Add Llama support to Inference Plugin #130092

Jan-Kazlouski-elastic · 2025-06-26T10:37:26Z

Creation of new Llama inference provider integration allowing text_embedding, completion (both streaming and non-streaming) and chat_completion (only streaming) to be executed as part of inference API.

Changes were tested locally against next models:

all-MiniLM-L6-v2 (text embedding)
llama3.2:3b (completion & chat_completion)

For testing ollama service was used.
Quickstart for setting up running llama service locally: https://llama-stack.readthedocs.io/en/latest/getting_started/index.html

Setup

Install uv

curl -LsSf https://astral.sh/uv/install.sh | sh

Download and execute ollama

https://ollama.com/download

Clone the llama stack repo: git clone git@github.com:meta-llama/llama-stack.git, then follow the detailed instructions in the docs above.

Running `all-minilm:l6-v2`

Download the model:

ollama pull all-minilm:l6-v2

INFERENCE_MODEL=all-minilm:l6-v2 uv run --with llama-stack llama stack build --template starter --image-type venv --run

Examples of RQ/RS from local testing:

Create Embedding Endpoint

No URL:

RQ:
PUT {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "service": "llama",
    "service_settings": {
        "api_key": "{{mistral-api-key}}",
        "model_id": "all-MiniLM-L6-v2"
    }
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "validation_exception",
                "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
            }
        ],
        "type": "validation_exception",
        "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
    },
    "status": 400
}

No API key (success):

RQ:
PUT {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/inference/embeddings",
        "model_id": "all-MiniLM-L6-v2"
    }
}
RS:
{
    "inference_id": "llama-text-embedding",
    "task_type": "text_embedding",
    "service": "llama",
    "service_settings": {
        "model_id": "all-MiniLM-L6-v2",
        "url": "http://localhost:8321/v1/inference/embeddings",
        "dimensions": 384,
        "similarity": "cosine",
        "rate_limit": {
            "requests_per_minute": 3000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}

Not Found:

RQ:
PUT {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/inference/embeddings1",
        "api_key": "{{mistral-api-key}}",
        "model_id": "all-MiniLM-L6-v2"
    }
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "status_exception",
                "reason": "Resource not found at [http://localhost:8321/v1/inference/embeddings1] for request from inference entity id [llama-text-embedding] status [404]. Error message: [{\"detail\":\"Not Found\"}]"
            }
        ],
        "type": "status_exception",
        "reason": "Could not complete inference endpoint creation as validation call to service threw an exception.",
        "caused_by": {
            "type": "status_exception",
            "reason": "Resource not found at [http://localhost:8321/v1/inference/embeddings1] for request from inference entity id [llama-text-embedding] status [404]. Error message: [{\"detail\":\"Not Found\"}]"
        }
    },
    "status": 400
}

Success:

RQ:
PUT {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/inference/embeddings",
        "api_key": "{{mistral-api-key}}",
        "model_id": "all-MiniLM-L6-v2"
    }
}
RS:
{
    "inference_id": "llama-text-embedding",
    "task_type": "text_embedding",
    "service": "llama",
    "service_settings": {
        "model_id": "all-MiniLM-L6-v2",
        "url": "http://localhost:8321/v1/inference/embeddings",
        "dimensions": 384,
        "similarity": "cosine",
        "rate_limit": {
            "requests_per_minute": 3000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}

Perform Embedding

Bad Request:

RQ:
POST {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "query": "string",
    "task_settings": {}
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "action_request_validation_exception",
                "reason": "Validation Failed: 1: Field [input] cannot be null;"
            }
        ],
        "type": "action_request_validation_exception",
        "reason": "Validation Failed: 1: Field [input] cannot be null;"
    },
    "status": 400
}

Success:

RQ:
POST {{base-url}}/_inference/text_embedding/llama-text-embedding
{
    "input": "The sky above the port was the color of television tuned to a dead channel."
}
RS:
{
    "text_embedding": [
        {
            "embedding": [
                0.055843446,
                0.01615099
            ]
        }
    ]
}

Create Completion Endpoint

No URL:

RQ:
PUT {{base-url}}/_inference/completion/llama-completion
{
    "service": "llama",
    "service_settings": {
        "api_key": "{{api-key}}",
        "model_id": "llama3.2:3b"
    }
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "validation_exception",
                "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
            }
        ],
        "type": "validation_exception",
        "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
    },
    "status": 400
}

Success:

RQ:
PUT {{base-url}}/_inference/completion/llama-completion
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/openai/v1/chat/completions",
        "model_id": "ollama/llama3.2:3b"
    }
}
RS:
{
    "inference_id": "llama-completion",
    "task_type": "completion",
    "service": "llama",
    "service_settings": {
        "model_id": "llama3.2:3b",
        "url": "http://localhost:8321/v1/openai/v1/chat/completions",
        "rate_limit": {
            "requests_per_minute": 3000
        }
    }
}

Perform Completion

Success (Non-Streaming):

RQ:
POST {{base-url}}/_inference/completion/llama-completion
{
    "input": "The sky above the port was the color of television tuned to a dead channel."
}
RS:
{
    "completion": [
        {
            "result": "You're quoting Joseph Heller's classic novel \"Catch-22\". The famous line from Chapter 14 reads:\n\n\"The sky above the port was the color of television set left on at high heat, which caught the sun in its glassy eye like a garnish on a prawns cocktail.\"\n\nThe phrase has since become a metaphor for a sense of desolation and hopelessness, often used to describe the feeling of being stuck or trapped in a situation."
        }
    ]
}

Success (Streaming):

RQ:
POST {{base-url}}/_inference/completion/llama-completion/_stream
{
    "input": "The sky above the port was the color of television tuned to a dead channel."
}
RS:
event: message
data: {"completion":[{"delta":"That"}]}

event: message
data: {"completion":[{"delta":"'s"}]}

event: message
data: {"completion":[{"delta":" a"}]}

event: message
data: {"completion":[{"delta":" great"}]}

event: message
data: {"completion":[{"delta":" quote"}]}

event: message
data: [DONE]

Bad Request(Non-Streaming):

RQ:
POST {{base-url}}/_inference/completion/llama-completion
{
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "action_request_validation_exception",
                "reason": "Validation Failed: 1: Field [input] cannot be null;"
            }
        ],
        "type": "action_request_validation_exception",
        "reason": "Validation Failed: 1: Field [input] cannot be null;"
    },
    "status": 400
}

Bad Request (Streaming):

RQ:
POST {{base-url}}/_inference/completion/llama-completion/_stream
{
}
RS:
event: error
data: {"error":{"root_cause":[{"type":"action_request_validation_exception","reason":"Validation Failed: 1: Field [input] cannot be null;"}],"type":"action_request_validation_exception","reason":"Validation Failed: 1: Field [input] cannot be null;"},"status":400}

Create Chat Completion Endpoint

No URL:

RQ:
PUT {{base-url}}/_inference/chat_completion/llama-chat-completion
{
    "service": "llama",
    "service_settings": {
        "api_key": "{{mistral-api-key}}",
        "model_id": "ollama/llama3.2:3b"
    }
}
RS:
{
    "error": {
        "root_cause": [
            {
                "type": "validation_exception",
                "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
            }
        ],
        "type": "validation_exception",
        "reason": "Validation Failed: 1: [service_settings] does not contain the required setting [url];"
    },
    "status": 400
}

Success:

RQ:
PUT {{base-url}}/_inference/chat_completion/llama-chat-completion
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/openai/v1/chat/completions",
        "api_key": "{{mistral-api-key}}",
        "model_id": "ollama/llama3.2:3b"
    }
}
RS:
{
    "inference_id": "llama-chat-completion",
    "task_type": "chat_completion",
    "service": "llama",
    "service_settings": {
        "model_id": "ollama/llama3.2:3b",
        "url": "http://localhost:8321/v1/openai/v1/chat/completions",
        "rate_limit": {
            "requests_per_minute": 3000
        }
    }
}

Perform Chat Completion

Success (basic):

RQ:
POST {{base-url}}/_inference/chat_completion/llama-chat-completion/_stream
{
    "messages": [
        {
            "role": "user",
            "content": "What is deep learning?"
        }
    ],
    "max_completion_tokens": 10
}
RS:
event: message
data: {"id":"chatcmpl-bc589b74-a744-418b-a856-fa11abd98c8c","choices":[{"delta":{"content":"","role":"assistant"},"finish_reason":"length","index":0}],"model":"llama3.2:3b","object":"chat.completion.chunk"}

event: message
data: {"id":"chatcmpl-bc589b74-a744-418b-a856-fa11abd98c8c","choices":[],"model":"llama3.2:3b","object":"chat.completion.chunk","usage":{"completion_tokens":10,"prompt_tokens":30,"total_tokens":40}}

event: message
data: [DONE]

Success (Complex):

RQ:
POST {{base-url}}/_inference/chat_completion/llama-chat-completion/_stream
{
    "model": "llama3.2:3b",
    "messages": [{
            "role": "user",
            "content": [{
                    "type": "text",
                    "text": "What's the price of a scarf?"
                }
            ]
        }
    ],
    "tools": [{
            "type": "function",
            "function": {
                "name": "get_current_price",
                "description": "Get the current price of a item",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "item": {
                            "id": "123"
                        }
                    }
                }
            }
        }
    ],
    "tool_choice": {
        "type": "function",
        "function": {
            "name": "get_current_price"
        }
    }
}

RS:
event: message
data: {"id":"chatcmpl-387a656b-2c0a-4fa7-9929-71e89c999c7e","choices":[{"delta":{"content":"","role":"assistant","tool_calls":[{"index":0,"id":"call_4qiq7n2n","function":{"arguments":"{\"item\":\"scarf\"}","name":"get_current_price"},"type":"function"}]},"index":0}],"model":"llama3.2:3b","object":"chat.completion.chunk"}

event: message
data: {"id":"chatcmpl-387a656b-2c0a-4fa7-9929-71e89c999c7e","choices":[{"delta":{"content":"","role":"assistant"},"finish_reason":"tool_calls","index":0}],"model":"llama3.2:3b","object":"chat.completion.chunk"}

event: message
data: {"id":"chatcmpl-387a656b-2c0a-4fa7-9929-71e89c999c7e","choices":[],"model":"llama3.2:3b","object":"chat.completion.chunk","usage":{"completion_tokens":15,"prompt_tokens":160,"total_tokens":175}}

event: message
data: [DONE]

Invalid Model:

RQ:
POST {{base-url}}/_inference/chat_completion/llama-chat-completion/_stream
{
    "model": "ggg",
    "messages": [
        {
            "role": "user",
            "content": "What is deep learning?"
        }
    ],
    "max_completion_tokens": 10
}
RS:
event: error
data: {"error":{"code":"stream_error","message":"Received an error response for request from inference entity id [llama-chat-completion]. Error message: [400: Invalid value: Model 'ggg' not found]","type":"llama_error"}}

- Have you signed the contributor license agreement?
- Have you followed the contributor guidelines?
- If submitting code, have you built your formula locally prior to submission with gradle check?
- If submitting code, is your pull request against main? Unless there is a good reason otherwise, we prefer pull requests against main and will backport as needed.
- If submitting code, have you checked that your submission is for an OS and architecture that we support?
- If you are submitting this code for a class then read our policy for that.

… for consistency

…andling

…ect arrays

…g-completion

…tion

…r handling and improve error response parsing

…clarity

…ontent type header

…figuration parsing and serialization

…ration parsing and serialization

… configuration scenarios

…or response handling

…d clarity

…ge serialization

…n and truncation behavior

…serialization

… HTTP responses

…figuration parsing and serialization

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

…equest handling

…tings

…t hashing

…streamline action creation

…d simplify model instantiation

…update similarity measure to DOT_PRODUCT

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

Jan-Kazlouski-elastic · 2025-07-11T18:51:12Z

@jonathan-buttner Thank you for your comments. They are addressed and PR ready to be re-reviewed.

…g-completion

…port version

jonathan-buttner

Thanks for the changes, left a few more suggestions.

jonathan-buttner · 2025-07-15T19:39:28Z

server/src/main/java/org/elasticsearch/TransportVersions.java

@@ -212,6 +212,7 @@ static TransportVersion def(int id) {
    public static final TransportVersion ESQL_PROFILE_INCLUDE_PLAN_8_19 = def(8_841_0_62);
    public static final TransportVersion ESQL_SPLIT_ON_BIG_VALUES_8_19 = def(8_841_0_63);
    public static final TransportVersion ESQL_FIXED_INDEX_LIKE_8_19 = def(8_841_0_64);
+    public static final TransportVersion ML_INFERENCE_LLAMA_ADDED_8_19 = def(8_841_0_65);


Sorry I forgot to mention this in the previous review, we won't be backporting this to 8.x so we can remove this transport version.

jonathan-buttner · 2025-07-15T19:47:09Z

...sticsearch/xpack/inference/services/llama/completion/LlamaChatCompletionServiceSettings.java

@@ -116,9 +116,16 @@ public String getWriteableName() {

    @Override
    public TransportVersion getMinimalSupportedVersion() {
+        assert false : "should never be called when supportsVersion is used";


I believe we can remove this line now because we won't need to backport to 8.x

jonathan-buttner · 2025-07-15T19:47:16Z

...sticsearch/xpack/inference/services/llama/completion/LlamaChatCompletionServiceSettings.java

        return TransportVersions.ML_INFERENCE_LLAMA_ADDED;
    }

+    @Override
+    public boolean supportsVersion(TransportVersion version) {


Let's remove this override.

jonathan-buttner · 2025-07-15T19:47:49Z

.../elasticsearch/xpack/inference/services/llama/embeddings/LlamaEmbeddingsServiceSettings.java

@@ -154,9 +154,16 @@ public String getWriteableName() {

    @Override
    public TransportVersion getMinimalSupportedVersion() {
+        assert false : "should never be called when supportsVersion is used";


Let's remove this.

jonathan-buttner · 2025-07-15T19:47:59Z

.../elasticsearch/xpack/inference/services/llama/embeddings/LlamaEmbeddingsServiceSettings.java

        return TransportVersions.ML_INFERENCE_LLAMA_ADDED;
    }

+    @Override


Let's remove this method override.

jonathan-buttner · 2025-07-15T19:52:25Z

...inference/src/main/java/org/elasticsearch/xpack/inference/services/mistral/MistralModel.java

@@ -49,7 +47,7 @@ public RateLimitSettings rateLimitSettings() {

    @Override
    public int rateLimitGroupingHash() {
-        return 0;


Good catch. In the future, let's add these bug fix changes to a separate PR.

Sure thing!

jonathan-buttner · 2025-07-15T19:55:57Z

.../src/test/java/org/elasticsearch/xpack/inference/services/AbstractInferenceServiceTests.java

@@ -141,7 +140,7 @@ public boolean isEnabled() {
            return true;
        }

-        protected abstract CustomModel createEmbeddingModel(@Nullable SimilarityMeasure similarityMeasure);
+        protected abstract Model createEmbeddingModel(@Nullable SimilarityMeasure similarityMeasure);


Thanks for these

No problem.

jonathan-buttner · 2025-07-15T20:09:20Z

...erence/src/test/java/org/elasticsearch/xpack/inference/services/llama/LlamaServiceTests.java

+        }
+    }
+
+    public void testParseRequestConfig_CreatesChatCompletionsModel() throws IOException {


I believe the base class covers this test, can you check and see if this test covers anything additional, if not, let's remove it from here.

You are correct. Added check for model_id to assert common model method since it was missed before.

…g-completion

…hods

jonathan-buttner · 2025-07-18T16:54:25Z

@Jan-Kazlouski-elastic I did some testing, things are looking good. I think there's one scenario we should add better validation error handling for.

I was struggling to get the llama3.2:3b to be recognized and finally realized that I need to prepend ollama/ in the model_id field. If you use a model string like llama3.2:3bbbb the inference endpoint will still be created even though the test request our inference plugin makes receives:

data: {"error": {"message": "400: Invalid value: Model 'llama3.2:3b' not found"}}

PUT _inference/chat_completion/chat
{
    "service": "llama",
    "service_settings": {
        "url": "http://localhost:8321/v1/openai/v1/chat/completions",
        "model_id": "llama3.2:3bbbb"
    }
}

I think a better experience would be for the PUT request to fail and report back the error it received. This is probably a larger change unrelated to this implementation though. I'll create an issue to improve the validation.

jonathan-buttner · 2025-07-18T16:54:56Z

Could you fix the merge conflicts and then I'll approve and merge on Monday 👍

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/InferencePlugin.java

…rove error message handling

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

Jan-Kazlouski-elastic · 2025-07-18T18:47:55Z

Conflicts are resolved. Adopted changes for Error Handling and for Service constructors from master.
FYI @jonathan-buttner

Jan-Kazlouski-elastic added 2 commits June 26, 2025 13:20

Refactor Hugging Face service settings and completion request methods…

85478cf

… for consistency

Add Llama model support for embeddings and chat completions

727fd8e

elasticsearchmachine added v9.2.0 external-contributor Pull request authored by a developer outside the Elasticsearch team labels Jun 26, 2025

Jan-Kazlouski-elastic and others added 24 commits June 26, 2025 21:14

Refactor Llama request classes to improve secret settings handling

cc14b18

Refactor DeltaParser in LlamaStreamingProcessor to improve argument h…

ceef95a

…andling

Enhance Llama streaming processing by adding support for nullable obj…

55d9014

…ect arrays

[CI] Auto commit changes from spotless

a83b0b7

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

852aa19

…g-completion

Fix error messages in LlamaActionCreator

d6b53c3

[CI] Auto commit changes from spotless

6ce4b09

Add detailed Javadoc comments to Llama classes for improved documenta…

8e7ca13

…tion

Enhance LlamaChatCompletionResponseHandler to support mid-stream erro…

604d441

…r handling and improve error response parsing

Add Javadoc comments to Llama classes for improved documentation and …

74fd6e8

…clarity

Fix checkstyle

ac161fa

Update LlamaEmbeddingsRequest to use mediaTypeWithoutParameters for c…

a13020c

…ontent type header

Add unit tests for LlamaActionCreator and related models

4eade05

Add unit tests for LlamaChatCompletionServiceSettings to validate con…

39c5787

…figuration parsing and serialization

Add unit tests for LlamaEmbeddingsServiceSettings to validate configu…

6a135c5

…ration parsing and serialization

Add unit tests for LlamaEmbeddingsServiceSettings to validate various…

c6fc56f

… configuration scenarios

Add unit tests for LlamaChatCompletionResponseHandler to validate err…

e2dce7c

…or response handling

Refactor Llama embedding and chat completion tests for consistency an…

41591ae

…d clarity

Add unit tests for LlamaChatCompletionRequestEntity to validate messa…

4d2a5dd

…ge serialization

Add unit tests for LlamaEmbeddingsRequest to validate request creatio…

1573d53

…n and truncation behavior

Add unit tests for LlamaEmbeddingsRequestEntity to validate XContent …

da55903

…serialization

Add unit tests for LlamaErrorResponse to validate error handling from…

8cc8958

… HTTP responses

Add unit tests for LlamaChatCompletionServiceSettings to validate con…

9573a48

…figuration parsing and serialization

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

36ff4cd

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

Jan-Kazlouski-elastic marked this pull request as ready for review July 4, 2025 14:02

Jan-Kazlouski-elastic requested a review from a team as a code owner July 4, 2025 14:02

Jan-Kazlouski-elastic added 9 commits July 10, 2025 21:26

Refactor Llama model classes to remove modelId and update embedding r…

fe6173e

…equest handling

Refactor Llama request classes to use pattern matching for secret set…

ad009c6

…tings

Update embeddings handler to use HuggingFace response entity

18ee182

Refactor Mistral model classes to remove modelId and update rate limi…

c2621e7

…t hashing

Refactor Mistral action classes to remove taskSettings parameter and …

eb60dfa

…streamline action creation

Refactor Llama and Mistral models to remove taskSettings parameter an…

76ddf99

…d simplify model instantiation

Refactor Llama service tests to use Model instead of CustomModel and …

9100f69

…update similarity measure to DOT_PRODUCT

Remove unused tests and imports from LlamaServiceTests

5fb9dad

Add chunking settings support to Llama embeddings model tests

47c9cc6

Jan-Kazlouski-elastic requested a review from jonathan-buttner July 11, 2025 18:46

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

34e21de

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

Jan-Kazlouski-elastic added 4 commits July 14, 2025 13:23

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

1c1ba1d

…g-completion

Add changelog

c267269

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

098849f

…g-completion

Add support for version checks in Llama settings and define new trans…

06c7bd1

…port version

jonathan-buttner reviewed Jul 15, 2025

View reviewed changes

Jan-Kazlouski-elastic added 2 commits July 16, 2025 23:22

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

33da7a9

…g-completion

Refactor Llama model assertions and remove unused version support met…

28335ef

…hods

Jan-Kazlouski-elastic requested a review from jonathan-buttner July 16, 2025 20:50

Jan-Kazlouski-elastic added 3 commits July 18, 2025 20:51

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

d43d1e9

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/InferencePlugin.java

Refactor Llama service constructors to include ClusterService and imp…

528a9d9

…rove error message handling

Merge remote-tracking branch 'origin/main' into feature/llama-embedin…

c879b96

…g-completion # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java

jonathan-buttner approved these changes Jul 18, 2025

View reviewed changes

jonathan-buttner merged commit beb18a8 into elastic:main Jul 18, 2025
35 checks passed

Jan-Kazlouski-elastic mentioned this pull request Jul 22, 2025

Update inference API specification to include new Llama Service elastic/elasticsearch-specification#5020

Open

2 tasks

Add Llama support to Inference Plugin #130092

Add Llama support to Inference Plugin #130092

Uh oh!

Conversation

Jan-Kazlouski-elastic commented Jun 26, 2025 • edited by jonathan-buttner Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Jan-Kazlouski-elastic commented Jul 11, 2025

Uh oh!

jonathan-buttner left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jonathan-buttner commented Jul 18, 2025

Uh oh!

jonathan-buttner commented Jul 18, 2025

Uh oh!

Jan-Kazlouski-elastic commented Jul 18, 2025

Uh oh!

Uh oh!

Uh oh!

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Jan-Kazlouski-elastic commented Jun 26, 2025 •

edited by jonathan-buttner

Loading