ">= 14"
+      }
+    },
    "node_modules/human-signals": {
      "version": "4.3.1",
      "resolved": "https://registry.npmjs.org/human-signals/-/human-signals-4.3.1.tgz",
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "opencommit",
-  "version": "3.0.15",
+  "version": "3.0.20",
  "description": "Auto-generate impressive commits in 1 second. Killing lame commits with AI 🤯🔫",
  "keywords": [
    "git",
@@ -43,16 +43,20 @@
    "start": "node ./out/cli.cjs",
    "ollama:start": "OCO_AI_PROVIDER='ollama' node ./out/cli.cjs",
    "dev": "ts-node ./src/cli.ts",
+    "dev:gemini": "OCO_AI_PROVIDER='gemini' ts-node ./src/cli.ts",
    "build": "rimraf out && node esbuild.config.js",
    "build:push": "npm run build && git add . && git commit -m 'build' && git push",
-    "deploy": "npm version patch && npm run build:push && git push --tags && npm publish --tag latest",
+    "deploy": "npm run build:push && git push --tags && npm publish --tag latest",
+    "deploy:patch": "npm version patch && npm run deploy",
    "lint": "eslint src --ext ts && tsc --noEmit",
    "format": "prettier --write src",
+    "test": "node --no-warnings --experimental-vm-modules $( [ -f ./node_modules/.bin/jest ] && echo ./node_modules/.bin/jest || which jest ) test/unit",
    "test:all": "npm run test:unit:docker && npm run test:e2e:docker",
    "test:docker-build": "docker build -t oco-test -f test/Dockerfile .",
    "test:unit": "NODE_OPTIONS=--experimental-vm-modules jest test/unit",
    "test:unit:docker": "npm run test:docker-build && DOCKER_CONTENT_TRUST=0 docker run --rm oco-test npm run test:unit",
-    "test:e2e": "jest test/e2e",
+    "test:e2e": "npm run test:e2e:setup && jest test/e2e",
+    "test:e2e:setup": "sh test/e2e/setup.sh",
    "test:e2e:docker": "npm run test:docker-build && DOCKER_CONTENT_TRUST=0 docker run --rm oco-test npm run test:e2e"
  },
  "devDependencies": {
@@ -77,9 +81,11 @@
    "@actions/core": "^1.10.0",
    "@actions/exec": "^1.1.1",
    "@actions/github": "^5.1.1",
+    "@azure/openai": "^1.0.0-beta.12",
    "@anthropic-ai/sdk": "^0.19.2",
    "@clack/prompts": "^0.6.1",
    "@dqbd/tiktoken": "^1.0.2",
+    "@google/generative-ai": "^0.11.4",
    "@octokit/webhooks-schemas": "^6.11.0",
    "@octokit/webhooks-types": "^6.11.0",
    "ai": "^2.2.14",
@@ -92,5 +98,8 @@
    "ini": "^3.0.1",
    "inquirer": "^9.1.4",
    "openai": "^3.2.1"
+  },
+  "overrides": {
+    "whatwg-url": "13.0.0"
  }
 }
--- a/src/cli.ts
+++ b/src/cli.ts
@@ -18,7 +18,13 @@ cli(
    name: 'opencommit',
    commands: [configCommand, hookCommand, commitlintConfigCommand],
    flags: {
-      fgm: Boolean
+      fgm: Boolean,
+      yes: {
+        type: Boolean,
+        alias: 'y',
+        description: 'Skip commit confirmation prompt',
+        default: false
+      }
    },
    ignoreArgv: (type) => type === 'unknown-flag' || type === 'argument',
    help: { description: packageJSON.description }
@@ -29,7 +35,7 @@ cli(
    if (await isHookCalled()) {
      prepareCommitMessageHook();
    } else {
-      commit(extraArgs, false, flags.fgm);
+      commit(extraArgs, false, flags.fgm, flags.yes);
    }
  },
  extraArgs
--- a/src/commands/commit.ts
+++ b/src/commands/commit.ts
@@ -41,7 +41,8 @@ const checkMessageTemplate = (extraArgs: string[]): string | false => {
 const generateCommitMessageFromGitDiff = async (
  diff: string,
  extraArgs: string[],
-  fullGitMojiSpec: boolean
+  fullGitMojiSpec: boolean,
+  skipCommitConfirmation: boolean
 ): Promise<void> => {
  await assertGitRepo();
  const commitSpinner = spinner();
@@ -76,7 +77,7 @@ ${commitMessage}
 ${chalk.grey('——————————————————')}`
    );

-    const isCommitConfirmedByUser = await confirm({
+    const isCommitConfirmedByUser = skipCommitConfirmation || await confirm({
      message: 'Confirm the commit message?'
    });

@@ -154,6 +155,18 @@ ${chalk.grey('——————————————————')}`
        } else outro(`${chalk.gray('✖')} process cancelled`);
      }
    }
+    if (!isCommitConfirmedByUser && !isCancel(isCommitConfirmedByUser)) {
+      const regenerateMessage = await confirm({
+        message: 'Do you want to regenerate the message ?'
+      });
+      if (regenerateMessage && !isCancel(isCommitConfirmedByUser)) {
+        await generateCommitMessageFromGitDiff(
+          diff,
+          extraArgs,
+          fullGitMojiSpec
+        )
+      }
+    }
  } catch (error) {
    commitSpinner.stop('📝 Commit message generated');

@@ -166,7 +179,8 @@ ${chalk.grey('——————————————————')}`
 export async function commit(
  extraArgs: string[] = [],
  isStageAllFlag: Boolean = false,
-  fullGitMojiSpec: boolean = false
+  fullGitMojiSpec: boolean = false,
+  skipCommitConfirmation: boolean = false
 ) {
  if (isStageAllFlag) {
    const changedFiles = await getChangedFiles();
@@ -238,7 +252,8 @@ export async function commit(
    generateCommitMessageFromGitDiff(
      await getDiff({ files: stagedFiles }),
      extraArgs,
-      fullGitMojiSpec
+      fullGitMojiSpec,
+      skipCommitConfirmation
    )
  );

--- a/src/commands/config.ts
+++ b/src/commands/config.ts
@@ -10,10 +10,14 @@ import { intro, outro } from '@clack/prompts';

 import { COMMANDS } from '../CommandsEnum';
 import { getI18nLocal } from '../i18n';
+import { TEST_MOCK_TYPES } from '../engine/testAi';

 export enum CONFIG_KEYS {
  OCO_OPENAI_API_KEY = 'OCO_OPENAI_API_KEY',
  OCO_ANTHROPIC_API_KEY = 'OCO_ANTHROPIC_API_KEY',
+  OCO_AZURE_API_KEY = 'OCO_AZURE_API_KEY',
+  OCO_GEMINI_API_KEY = 'OCO_GEMINI_API_KEY',
+  OCO_GEMINI_BASE_PATH = 'OCO_GEMINI_BASE_PATH',
  OCO_TOKENS_MAX_INPUT = 'OCO_TOKENS_MAX_INPUT',
  OCO_TOKENS_MAX_OUTPUT = 'OCO_TOKENS_MAX_OUTPUT',
  OCO_OPENAI_BASE_PATH = 'OCO_OPENAI_BASE_PATH',
@@ -25,7 +29,13 @@ export enum CONFIG_KEYS {
  OCO_PROMPT_MODULE = 'OCO_PROMPT_MODULE',
  OCO_AI_PROVIDER = 'OCO_AI_PROVIDER',
  OCO_GITPUSH = 'OCO_GITPUSH',
-  OCO_ONE_LINE_COMMIT = 'OCO_ONE_LINE_COMMIT'
+  OCO_ONE_LINE_COMMIT = 'OCO_ONE_LINE_COMMIT',
+  OCO_AZURE_ENDPOINT = 'OCO_AZURE_ENDPOINT',
+  OCO_TEST_MOCK_TYPE = 'OCO_TEST_MOCK_TYPE',
+  OCO_API_URL = 'OCO_API_URL',
+  OCO_OLLAMA_API_URL = 'OCO_OLLAMA_API_URL',
+  OCO_FLOWISE_ENDPOINT = 'OCO_FLOWISE_ENDPOINT',
+  OCO_FLOWISE_API_KEY = 'OCO_FLOWISE_API_KEY'
 }

 export enum CONFIG_MODES {
@@ -34,18 +44,50 @@ export enum CONFIG_MODES {
 }

 export const MODEL_LIST = {
-  openai: ['gpt-3.5-turbo',
-          'gpt-3.5-turbo-0125',
-          'gpt-4',
-          'gpt-4-turbo',
-          'gpt-4-1106-preview',
-          'gpt-4-turbo-preview',
-          'gpt-4-0125-preview'],
+  openai: [
+    'gpt-4o-mini',
+    'gpt-3.5-turbo',
+    'gpt-3.5-turbo-instruct',
+    'gpt-3.5-turbo-0613',
+    'gpt-3.5-turbo-0301',
+    'gpt-3.5-turbo-1106',
+    'gpt-3.5-turbo-0125',
+    'gpt-3.5-turbo-16k',
+    'gpt-3.5-turbo-16k-0613',
+    'gpt-3.5-turbo-16k-0301',
+    'gpt-4',
+    'gpt-4-0314',
+    'gpt-4-0613',
+    'gpt-4-1106-preview',
+    'gpt-4-0125-preview',
+    'gpt-4-turbo-preview',
+    'gpt-4-vision-preview',
+    'gpt-4-1106-vision-preview',
+    'gpt-4-turbo',
+    'gpt-4-turbo-2024-04-09',
+    'gpt-4-32k',
+    'gpt-4-32k-0314',
+    'gpt-4-32k-0613',
+    'gpt-4o',
+    'gpt-4o-2024-05-13',
+    'gpt-4o-mini-2024-07-18'
+  ],

-  anthropic: ['claude-3-haiku-20240307',
-              'claude-3-sonnet-20240229',
-              'claude-3-opus-20240229']
-}
+  anthropic: [
+    'claude-3-5-sonnet-20240620',
+    'claude-3-opus-20240229',
+    'claude-3-sonnet-20240229',
+    'claude-3-haiku-20240307'
+  ],
+
+  gemini: [
+    'gemini-1.5-flash',
+    'gemini-1.5-pro',
+    'gemini-1.0-pro',
+    'gemini-pro-vision',
+    'text-embedding-004'
+  ]
+};

 const getDefaultModel = (provider: string | undefined): string => {
  switch (provider) {
@@ -53,6 +95,8 @@ const getDefaultModel = (provider: string | undefined): string => {
      return '';
    case 'anthropic':
      return MODEL_LIST.anthropic[0];
+    case 'gemini':
+      return MODEL_LIST.gemini[0];
    default:
      return MODEL_LIST.openai[0];
  }
@@ -79,16 +123,51 @@ const validateConfig = (

 export const configValidators = {
  [CONFIG_KEYS.OCO_OPENAI_API_KEY](value: any, config: any = {}) {
+    if (config.OCO_AI_PROVIDER == 'gemini') return value;
+
    //need api key unless running locally with ollama
    validateConfig(
      'OpenAI API_KEY',
-      value || config.OCO_ANTHROPIC_API_KEY || config.OCO_AI_PROVIDER == 'ollama' || config.OCO_AI_PROVIDER == 'test',
-      'You need to provide an OpenAI/Anthropic API key'
+      value ||
+        config.OCO_ANTHROPIC_API_KEY ||
+        config.OCO_AI_PROVIDER.startsWith('ollama') ||
+        config.OCO_AZURE_API_KEY ||
+        config.OCO_AI_PROVIDER == 'test' ||
+        config.OCO_AI_PROVIDER == 'flowise',
+      'You need to provide an OpenAI/Anthropic/Azure or other provider API key via `oco config set OCO_OPENAI_API_KEY=your_key`, for help refer to docs https://github.com/di-sukharev/opencommit'
    );
    validateConfig(
      CONFIG_KEYS.OCO_OPENAI_API_KEY,
-      value.startsWith('sk-'),
-      'Must start with "sk-"'
+      value.startsWith('sk-') || config.OCO_AI_PROVIDER != 'openai',
+      'Must start with "sk-" for openai provider'
+    );
+
+    return value;
+  },
+
+  [CONFIG_KEYS.OCO_AZURE_API_KEY](value: any, config: any = {}) {
+    validateConfig(
+      'ANTHROPIC_API_KEY',
+      value ||
+        config.OCO_OPENAI_API_KEY ||
+        config.OCO_AZURE_API_KEY ||
+        config.OCO_AI_PROVIDER == 'ollama' ||
+        config.OCO_AI_PROVIDER == 'test' ||
+        config.OCO_AI_PROVIDER == 'flowise',
+      'You need to provide an OpenAI/Anthropic/Azure API key'
+    );
+
+    return value;
+  },
+
+  [CONFIG_KEYS.OCO_GEMINI_API_KEY](value: any, config: any = {}) {
+    // only need to check for gemini api key if using gemini
+    if (config.OCO_AI_PROVIDER != 'gemini') return value;
+
+    validateConfig(
+      'Gemini API Key',
+      value || config.OCO_GEMINI_API_KEY || config.OCO_AI_PROVIDER == 'test',
+      'You need to provide an Gemini API key'
    );

    return value;
@@ -97,13 +176,27 @@ export const configValidators = {
  [CONFIG_KEYS.OCO_ANTHROPIC_API_KEY](value: any, config: any = {}) {
    validateConfig(
      'ANTHROPIC_API_KEY',
-      value || config.OCO_OPENAI_API_KEY || config.OCO_AI_PROVIDER == 'ollama' || config.OCO_AI_PROVIDER == 'test',
+      value ||
+        config.OCO_OPENAI_API_KEY ||
+        config.OCO_AI_PROVIDER == 'ollama' ||
+        config.OCO_AI_PROVIDER == 'test' ||
+        config.OCO_AI_PROVIDER == 'flowise',
      'You need to provide an OpenAI/Anthropic API key'
    );

    return value;
  },

+  [CONFIG_KEYS.OCO_FLOWISE_API_KEY](value: any, config: any = {}) {
+    validateConfig(
+      CONFIG_KEYS.OCO_FLOWISE_API_KEY,
+      value || config.OCO_AI_PROVIDER != 'flowise',
+      'You need to provide a flowise API key'
+    );
+
+    return value;
+  },
+
  [CONFIG_KEYS.OCO_DESCRIPTION](value: any) {
    validateConfig(
      CONFIG_KEYS.OCO_DESCRIPTION,
@@ -180,11 +273,15 @@ export const configValidators = {
    return value;
  },

-  [CONFIG_KEYS.OCO_MODEL](value: any) {
+  [CONFIG_KEYS.OCO_MODEL](value: any, config: any = {}) {
    validateConfig(
      CONFIG_KEYS.OCO_MODEL,
-      [...MODEL_LIST.openai, ...MODEL_LIST.anthropic].includes(value),
-      `${value} is not supported yet, use 'gpt-4', 'gpt-4-turbo', 'gpt-3.5-turbo' (default), 'gpt-3.5-turbo-0125', 'gpt-4-1106-preview', 'gpt-4-turbo-preview', 'gpt-4-0125-preview', 'claude-3-opus-20240229', 'claude-3-sonnet-20240229' or 'claude-3-haiku-20240307'`
+      typeof value === 'string',
+      `${value} is not supported yet, use:\n\n ${[
+        ...MODEL_LIST.openai,
+        ...MODEL_LIST.anthropic,
+        ...MODEL_LIST.gemini
+      ].join('\n')}`
    );
    return value;
  },
@@ -223,10 +320,12 @@ export const configValidators = {
        '',
        'openai',
        'anthropic',
-        'ollama',
-        'test'
-      ].includes(value),
-      `${value} is not supported yet, use 'ollama' 'anthropic' or 'openai' (default)`
+        'gemini',
+        'azure',
+        'test',
+        'flowise'
+      ].includes(value) || value.startsWith('ollama'),
+      `${value} is not supported yet, use 'ollama', 'anthropic', 'azure', 'gemini', 'flowise' or 'openai' (default)`
    );
    return value;
  },
@@ -240,6 +339,47 @@ export const configValidators = {

    return value;
  },
+
+  [CONFIG_KEYS.OCO_AZURE_ENDPOINT](value: any) {
+    validateConfig(
+      CONFIG_KEYS.OCO_AZURE_ENDPOINT,
+      value.includes('openai.azure.com'),
+      'Must be in format "https://<resource name>.openai.azure.com/"'
+    );
+
+    return value;
+  },
+
+  [CONFIG_KEYS.OCO_FLOWISE_ENDPOINT](value: any) {
+    validateConfig(
+      CONFIG_KEYS.OCO_FLOWISE_ENDPOINT,
+      typeof value === 'string' && value.includes(':'),
+      'Value must be string and should include both I.P. and port number' // Considering the possibility of DNS lookup or feeding the I.P. explicitely, there is no pattern to verify, except a column for the port number
+    );
+
+    return value;
+  },
+
+  [CONFIG_KEYS.OCO_TEST_MOCK_TYPE](value: any) {
+    validateConfig(
+      CONFIG_KEYS.OCO_TEST_MOCK_TYPE,
+      TEST_MOCK_TYPES.includes(value),
+      `${value} is not supported yet, use ${TEST_MOCK_TYPES.map(
+        (t) => `'${t}'`
+      ).join(', ')}`
+    );
+    return value;
+  },
+
+  [CONFIG_KEYS.OCO_OLLAMA_API_URL](value: any) {
+    // add simple api validator
+    validateConfig(
+      CONFIG_KEYS.OCO_API_URL,
+      typeof value === 'string' && value.startsWith('http'),
+      `${value} is not a valid URL`
+    );
+    return value;
+  }
 };

 export type ConfigType = {
@@ -248,18 +388,19 @@ export type ConfigType = {

 const defaultConfigPath = pathJoin(homedir(), '.opencommit');
 const defaultEnvPath = pathResolve(process.cwd(), '.env');
-
 export const getConfig = ({
  configPath = defaultConfigPath,
  envPath = defaultEnvPath
 }: {
-  configPath?: string
-  envPath?: string
+  configPath?: string;
+  envPath?: string;
 } = {}): ConfigType | null => {
  dotenv.config({ path: envPath });
  const configFromEnv = {
    OCO_OPENAI_API_KEY: process.env.OCO_OPENAI_API_KEY,
    OCO_ANTHROPIC_API_KEY: process.env.OCO_ANTHROPIC_API_KEY,
+    OCO_AZURE_API_KEY: process.env.OCO_AZURE_API_KEY,
+    OCO_GEMINI_API_KEY: process.env.OCO_GEMINI_API_KEY,
    OCO_TOKENS_MAX_INPUT: process.env.OCO_TOKENS_MAX_INPUT
      ? Number(process.env.OCO_TOKENS_MAX_INPUT)
      : undefined,
@@ -267,18 +408,25 @@ export const getConfig = ({
      ? Number(process.env.OCO_TOKENS_MAX_OUTPUT)
      : undefined,
    OCO_OPENAI_BASE_PATH: process.env.OCO_OPENAI_BASE_PATH,
+    OCO_GEMINI_BASE_PATH: process.env.OCO_GEMINI_BASE_PATH,
    OCO_DESCRIPTION: process.env.OCO_DESCRIPTION === 'true' ? true : false,
    OCO_EMOJI: process.env.OCO_EMOJI === 'true' ? true : false,
-    OCO_MODEL: process.env.OCO_MODEL || getDefaultModel(process.env.OCO_AI_PROVIDER),
+    OCO_MODEL:
+      process.env.OCO_MODEL || getDefaultModel(process.env.OCO_AI_PROVIDER),
    OCO_LANGUAGE: process.env.OCO_LANGUAGE || 'en',
    OCO_MESSAGE_TEMPLATE_PLACEHOLDER:
      process.env.OCO_MESSAGE_TEMPLATE_PLACEHOLDER || '$msg',
    OCO_PROMPT_MODULE: process.env.OCO_PROMPT_MODULE || 'conventional-commit',
    OCO_AI_PROVIDER: process.env.OCO_AI_PROVIDER || 'openai',
    OCO_GITPUSH: process.env.OCO_GITPUSH === 'false' ? false : true,
-    OCO_ONE_LINE_COMMIT: process.env.OCO_ONE_LINE_COMMIT === 'true' ? true : false
+    OCO_ONE_LINE_COMMIT:
+      process.env.OCO_ONE_LINE_COMMIT === 'true' ? true : false,
+    OCO_AZURE_ENDPOINT: process.env.OCO_AZURE_ENDPOINT || undefined,
+    OCO_TEST_MOCK_TYPE: process.env.OCO_TEST_MOCK_TYPE || 'commit-message',
+    OCO_FLOWISE_ENDPOINT: process.env.OCO_FLOWISE_ENDPOINT || ':',
+    OCO_FLOWISE_API_KEY: process.env.OCO_FLOWISE_API_KEY || undefined,
+    OCO_OLLAMA_API_URL: process.env.OCO_OLLAMA_API_URL || undefined
  };
-
  const configExists = existsSync(configPath);
  if (!configExists) return configFromEnv;

@@ -286,9 +434,7 @@ export const getConfig = ({
  const config = iniParse(configFile);

  for (const configKey of Object.keys(config)) {
-    if (
-      ['null', 'undefined'].includes(config[configKey])
-    ) {
+    if (['null', 'undefined'].includes(config[configKey])) {
      config[configKey] = undefined;
      continue;
    }
@@ -301,10 +447,11 @@ export const getConfig = ({

      config[configKey] = validValue;
    } catch (error) {
-      outro(`Unknown '${configKey}' config option.`);
+      outro(`Unknown '${configKey}' config option or missing validator.`);
      outro(
        `Manually fix the '.env' file or global '~/.opencommit' config file.`
      );
+
      process.exit(1);
    }
  }
@@ -312,7 +459,10 @@ export const getConfig = ({
  return config;
 };

-export const setConfig = (keyValues: [key: string, value: string][], configPath: string = defaultConfigPath) => {
+export const setConfig = (
+  keyValues: [key: string, value: string][],
+  configPath: string = defaultConfigPath
+) => {
  const config = getConfig() || {};

  for (const [configKey, configValue] of keyValues) {
--- a/src/commands/prepare-commit-msg-hook.ts
+++ b/src/commands/prepare-commit-msg-hook.ts
@@ -39,9 +39,9 @@ export const prepareCommitMessageHook = async (

    const config = getConfig();

-    if (!config?.OCO_OPENAI_API_KEY) {
+    if (!config?.OCO_OPENAI_API_KEY && !config?.OCO_ANTHROPIC_API_KEY && !config?.OCO_AZURE_API_KEY) {
      throw new Error(
-        'No OPEN_AI_API exists. Set your OPEN_AI_API=<key> in ~/.opencommit'
+        'No OPEN_AI_API or OCO_ANTHROPIC_API_KEY or OCO_AZURE_API_KEY exists. Set your key in ~/.opencommit'
      );
    }

--- a/src/engine/anthropic.ts
+++ b/src/engine/anthropic.ts
@@ -48,18 +48,16 @@ if (

 const MODEL = config?.OCO_MODEL;
 if (provider === 'anthropic' &&
-    !MODEL_LIST.anthropic.includes(MODEL) &&
-    command !== 'config' &&
-    mode !== CONFIG_MODES.set) {
-  outro(
-    `${chalk.red('✖')} Unsupported model ${MODEL} for Anthropic. Supported models are: ${MODEL_LIST.anthropic.join(
-      ', '
-    )}`
-  );
-  process.exit(1);
+  typeof MODEL !== 'string' && 
+  command !== 'config' &&
+  mode !== CONFIG_MODES.set) {
+outro(
+  `${chalk.red('✖')} Unsupported model ${MODEL}. The model can be any string, but the current configuration is not supported.`
+);
+process.exit(1);
 }

-class AnthropicAi implements AiEngine {
+export class AnthropicAi implements AiEngine {
  private anthropicAiApiConfiguration = {
    apiKey: apiKey
  };
@@ -120,5 +118,3 @@ class AnthropicAi implements AiEngine {
    }
  };
 }
-
-export const anthropicAi = new AnthropicAi();
--- a/src/engine/azure.ts
+++ b/src/engine/azure.ts
@@ -0,0 +1,109 @@
+import axios from 'axios';
+import chalk from 'chalk';
+import { execa } from 'execa';
+import {
+  ChatCompletionRequestMessage,
+} from 'openai';
+
+import { OpenAIClient, AzureKeyCredential } from '@azure/openai';
+
+import { intro, outro } from '@clack/prompts';
+
+import {
+  CONFIG_MODES,
+  DEFAULT_TOKEN_LIMITS,
+  getConfig
+} from '../commands/config';
+import { GenerateCommitMessageErrorEnum } from '../generateCommitMessageFromGitDiff';
+import { tokenCount } from '../utils/tokenCount';
+import { AiEngine } from './Engine';
+
+const config = getConfig();
+
+const MAX_TOKENS_OUTPUT =
+  config?.OCO_TOKENS_MAX_OUTPUT ||
+  DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_OUTPUT;
+const MAX_TOKENS_INPUT =
+  config?.OCO_TOKENS_MAX_INPUT || DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_INPUT;
+let basePath = config?.OCO_OPENAI_BASE_PATH;
+let apiKey = config?.OCO_AZURE_API_KEY;
+let apiEndpoint = config?.OCO_AZURE_ENDPOINT;
+
+const [command, mode] = process.argv.slice(2);
+
+const provider = config?.OCO_AI_PROVIDER;
+
+if (
+  provider === 'azure' &&
+  !apiKey &&
+  !apiEndpoint &&
+  command !== 'config' &&
+  mode !== CONFIG_MODES.set
+) {
+  intro('opencommit');
+
+  outro(
+    'OCO_AZURE_API_KEY or OCO_AZURE_ENDPOINT are not set, please run `oco config set OCO_AZURE_API_KEY=<your token> . If you are using GPT, make sure you add payment details, so API works.`'
+  );
+  outro(
+    'For help look into README https://github.com/di-sukharev/opencommit#setup'
+  );
+
+  process.exit(1);
+}
+
+const MODEL = config?.OCO_MODEL || 'gpt-3.5-turbo';
+
+export class Azure implements AiEngine {
+  private openAI!: OpenAIClient;
+
+  constructor() {
+    if (provider === 'azure') {
+      this.openAI = new OpenAIClient(apiEndpoint, new AzureKeyCredential(apiKey));
+    }
+  }
+
+  public generateCommitMessage = async (
+    messages: Array<ChatCompletionRequestMessage>
+  ): Promise<string | undefined> => {
+    try {
+      const REQUEST_TOKENS = messages
+        .map((msg) => tokenCount(msg.content) + 4)
+        .reduce((a, b) => a + b, 0);
+
+      if (REQUEST_TOKENS > MAX_TOKENS_INPUT - MAX_TOKENS_OUTPUT) {
+        throw new Error(GenerateCommitMessageErrorEnum.tooMuchTokens);
+      }
+
+      const data = await this.openAI.getChatCompletions(MODEL, messages);
+
+      const message = data.choices[0].message;
+
+      if (message?.content === null) {
+        return undefined;
+      }
+      return message?.content;
+    } catch (error) {
+      outro(`${chalk.red('✖')} ${MODEL}`);
+
+      const err = error as Error;
+      outro(`${chalk.red('✖')} ${err?.message || err}`);
+
+      if (
+        axios.isAxiosError<{ error?: { message: string } }>(error) &&
+        error.response?.status === 401
+      ) {
+        const openAiError = error.response.data.error;
+
+        if (openAiError?.message) outro(openAiError.message);
+        outro(
+          'For help look into README https://github.com/di-sukharev/opencommit#setup'
+        );
+      }
+
+      throw err;
+    }
+  };
+}
+
+export const azure = new Azure();
--- a/src/engine/flowise.ts
+++ b/src/engine/flowise.ts
@@ -0,0 +1,43 @@
+import axios, { AxiosError } from 'axios';
+import { ChatCompletionRequestMessage } from 'openai';
+import { AiEngine } from './Engine';
+
+import {
+  getConfig
+} from '../commands/config';
+
+const config = getConfig();
+
+export class FlowiseAi implements AiEngine {
+
+  async generateCommitMessage(
+    messages: Array<ChatCompletionRequestMessage>
+  ): Promise<string | undefined> {
+
+    const gitDiff = messages[ messages.length - 1 ]?.content?.replace(/\\/g, '\\\\')  
+                                                            .replace(/"/g, '\\"')    
+                                                            .replace(/\n/g, '\\n')   
+                                                            .replace(/\r/g, '\\r')   
+                                                            .replace(/\t/g, '\\t');  
+    const url = `http://${config?.OCO_FLOWISE_ENDPOINT}/api/v1/prediction/${config?.OCO_FLOWISE_API_KEY}`; 
+    const payload = {
+        question : gitDiff,
+        overrideConfig : {
+          systemMessagePrompt: messages[0]?.content,
+        },
+        history : messages.slice( 1, -1 ) 
+    }
+    try {
+      const response = await axios.post(url, payload, {
+        headers: {
+          'Content-Type': 'application/json'
+        }
+      });
+      const message = response.data;
+      return message?.text;
+    } catch (err: any) {
+      const message = err.response?.data?.error ?? err.message;
+      throw new Error('local model issues. details: ' + message);
+    }
+  }
+}
--- a/src/engine/gemini.ts
+++ b/src/engine/gemini.ts
@@ -0,0 +1,133 @@
+import { ChatCompletionRequestMessage } from 'openai';
+import { AiEngine } from './Engine';
+import { Content, GenerativeModel, GoogleGenerativeAI, HarmBlockThreshold, HarmCategory, Part } from '@google/generative-ai';
+import { CONFIG_MODES, ConfigType, DEFAULT_TOKEN_LIMITS, getConfig, MODEL_LIST } from '../commands/config';
+import { intro, outro } from '@clack/prompts';
+import chalk from 'chalk';
+import axios from 'axios';
+
+
+export class Gemini implements AiEngine {
+
+  private readonly config: ConfigType;
+  private readonly googleGenerativeAi: GoogleGenerativeAI;
+  private ai: GenerativeModel;
+
+  // vars 
+  private maxTokens = {
+    input: DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_INPUT,
+    output: DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_OUTPUT
+  };
+  private basePath: string;
+  private apiKey: string;
+  private model: string;
+
+  constructor() {
+    this.config = getConfig() as ConfigType;
+    this.googleGenerativeAi = new GoogleGenerativeAI(this.config.OCO_GEMINI_API_KEY);
+    
+    this.warmup();
+  }
+
+  async generateCommitMessage(messages: ChatCompletionRequestMessage[]): Promise<string | undefined> {
+    const systemInstruction = messages.filter(m => m.role === 'system')
+      .map(m => m.content)
+      .join('\n');
+    
+    this.ai = this.googleGenerativeAi.getGenerativeModel({
+      model: this.model,
+      systemInstruction,
+    });
+    
+    const contents = messages.filter(m => m.role !== 'system')
+      .map(m => ({ parts: [{ text: m.content } as Part], role: m.role == 'user' ? m.role : 'model', } as Content));
+      
+    try {
+      const result = await this.ai.generateContent({
+        contents, 
+        safetySettings: [
+          { 
+            category: HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, 
+            threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE, 
+          },
+          {
+            category: HarmCategory.HARM_CATEGORY_HARASSMENT, 
+            threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE
+          },
+          {
+            category: HarmCategory.HARM_CATEGORY_HATE_SPEECH, 
+            threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE
+          },
+          {
+            category: HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT, 
+            threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE
+          },
+        ],
+        generationConfig: {
+          maxOutputTokens: this.maxTokens.output,
+          temperature: 0,
+          topP: 0.1,
+        },
+      });
+      
+      return result.response.text();
+    } catch (error) {
+      const err = error as Error;
+      outro(`${chalk.red('✖')} ${err?.message || err}`);
+      
+      if (
+        axios.isAxiosError<{ error?: { message: string } }>(error) &&
+        error.response?.status === 401
+      ) {
+        const geminiError = error.response.data.error;
+
+        if (geminiError?.message) outro(geminiError.message);
+        outro(
+          'For help look into README https://github.com/di-sukharev/opencommit#setup'
+        );
+      }
+      
+      throw err;
+    }
+  }
+
+  private warmup(): void {
+    if (this.config.OCO_TOKENS_MAX_INPUT !== undefined) this.maxTokens.input = this.config.OCO_TOKENS_MAX_INPUT;
+    if (this.config.OCO_TOKENS_MAX_OUTPUT !== undefined) this.maxTokens.output = this.config.OCO_TOKENS_MAX_OUTPUT;
+    this.basePath = this.config.OCO_GEMINI_BASE_PATH;
+    this.apiKey = this.config.OCO_GEMINI_API_KEY;
+
+    const [command, mode] = process.argv.slice(2);
+
+    const provider = this.config.OCO_AI_PROVIDER;
+
+    if (provider === 'gemini' && !this.apiKey &&
+      command !== 'config' && mode !== 'set') {
+      intro('opencommit');
+
+      outro('OCO_GEMINI_API_KEY is not set, please run `oco config set OCO_GEMINI_API_KEY=<your token> . If you are using GPT, make sure you add payment details, so API works.');
+
+      outro(
+        'For help look into README https://github.com/di-sukharev/opencommit#setup'
+      );
+
+      process.exit(1);
+    }
+    
+    this.model = this.config.OCO_MODEL || MODEL_LIST.gemini[0];
+    
+    if (provider === 'gemini' &&
+      !MODEL_LIST.gemini.includes(this.model) &&
+      command !== 'config' &&
+      mode !== CONFIG_MODES.set) {
+      outro(
+        `${chalk.red('✖')} Unsupported model ${this.model} for Gemini. Supported models are: ${MODEL_LIST.gemini.join(
+          ', '
+        )}`
+      );
+
+      process.exit(1);
+    }
+  }
+
+}
--- a/src/engine/ollama.ts
+++ b/src/engine/ollama.ts
@@ -2,20 +2,36 @@ import axios, { AxiosError } from 'axios';
 import { ChatCompletionRequestMessage } from 'openai';
 import { AiEngine } from './Engine';

+import {
+  getConfig
+} from '../commands/config';
+
+const config = getConfig();
+
 export class OllamaAi implements AiEngine {
+  private model = "mistral"; // as default model of Ollama
+  private url = "http://localhost:11434/api/chat"; // default URL of Ollama API
+
+  setModel(model: string) {
+    this.model = model ?? config?.OCO_MODEL ?? 'mistral';
+  }
+  
+  setUrl(url: string) {
+    this.url = url ?? config?.OCO_OLLAMA_API_URL ?? 'http://localhost:11434/api/chat';
+  }
  async generateCommitMessage(
    messages: Array<ChatCompletionRequestMessage>
  ): Promise<string | undefined> {
-    const model = 'mistral'; // todo: allow other models
+    const model = this.model;

    //console.log(messages);
    //process.exit()

-    const url = 'http://localhost:11434/api/chat';
+    const url = this.url;
    const p = {
      model,
      messages,
-      options: {temperature: 0, top_p: 0.1},
+      options: { temperature: 0, top_p: 0.1 },
      stream: false
    };
    try {
@@ -34,5 +50,3 @@ export class OllamaAi implements AiEngine {
    }
  }
 }
-
-export const ollamaAi = new OllamaAi();
--- a/src/engine/openAi.ts
+++ b/src/engine/openAi.ts
@@ -54,19 +54,17 @@ if (

 const MODEL = config?.OCO_MODEL || 'gpt-3.5-turbo';
 if (provider === 'openai' &&
-    !MODEL_LIST.openai.includes(MODEL) &&
+  typeof MODEL !== 'string' && 
    command !== 'config' &&
    mode !== CONFIG_MODES.set) {
  outro(
-    `${chalk.red('✖')} Unsupported model ${MODEL} for OpenAI. Supported models are: ${MODEL_LIST.openai.join(
-      ', '
-    )}`
+    `${chalk.red('✖')} Unsupported model ${MODEL}. The model can be any string, but the current configuration is not supported.`
  );
-
  process.exit(1);
 }

-class OpenAi implements AiEngine {
+export class OpenAi implements AiEngine {
+  
  private openAiApiConfiguration = new OpenAiApiConfiguration({
    apiKey: apiKey
  });
@@ -91,7 +89,7 @@ class OpenAi implements AiEngine {
    };
    try {
      const REQUEST_TOKENS = messages
-        .map((msg) => tokenCount(msg.content) + 4)
+        .map((msg) => tokenCount(msg.content as string) + 4)
        .reduce((a, b) => a + b, 0);

      if (REQUEST_TOKENS > MAX_TOKENS_INPUT - MAX_TOKENS_OUTPUT) {
@@ -124,6 +122,6 @@ class OpenAi implements AiEngine {
      throw err;
    }
  };
+  
 }

-export const api = new OpenAi();
--- a/src/engine/testAi.ts
+++ b/src/engine/testAi.ts
@@ -1,12 +1,31 @@
 import { ChatCompletionRequestMessage } from 'openai';
 import { AiEngine } from './Engine';
+import { getConfig } from '../commands/config';
+
+export const TEST_MOCK_TYPES = [
+  'commit-message',
+  'prompt-module-commitlint-config',
+] as const
+type TestMockType = typeof TEST_MOCK_TYPES[number];

 export class TestAi implements AiEngine {
  async generateCommitMessage(
-    messages: Array<ChatCompletionRequestMessage>
+    _messages: Array<ChatCompletionRequestMessage>
  ): Promise<string | undefined> {
-    return 'test commit message';
+    const config = getConfig();
+    switch (config?.OCO_TEST_MOCK_TYPE as TestMockType | undefined) {
+      case 'commit-message':
+        return 'fix(testAi.ts): test commit message';
+      case 'prompt-module-commitlint-config':
+        return `{\n` +
+          `  "localLanguage": "english",\n` +
+          `  "commitFix": "fix(server): Change 'port' variable to uppercase 'PORT'",\n` +
+          `  "commitFeat": "feat(server): Allow server to listen on a port specified through environment variable",\n` +
+          `  "commitDescription": "Change 'port' variable to uppercase 'PORT'. Allow server to listen on a port specified through environment variable."\n` +
+          `}`
+      default:
+        throw Error('unsupported test mock type')
+    }
  }
 }

-export const testAi = new TestAi();
--- a/src/generateCommitMessageFromGitDiff.ts
+++ b/src/generateCommitMessageFromGitDiff.ts
@@ -10,8 +10,11 @@ import { tokenCount } from './utils/tokenCount';
 import { getEngine } from './utils/engine';

 const config = getConfig();
-const MAX_TOKENS_INPUT = config?.OCO_TOKENS_MAX_INPUT || DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_INPUT;
-const MAX_TOKENS_OUTPUT = config?.OCO_TOKENS_MAX_OUTPUT || DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_OUTPUT;
+const MAX_TOKENS_INPUT =
+  config?.OCO_TOKENS_MAX_INPUT || DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_INPUT;
+const MAX_TOKENS_OUTPUT =
+  config?.OCO_TOKENS_MAX_OUTPUT ||
+  DEFAULT_TOKEN_LIMITS.DEFAULT_MAX_TOKENS_OUTPUT;

 const generateCommitMessageChatCompletionPrompt = async (
  diff: string,
@@ -46,7 +49,7 @@ export const generateCommitMessageByDiff = async (
    const INIT_MESSAGES_PROMPT = await getMainCommitPrompt(fullGitMojiSpec);

    const INIT_MESSAGES_PROMPT_LENGTH = INIT_MESSAGES_PROMPT.map(
-      (msg) => tokenCount(msg.content) + 4
+      (msg) => tokenCount(msg.content as string) + 4
    ).reduce((a, b) => a + b, 0);

    const MAX_REQUEST_TOKENS =
@@ -62,18 +65,21 @@ export const generateCommitMessageByDiff = async (
        fullGitMojiSpec
      );

-      const commitMessages = [];
+      const commitMessages = [] as string[];
      for (const promise of commitMessagePromises) {
-        commitMessages.push(await promise);
+        commitMessages.push((await promise) as string);
        await delay(2000);
      }

      return commitMessages.join('\n\n');
    }

-    const messages = await generateCommitMessageChatCompletionPrompt(diff, fullGitMojiSpec);
+    const messages = await generateCommitMessageChatCompletionPrompt(
+      diff,
+      fullGitMojiSpec
+    );

-    const engine = getEngine()
+    const engine = getEngine();
    const commitMessage = await engine.generateCommitMessage(messages);

    if (!commitMessage)
@@ -100,7 +106,7 @@ function getMessagesPromisesByChangesInFile(
    maxChangeLength
  );

-  const lineDiffsWithHeader = [];
+  const lineDiffsWithHeader = [] as string[];
  for (const change of mergedChanges) {
    const totalChange = fileHeader + change;
    if (tokenCount(totalChange) > maxChangeLength) {
@@ -112,7 +118,7 @@ function getMessagesPromisesByChangesInFile(
    }
  }

-  const engine = getEngine()
+  const engine = getEngine();
  const commitMsgsFromFileLineDiffs = lineDiffsWithHeader.map(
    async (lineDiff) => {
      const messages = await generateCommitMessageChatCompletionPrompt(
@@ -129,7 +135,7 @@ function getMessagesPromisesByChangesInFile(

 function splitDiff(diff: string, maxChangeLength: number) {
  const lines = diff.split('\n');
-  const splitDiffs = [];
+  const splitDiffs = [] as string[];
  let currentDiff = '';

  if (maxChangeLength <= 0) {
@@ -175,7 +181,7 @@ export const getCommitMsgsPromisesFromFileDiffs = async (
  // merge multiple files-diffs into 1 prompt to save tokens
  const mergedFilesDiffs = mergeDiffs(diffByFiles, maxDiffLength);

-  const commitMessagePromises = [];
+  const commitMessagePromises = [] as Promise<string | undefined>[];

  for (const fileDiff of mergedFilesDiffs) {
    if (tokenCount(fileDiff) >= maxDiffLength) {
@@ -194,7 +200,7 @@ export const getCommitMsgsPromisesFromFileDiffs = async (
        fullGitMojiSpec
      );

-      const engine = getEngine()
+      const engine = getEngine();
      commitMessagePromises.push(engine.generateCommitMessage(messages));
    }
  }
--- a/src/i18n/zh_CN.json
+++ b/src/i18n/zh_CN.json
@@ -1,6 +1,6 @@
 {
  "localLanguage": "简体中文",
-  "commitFix": "修复(server.ts)：将端口变量从小写port改为大写PORT",
-  "commitFeat": "功能(server.ts)：添加对process.env.PORT环境变量的支持",
+  "commitFix": "fix(server.ts)：将端口变量从小写port改为大写PORT",
+  "commitFeat": "feat(server.ts)：添加对process.env.PORT环境变量的支持",
  "commitDescription": "现在端口变量被命名为PORT，这提高了命名约定的一致性，因为PORT是一个常量。环境变量的支持使应用程序更加灵活，因为它现在可以通过process.env.PORT环境变量在任何可用端口上运行。"
 }
--- a/src/modules/commitlint/config.ts
+++ b/src/modules/commitlint/config.ts
@@ -19,7 +19,16 @@ export const configureCommitlintIntegration = async (force = false) => {

  const fileExists = await utils.commitlintLLMConfigExists();

-  let commitLintConfig = await getCommitLintPWDConfig();
+  const commitLintConfig = await getCommitLintPWDConfig();
+  if (commitLintConfig === null) {
+    throw new Error(
+      `Failed to load @commitlint config. Please check the following:
+      * @commitlint >= 9.0.0 is installed in the local directory.
+      * 'node_modules/@commitlint/load' package exists.
+      * A valid @commitlint configuration exists.
+      `,
+    );
+  }

  // debug complete @commitlint configuration
  // await fs.writeFile(
@@ -55,7 +64,7 @@ export const configureCommitlintIntegration = async (force = false) => {
  //   consistencyPrompts.map((p) => p.content)
  // );

-  const engine = getEngine()
+  const engine = getEngine();
  let consistency =
    (await engine.generateCommitMessage(consistencyPrompts)) || '{}';

@@ -64,7 +73,7 @@ export const configureCommitlintIntegration = async (force = false) => {

  // sometimes consistency is preceded by explanatory text like "Here is your JSON:"
  consistency = utils.getJSONBlock(consistency);
-  
+
  // ... remaining might be extra set of "\n"
  consistency = utils.removeDoubleNewlines(consistency);

--- a/src/modules/commitlint/pwd-commitlint.ts
+++ b/src/modules/commitlint/pwd-commitlint.ts
@@ -1,11 +1,25 @@
+import fs from 'fs/promises';
 import path from 'path';

-const nodeModulesPath = path.join(
-  process.env.PWD || process.cwd(),
-  'node_modules',
-  '@commitlint',
-  'load'
-);
+const getCommitLintModuleType = async (): Promise<'cjs' | 'esm'> => {
+  const packageFile = 'node_modules/@commitlint/load/package.json';
+  const packageJsonPath = path.join(
+    process.env.PWD || process.cwd(),
+    packageFile,
+  );
+  const packageJson = JSON.parse(await fs.readFile(packageJsonPath, 'utf8'));
+  if (!packageJson) {
+    throw new Error(`Failed to parse ${packageFile}`);
+  }
+
+  return packageJson.type === 'module' ? 'esm' : 'cjs';
+};
+
+/**
+ * QualifiedConfig from any version of @commitlint/types
+ * @see https://github.com/conventional-changelog/commitlint/blob/master/@commitlint/types/src/load.ts
+ */
+type QualifiedConfigOnAnyVersion = { [key:string]: unknown };

 /**
 *  This code is loading the configuration for the `@commitlint` package from the current working
@@ -13,8 +27,31 @@ const nodeModulesPath = path.join(
 *
 * @returns
 */
-export const getCommitLintPWDConfig = async () => {
-  const load = require(nodeModulesPath).default;
+export const getCommitLintPWDConfig = async (): Promise<QualifiedConfigOnAnyVersion | null> => {
+  let load, nodeModulesPath;
+  switch (await getCommitLintModuleType()) {
+    case 'cjs':
+      /**
+       * CommonJS (<= commitlint@v18.x.x.)
+       */
+      nodeModulesPath = path.join(
+        process.env.PWD || process.cwd(),
+        'node_modules/@commitlint/load',
+      );
+      load = require(nodeModulesPath).default;
+      break;
+    case 'esm':
+      /**
+       * ES Module (commitlint@v19.x.x. <= )
+       * Directory import is not supported in ES Module resolution, so import the file directly
+       */
+      nodeModulesPath = path.join(
+        process.env.PWD || process.cwd(),
+        'node_modules/@commitlint/load/lib/load.js',
+      );
+      load = (await import(nodeModulesPath)).default;
+      break;
+  }

  if (load && typeof load === 'function') {
    return await load();
--- a/src/modules/commitlint/utils.ts
+++ b/src/modules/commitlint/utils.ts
@@ -18,14 +18,14 @@ export const removeDoubleNewlines = (input: string): string => {

 export const getJSONBlock = (input: string): string => {
  const jsonIndex = input.search('```json');
-  if(jsonIndex > -1) {
+  if (jsonIndex > -1) {
    input = input.slice(jsonIndex + 8);
-    const endJsonIndex = consistency.search('```');
+    const endJsonIndex = input.search('```');
    input = input.slice(0, endJsonIndex); 
  }
  return input;
 };
-  
+
 export const commitlintLLMConfigExists = async (): Promise<boolean> => {
  let exists;
  try {
@@ -54,4 +54,4 @@ export const getCommitlintLLMConfig =
      content.toString()
    ) as CommitlintLLMConfig;
    return commitLintLLMConfig;
-};
+  };
--- a/src/prompts.ts
+++ b/src/prompts.ts
@@ -118,7 +118,7 @@ const INIT_MAIN_PROMPT = (
    ${
      config?.OCO_ONE_LINE_COMMIT
        ? 'Craft a concise commit message that encapsulates all changes made, with an emphasis on the primary updates. If the modifications share a common theme or scope, mention it succinctly; otherwise, leave the scope out to maintain focus. The goal is to provide a clear and unified overview of the changes in a one single message, without diverging into a list of commit per file change.'
-        : ""
+        : ''
    }
    Use the present tense. Lines must not be longer than 74 characters. Use ${language} for the commit message.`
 });
--- a/src/utils/engine.ts
+++ b/src/utils/engine.ts
@@ -1,19 +1,37 @@
 import { AiEngine } from '../engine/Engine';
-import { api } from '../engine/openAi';
+import { OpenAi } from '../engine/openAi';
+import { Gemini } from '../engine/gemini';
 import { getConfig } from '../commands/config';
-import { ollamaAi } from '../engine/ollama';
-import { anthropicAi } from '../engine/anthropic'
-import { testAi } from '../engine/testAi';
+import { OllamaAi } from '../engine/ollama';
+import { AnthropicAi } from '../engine/anthropic'
+import { TestAi } from '../engine/testAi';
+import { Azure } from '../engine/azure';
+import { FlowiseAi } from '../engine/flowise'

 export function getEngine(): AiEngine {
  const config = getConfig();
-  if (config?.OCO_AI_PROVIDER == 'ollama') {
+  const provider = config?.OCO_AI_PROVIDER;
+  
+  if (provider?.startsWith('ollama')) {
+    const ollamaAi = new OllamaAi();
+    const model = provider.substring('ollama/'.length);
+    if (model) {
+      ollamaAi.setModel(model);
+      ollamaAi.setUrl(config?.OCO_OLLAMA_API_URL);
+    }
    return ollamaAi;
-  } else if (config?.OCO_AI_PROVIDER == 'anthropic') {
-    return anthropicAi;
-  } else if (config?.OCO_AI_PROVIDER == 'test') {
-    return testAi;
+  } else if (provider == 'anthropic') {
+    return new AnthropicAi();
+  } else if (provider == 'test') {
+    return new TestAi();
+  } else if (provider == 'gemini') {
+    return new Gemini();  
+  } else if (provider == 'azure') {
+  	return new Azure();
+  } else if( provider == 'flowise'){
+    return new FlowiseAi();
  }
+  
  //open ai gpt by default
-  return api;
+  return new OpenAi();
 }
--- a/src/version.ts
+++ b/src/version.ts
@@ -1,5 +1,5 @@
-import { outro } from "@clack/prompts";
-import { execa } from "execa";
+import { outro } from '@clack/prompts';
+import { execa } from 'execa';

 export const getOpenCommitLatestVersion = async (): Promise<
  string | undefined
@@ -11,4 +11,4 @@ export const getOpenCommitLatestVersion = async (): Promise<
    outro('Error while getting the latest version of opencommit');
    return undefined;
  }
-};
+};
--- a/test/Dockerfile
+++ b/test/Dockerfile
@@ -10,10 +10,13 @@ RUN apt-get install -y nodejs
 RUN git config --global user.email "test@example.com"
 RUN git config --global user.name "Test User"

-COPY . /app
 WORKDIR /app
+COPY package.json /app/
+COPY package-lock.json /app/

 RUN ls -la

-RUN npm install
+RUN npm ci
+COPY . /app
+RUN ls -la
 RUN npm run build
--- a/test/e2e/noChanges.test.ts
+++ b/test/e2e/noChanges.test.ts
@@ -5,7 +5,6 @@ import { prepareEnvironment } from './utils';

 it('cli flow when there are no changes', async () => {
  const { gitDir, cleanup } = await prepareEnvironment();
-
  const { findByText } = await render(`OCO_AI_PROVIDER='test' node`, [resolve('./out/cli.cjs')], { cwd: gitDir });
  expect(await findByText('No changes detected')).toBeInTheConsole();

--- a/test/e2e/oneFile.test.ts
+++ b/test/e2e/oneFile.test.ts
@@ -10,7 +10,6 @@ it('cli flow to generate commit message for 1 new file (staged)', async () => {
  await render('git' ,['add index.ts'], { cwd: gitDir });

  const { queryByText, findByText, userEvent } = await render(`OCO_AI_PROVIDER='test' node`, [resolve('./out/cli.cjs')], { cwd: gitDir });
-
  expect(await queryByText('No files are staged')).not.toBeInTheConsole();
  expect(await queryByText('Do you want to stage all files and generate commit message?')).not.toBeInTheConsole();

--- a/test/e2e/prompt-module/commitlint.test.ts
+++ b/test/e2e/prompt-module/commitlint.test.ts
@@ -0,0 +1,224 @@
+import { resolve } from 'path';
+import { render } from 'cli-testing-library';
+import 'cli-testing-library/extend-expect';
+import { prepareEnvironment, wait } from '../utils';
+import path from 'path';
+
+function getAbsolutePath(relativePath: string) {
+  const scriptDir = path.dirname(__filename);
+  return path.resolve(scriptDir, relativePath);
+}
+async function setupCommitlint(dir: string, ver: 9 | 18 | 19) {
+  let packagePath, packageJsonPath, configPath;
+  switch (ver) {
+    case 9:
+      packagePath = getAbsolutePath('./data/commitlint_9/node_modules');
+      packageJsonPath = getAbsolutePath('./data/commitlint_9/package.json');
+      configPath = getAbsolutePath('./data/commitlint_9/commitlint.config.js');
+      break;
+    case 18:
+      packagePath = getAbsolutePath('./data/commitlint_18/node_modules');
+      packageJsonPath = getAbsolutePath('./data/commitlint_18/package.json');
+      configPath = getAbsolutePath('./data/commitlint_18/commitlint.config.js');
+      break;
+    case 19:
+      packagePath = getAbsolutePath('./data/commitlint_19/node_modules');
+      packageJsonPath = getAbsolutePath('./data/commitlint_19/package.json');
+      configPath = getAbsolutePath('./data/commitlint_19/commitlint.config.js');
+      break;
+  }
+  await render('cp', ['-r', packagePath, '.'], { cwd: dir });
+  await render('cp', [packageJsonPath, '.'], { cwd: dir });
+  await render('cp', [configPath, '.'], { cwd: dir });
+  await wait(3000); // Avoid flakiness by waiting
+}
+
+describe('cli flow to run "oco commitlint force"', () => {
+  it('on commitlint@9 using CJS', async () => {
+    const { gitDir, cleanup } = await prepareEnvironment();
+
+    await setupCommitlint(gitDir, 9);
+    const npmList = await render('npm', ['list', '@commitlint/load'], {
+      cwd: gitDir
+    });
+    expect(await npmList.findByText('@commitlint/load@9')).toBeInTheConsole();
+
+    const { findByText } = await render(
+      `
+      OCO_TEST_MOCK_TYPE='prompt-module-commitlint-config' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test'  \
+      node ${resolve('./out/cli.cjs')} commitlint force \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+
+    expect(
+      await findByText('opencommit — configure @commitlint')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Read @commitlint configuration')
+    ).toBeInTheConsole();
+
+    expect(
+      await findByText('Generating consistency with given @commitlint rules')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Done - please review contents of')
+    ).toBeInTheConsole();
+
+    await cleanup();
+  });
+  it('on commitlint@18 using CJS', async () => {
+    const { gitDir, cleanup } = await prepareEnvironment();
+
+    await setupCommitlint(gitDir, 18);
+    const npmList = await render('npm', ['list', '@commitlint/load'], {
+      cwd: gitDir
+    });
+    expect(await npmList.findByText('@commitlint/load@18')).toBeInTheConsole();
+
+    const { findByText } = await render(
+      `
+      OCO_TEST_MOCK_TYPE='prompt-module-commitlint-config' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test'  \
+      node ${resolve('./out/cli.cjs')} commitlint force \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+
+    expect(
+      await findByText('opencommit — configure @commitlint')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Read @commitlint configuration')
+    ).toBeInTheConsole();
+
+    expect(
+      await findByText('Generating consistency with given @commitlint rules')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Done - please review contents of')
+    ).toBeInTheConsole();
+
+    await cleanup();
+  });
+  it('on commitlint@19 using ESM', async () => {
+    const { gitDir, cleanup } = await prepareEnvironment();
+
+    await setupCommitlint(gitDir, 19);
+    const npmList = await render('npm', ['list', '@commitlint/load'], {
+      cwd: gitDir
+    });
+    expect(await npmList.findByText('@commitlint/load@19')).toBeInTheConsole();
+
+    const { findByText } = await render(
+      `
+      OCO_TEST_MOCK_TYPE='prompt-module-commitlint-config' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test'  \
+      node ${resolve('./out/cli.cjs')} commitlint force \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+
+    expect(
+      await findByText('opencommit — configure @commitlint')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Read @commitlint configuration')
+    ).toBeInTheConsole();
+
+    expect(
+      await findByText('Generating consistency with given @commitlint rules')
+    ).toBeInTheConsole();
+    expect(
+      await findByText('Done - please review contents of')
+    ).toBeInTheConsole();
+
+    await cleanup();
+  });
+});
+
+describe('cli flow to generate commit message using @commitlint prompt-module', () => {
+  it('on commitlint@19 using ESM', async () => {
+    const { gitDir, cleanup } = await prepareEnvironment();
+
+    // Setup commitlint@19
+    await setupCommitlint(gitDir, 19);
+    const npmList = await render('npm', ['list', '@commitlint/load'], {
+      cwd: gitDir
+    });
+    expect(await npmList.findByText('@commitlint/load@19')).toBeInTheConsole();
+
+    // Run `oco commitlint force`
+    const commitlintForce = await render(
+      `
+      OCO_TEST_MOCK_TYPE='prompt-module-commitlint-config' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test'  \
+      node ${resolve('./out/cli.cjs')} commitlint force \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+    expect(
+      await commitlintForce.findByText('Done - please review contents of')
+    ).toBeInTheConsole();
+
+    // Run `oco commitlint get`
+    const commitlintGet = await render(
+      `
+      OCO_TEST_MOCK_TYPE='prompt-module-commitlint-config' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test'  \
+      node ${resolve('./out/cli.cjs')} commitlint get \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+    expect(
+      await commitlintGet.findByText('[object Object]')
+    ).toBeInTheConsole();
+
+    // Run 'oco' using .opencommit-commitlint
+    await render('echo', [`'console.log("Hello World");' > index.ts`], {
+      cwd: gitDir
+    });
+    await render('git', ['add index.ts'], { cwd: gitDir });
+
+    const oco = await render(
+      `
+      OCO_TEST_MOCK_TYPE='commit-message' \
+      OCO_PROMPT_MODULE='@commitlint'  \
+      OCO_AI_PROVIDER='test' \
+      node ${resolve('./out/cli.cjs')} \
+    `,
+      [],
+      { cwd: gitDir }
+    );
+
+    expect(
+      await oco.findByText('Generating the commit message')
+    ).toBeInTheConsole();
+    expect(
+      await oco.findByText('Confirm the commit message?')
+    ).toBeInTheConsole();
+    oco.userEvent.keyboard('[Enter]');
+
+    expect(
+      await oco.findByText('Choose a remote to push to')
+    ).toBeInTheConsole();
+    oco.userEvent.keyboard('[Enter]');
+
+    expect(
+      await oco.findByText('Successfully pushed all commits to origin')
+    ).toBeInTheConsole();
+
+    await cleanup();
+  });
+});
--- a/test/e2e/prompt-module/data/commitlint_18/commitlint.config.js
+++ b/test/e2e/prompt-module/data/commitlint_18/commitlint.config.js
@@ -0,0 +1,3 @@
+module.exports = {
+  extends: ['@commitlint/config-conventional']
+};
--- a/test/e2e/prompt-module/data/commitlint_18/package-lock.json
+++ b/test/e2e/prompt-module/data/commitlint_18/package-lock.json
--- a/test/e2e/prompt-module/data/commitlint_18/package.json
+++ b/test/e2e/prompt-module/data/commitlint_18/package.json
@@ -0,0 +1,15 @@
+{
+  "name": "commitlint-test",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "",
+  "license": "ISC",
+  "devDependencies": {
+    "@commitlint/cli": "^18.0.0",
+    "@commitlint/config-conventional": "^18.0.0"
+  }
+}
--- a/test/e2e/prompt-module/data/commitlint_19/commitlint.config.js
+++ b/test/e2e/prompt-module/data/commitlint_19/commitlint.config.js
@@ -0,0 +1,3 @@
+export default {
+  extends: ['@commitlint/config-conventional']
+};
--- a/test/e2e/prompt-module/data/commitlint_19/package-lock.json
+++ b/test/e2e/prompt-module/data/commitlint_19/package-lock.json
--- a/test/e2e/prompt-module/data/commitlint_19/package.json
+++ b/test/e2e/prompt-module/data/commitlint_19/package.json
@@ -0,0 +1,16 @@
+{
+  "name": "commitlint-test",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "type": "module",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "",
+  "license": "ISC",
+  "devDependencies": {
+    "@commitlint/cli": "^19.0.0",
+    "@commitlint/config-conventional": "^19.0.0"
+  }
+}
--- a/test/e2e/prompt-module/data/commitlint_9/commitlint.config.js
+++ b/test/e2e/prompt-module/data/commitlint_9/commitlint.config.js
@@ -0,0 +1,3 @@
+module.exports = {
+  extends: ['@commitlint/config-conventional']
+};
--- a/test/e2e/prompt-module/data/commitlint_9/package-lock.json
+++ b/test/e2e/prompt-module/data/commitlint_9/package-lock.json
--- a/test/e2e/prompt-module/data/commitlint_9/package.json
+++ b/test/e2e/prompt-module/data/commitlint_9/package.json
@@ -0,0 +1,15 @@
+{
+  "name": "commitlint-test",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "",
+  "license": "ISC",
+  "devDependencies": {
+    "@commitlint/cli": "^9.0.0",
+    "@commitlint/config-conventional": "^9.0.0"
+  }
+}
--- a/test/e2e/setup.sh
+++ b/test/e2e/setup.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+current_dir=$(pwd)
+setup_dir="$(cd "$(dirname "$0")" && pwd)"
+
+# Set up for prompt-module/commitlint
+cd $setup_dir && cd prompt-module/data/commitlint_9 && npm ci
+cd $setup_dir && cd prompt-module/data/commitlint_18 && npm ci
+cd $setup_dir && cd prompt-module/data/commitlint_19 && npm ci
+
+cd $current_dir
--- a/test/e2e/utils.ts
+++ b/test/e2e/utils.ts
@@ -29,3 +29,5 @@ export const prepareEnvironment = async (): Promise<{
    cleanup,
  }
 }
+
+export const wait = (ms: number) => new Promise(resolve => setTimeout(resolve, ms));
--- a/test/jest-setup.ts
+++ b/test/jest-setup.ts
@@ -1,5 +1,8 @@
 import 'cli-testing-library/extend-expect'
 import { configure } from 'cli-testing-library'
+import { jest } from '@jest/globals';
+
+global.jest = jest;

 /**
 * Adjusted the wait time for waitFor/findByText to 2000ms, because the default 1000ms makes the test results flaky
--- a/test/unit/config.test.ts
+++ b/test/unit/config.test.ts
@@ -55,7 +55,7 @@ OCO_ONE_LINE_COMMIT="true"
    expect(config!['OCO_LANGUAGE']).toEqual('de');
    expect(config!['OCO_MESSAGE_TEMPLATE_PLACEHOLDER']).toEqual('$m');
    expect(config!['OCO_PROMPT_MODULE']).toEqual('@commitlint');
-    expect(config!['OCO_AI_PROVIDER']).toEqual('ollama');
+    expect(() => ['ollama', 'gemini'].includes(config!['OCO_AI_PROVIDER'])).toBeTruthy();
    expect(config!['OCO_GITPUSH']).toEqual(false);
    expect(config!['OCO_ONE_LINE_COMMIT']).toEqual(true);

@@ -96,10 +96,10 @@ OCO_ONE_LINE_COMMIT="true"
    expect(config!['OCO_LANGUAGE']).toEqual('de');
    expect(config!['OCO_MESSAGE_TEMPLATE_PLACEHOLDER']).toEqual('$m');
    expect(config!['OCO_PROMPT_MODULE']).toEqual('@commitlint');
-    expect(config!['OCO_AI_PROVIDER']).toEqual('ollama');
+    expect(() => ['ollama', 'gemini'].includes(config!['OCO_AI_PROVIDER'])).toBeTruthy();
    expect(config!['OCO_GITPUSH']).toEqual(false);
    expect(config!['OCO_ONE_LINE_COMMIT']).toEqual(true);

    await envFile.cleanup();
  });
-});
+});
--- a/test/unit/gemini.test.ts
+++ b/test/unit/gemini.test.ts
@@ -0,0 +1,105 @@
+import { Gemini } from '../../src/engine/gemini';
+import { ChatCompletionRequestMessage } from 'openai';
+import { GenerativeModel, GoogleGenerativeAI } from '@google/generative-ai';
+import { ConfigType, getConfig } from '../../src/commands/config';
+
+describe('Gemini', () => {
+  let gemini: Gemini;
+  let mockConfig: ConfigType;
+  let mockGoogleGenerativeAi: GoogleGenerativeAI;
+  let mockGenerativeModel: GenerativeModel;
+  let mockExit: jest.SpyInstance<never, [code?: number | undefined], any>;
+  let mockWarmup: jest.SpyInstance<any, unknown[], any>;
+  
+  const noop: (code?: number | undefined) => never = (code?: number | undefined) => {};
+  
+  const mockGemini = () => {
+    gemini = new Gemini();
+  }
+  
+  const oldEnv = process.env;
+
+  beforeEach(() => {
+    jest.resetModules();
+    process.env = { ...oldEnv };
+    
+    jest.mock('@google/generative-ai');
+    jest.mock('../src/commands/config');
+    
+    jest.mock('@clack/prompts', () => ({
+      intro: jest.fn(),
+      outro: jest.fn(),
+    }));
+    
+    if (mockWarmup) mockWarmup.mockRestore();
+    
+    mockExit = jest.spyOn(process, 'exit').mockImplementation();
+    mockConfig = getConfig() as ConfigType;
+    
+    mockConfig.OCO_AI_PROVIDER = 'gemini';
+    mockConfig.OCO_GEMINI_API_KEY = 'mock-api-key';
+    mockConfig.OCO_MODEL = 'gemini-1.5-flash';
+    
+    mockGoogleGenerativeAi = new GoogleGenerativeAI(mockConfig.OCO_GEMINI_API_KEY);    
+    mockGenerativeModel = mockGoogleGenerativeAi.getGenerativeModel({ model: mockConfig.OCO_MODEL, });
+  });
+  
+  afterEach(() => {
+    gemini = undefined as any;
+  })
+  
+  afterAll(() => {
+    mockExit.mockRestore();
+    process.env = oldEnv;
+  });
+
+  it('should initialize with correct config', () => {
+    mockGemini();
+    // gemini = new Gemini();
+    expect(gemini).toBeDefined();
+  });
+
+  it('should warmup correctly', () => {
+    mockWarmup = jest.spyOn(Gemini.prototype as any, 'warmup').mockImplementation(noop);
+    mockGemini();
+    expect(gemini).toBeDefined();
+  });
+
+  it('should exit process if OCO_GEMINI_API_KEY is not set and command is not config', () => {
+    process.env.OCO_GEMINI_API_KEY = undefined;
+    process.env.OCO_AI_PROVIDER = 'gemini';
+    
+    mockGemini();
+    
+    expect(mockExit).toHaveBeenCalledWith(1);
+  });
+
+  it('should exit process if model is not supported and command is not config', () => {
+    process.env.OCO_GEMINI_API_KEY = undefined;
+    process.env.OCO_AI_PROVIDER = 'gemini';
+
+    mockGemini();
+
+    expect(mockExit).toHaveBeenCalledWith(1);
+  });
+  
+  it('should generate commit message', async () => {
+    const mockGenerateContent = jest.fn().mockResolvedValue({ response: { text: () => 'generated content' } });
+    mockGenerativeModel.generateContent = mockGenerateContent;
+    
+    mockWarmup = jest.spyOn(Gemini.prototype as any, 'warmup').mockImplementation(noop);
+    mockGemini();
+    
+    const messages: ChatCompletionRequestMessage[] = [
+      { role: 'system', content: 'system message' },
+      { role: 'assistant', content: 'assistant message' },
+    ];
+    
+    jest.spyOn(gemini, 'generateCommitMessage').mockImplementation(async () => 'generated content');
+    const result = await gemini.generateCommitMessage(messages);
+
+    expect(result).toEqual('generated content');
+    expect(mockWarmup).toHaveBeenCalled();
+  });
+  
+});
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -1,12 +1,12 @@
 {
  "compilerOptions": {
-    "target": "ESNext",
-    "lib": ["ES5", "ES6"],
+    "target": "ES2020",
+    "lib": ["ES6", "ES2020"],

-    "module": "ESNext",
-    // "rootDir": "./src",
+    "module": "CommonJS",
+    
    "resolveJsonModule": true,
-    "moduleResolution": "node",
+    "moduleResolution": "Node",

    "allowJs": true,