apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-07-05 15:52:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix(ci): switch retired claude-sonnet-4-20250514 to claude-sonnet-4-6 (#975)

Browse source
This commit is contained in:
Musa 2026-06-24 10:13:37 -07:00 • committed by GitHub
parent 5d990d9609
commit 5cc4c4ee77
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 80 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

2
cli/planoai/templates/conversational_state_v1_responses.yaml
View file

@ -11,7 +11,7 @@ model_providers:
default: true default: true
# Anthropic Models # Anthropic Models
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
listeners: listeners:

2
cli/planoai/templates/preference_aware_routing.yaml
View file

@ -12,7 +12,7 @@ model_providers:
- name: code understanding - name: code understanding
description: understand and explain existing code snippets, functions, or libraries description: understand and explain existing code snippets, functions, or libraries
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: code generation - name: code generation

14
cli/test/test_config_generator.py
View file

@ -584,7 +584,7 @@ model_providers:
- name: code understanding - name: code understanding
description: understand and explain existing code snippets, functions, or libraries description: understand and explain existing code snippets, functions, or libraries
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: code generation - name: code generation
@ -601,9 +601,7 @@ model_providers:
by_name = {entry["name"]: entry for entry in top_level} by_name = {entry["name"]: entry for entry in top_level}
assert set(by_name) == {"code understanding", "code generation"} assert set(by_name) == {"code understanding", "code generation"}
assert by_name["code understanding"]["models"] == ["openai/gpt-4o"] assert by_name["code understanding"]["models"] == ["openai/gpt-4o"]
assert by_name["code generation"]["models"] == [ assert by_name["code generation"]["models"] == ["anthropic/claude-sonnet-4-6"]
"anthropic/claude-sonnet-4-20250514"
]
assert ( assert (
by_name["code understanding"]["description"] by_name["code understanding"]["description"]
== "understand and explain existing code snippets, functions, or libraries" == "understand and explain existing code snippets, functions, or libraries"
@ -626,7 +624,7 @@ model_providers:
- name: code generation - name: code generation
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: code generation - name: code generation
@ -641,7 +639,7 @@ model_providers:
assert entry["name"] == "code generation" assert entry["name"] == "code generation"
assert entry["models"] == [ assert entry["models"] == [
"openai/gpt-4o", "openai/gpt-4o",
"anthropic/claude-sonnet-4-20250514", "anthropic/claude-sonnet-4-6",
] ]
assert config_yaml["version"] == "v0.4.0" assert config_yaml["version"] == "v0.4.0"
@ -658,7 +656,7 @@ listeners:
model_providers: model_providers:
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
@ -666,7 +664,7 @@ routing_preferences:
description: generating new code snippets or boilerplate description: generating new code snippets or boilerplate
models: models:
- openai/gpt-4o - openai/gpt-4o
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
""" """
config_yaml = yaml.safe_load(plano_config) config_yaml = yaml.safe_load(plano_config)
before = yaml.safe_dump(config_yaml, sort_keys=True) before = yaml.safe_dump(config_yaml, sort_keys=True)

2
demos/filter_chains/pii_anonymizer/config.yaml
View file

@ -12,7 +12,7 @@ model_providers:
- model: openai/gpt-4o-mini - model: openai/gpt-4o-mini
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
default: true default: true
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
listeners: listeners:

6
demos/filter_chains/pii_anonymizer/test.sh
View file

@ -93,19 +93,19 @@ echo ""
echo "=== /v1/messages ===" echo "=== /v1/messages ==="
run_test "Non-streaming with PII (phone)" /v1/messages 200 '{ run_test "Non-streaming with PII (phone)" /v1/messages 200 '{
"model": "claude-sonnet-4-20250514", "model": "claude-sonnet-4-6",
"max_tokens": 256, "max_tokens": 256,
"messages": [{"role": "user", "content": "Call me at 555-867-5309 to discuss my account"}] "messages": [{"role": "user", "content": "Call me at 555-867-5309 to discuss my account"}]
}' }'
run_test "Non-streaming with PII (SSN)" /v1/messages 200 '{ run_test "Non-streaming with PII (SSN)" /v1/messages 200 '{
"model": "claude-sonnet-4-20250514", "model": "claude-sonnet-4-6",
"max_tokens": 256, "max_tokens": 256,
"messages": [{"role": "user", "content": "My SSN is 123-45-6789"}] "messages": [{"role": "user", "content": "My SSN is 123-45-6789"}]
}' }'
run_test "No PII" /v1/messages 200 '{ run_test "No PII" /v1/messages 200 '{
"model": "claude-sonnet-4-20250514", "model": "claude-sonnet-4-6",
"max_tokens": 256, "max_tokens": 256,
"messages": [{"role": "user", "content": "Hello, how are you?"}] "messages": [{"role": "user", "content": "Hello, how are you?"}]
}' }'

2
demos/getting_started/weather_forecast/config.yaml
View file

@ -30,7 +30,7 @@ model_providers:
model: openai/gpt-4o-mini model: openai/gpt-4o-mini
- access_key: $ANTHROPIC_API_KEY - access_key: $ANTHROPIC_API_KEY
model: anthropic/claude-sonnet-4-20250514 model: anthropic/claude-sonnet-4-6
system_prompt: | system_prompt: |
You are a helpful assistant. You are a helpful assistant.

6
demos/llm_routing/model_alias_routing/config_with_aliases.yaml
View file

@ -28,7 +28,7 @@ model_providers:
- model: anthropic/* - model: anthropic/*
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: anthropic/claude-3-haiku-20240307 - model: anthropic/claude-3-haiku-20240307
@ -71,7 +71,7 @@ model_aliases:
# Alias for creative tasks -> Claude model # Alias for creative tasks -> Claude model
arch.creative.v1: arch.creative.v1:
target: claude-sonnet-4-20250514 target: claude-sonnet-4-6
# Alias for quick responses -> fast model # Alias for quick responses -> fast model
arch.fast.v1: arch.fast.v1:
@ -85,7 +85,7 @@ model_aliases:
target: gpt-5-mini-2025-08-07 target: gpt-5-mini-2025-08-07
creative-model: creative-model:
target: claude-sonnet-4-20250514 target: claude-sonnet-4-6
coding-model: coding-model:
target: us.amazon.nova-premier-v1:0 target: us.amazon.nova-premier-v1:0

18
demos/llm_routing/model_routing_service/README.md
View file

@ -33,7 +33,7 @@ routing_preferences:
- name: code_generation - name: code_generation
description: generating new code, writing functions, or creating boilerplate description: generating new code, writing functions, or creating boilerplate
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- openai/gpt-4o - openai/gpt-4o
``` ```
@ -46,7 +46,7 @@ When a request arrives, Plano:
``` ```
1. Request arrives → "Write binary search in Python" 1. Request arrives → "Write binary search in Python"
2. Plano-Orchestrator classifies → route: "code_generation" 2. Plano-Orchestrator classifies → route: "code_generation"
3. Response → models: ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"] 3. Response → models: ["anthropic/claude-sonnet-4-6", "openai/gpt-4o"]
``` ```
No match? Plano-Orchestrator returns an empty route → client falls back to the model in the original request. No match? Plano-Orchestrator returns an empty route → client falls back to the model in the original request.
@ -98,7 +98,7 @@ curl http://localhost:12000/routing/v1/chat/completions \
Response: Response:
```json ```json
{ {
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"], "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o"],
"route": "code_generation", "route": "code_generation",
"trace_id": "c16d1096c1af4a17abb48fb182918a88" "trace_id": "c16d1096c1af4a17abb48fb182918a88"
} }
@ -124,7 +124,7 @@ curl http://localhost:12000/routing/v1/chat/completions \
Response (first call): Response (first call):
```json ```json
{ {
"model": "anthropic/claude-sonnet-4-20250514", "model": "anthropic/claude-sonnet-4-6",
"route": "code_generation", "route": "code_generation",
"trace_id": "c16d1096c1af4a17abb48fb182918a88", "trace_id": "c16d1096c1af4a17abb48fb182918a88",
"session_id": "my-session-123", "session_id": "my-session-123",
@ -146,7 +146,7 @@ curl http://localhost:12000/routing/v1/chat/completions \
Response (pinned): Response (pinned):
```json ```json
{ {
"model": "anthropic/claude-sonnet-4-20250514", "model": "anthropic/claude-sonnet-4-6",
"route": "code_generation", "route": "code_generation",
"trace_id": "a1b2c3d4e5f6...", "trace_id": "a1b2c3d4e5f6...",
"session_id": "my-session-123", "session_id": "my-session-123",
@ -233,7 +233,7 @@ kubectl rollout restart deployment/plano
--- 1. Code generation query (OpenAI format) --- --- 1. Code generation query (OpenAI format) ---
{ {
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"], "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o"],
"route": "code_generation", "route": "code_generation",
"trace_id": "c16d1096c1af4a17abb48fb182918a88" "trace_id": "c16d1096c1af4a17abb48fb182918a88"
} }
@ -254,14 +254,14 @@ kubectl rollout restart deployment/plano
--- 4. Code generation query (Anthropic format) --- --- 4. Code generation query (Anthropic format) ---
{ {
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"], "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o"],
"route": "code_generation", "route": "code_generation",
"trace_id": "26be822bbdf14a3ba19fe198e55ea4a9" "trace_id": "26be822bbdf14a3ba19fe198e55ea4a9"
} }
--- 7. Session pinning - first call (fresh routing decision) --- --- 7. Session pinning - first call (fresh routing decision) ---
{ {
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"], "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o"],
"route": "code_generation", "route": "code_generation",
"trace_id": "f1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6", "trace_id": "f1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6",
"session_id": "demo-session-001", "session_id": "demo-session-001",
@ -271,7 +271,7 @@ kubectl rollout restart deployment/plano
--- 8. Session pinning - second call (same session, pinned) --- --- 8. Session pinning - second call (same session, pinned) ---
Notice: same model returned with "pinned": true, routing was skipped Notice: same model returned with "pinned": true, routing was skipped
{ {
"model": "anthropic/claude-sonnet-4-20250514", "model": "anthropic/claude-sonnet-4-6",
"route": "code_generation", "route": "code_generation",
"trace_id": "a9b8c7d6e5f4a3b2c1d0e9f8a7b6c5d4", "trace_id": "a9b8c7d6e5f4a3b2c1d0e9f8a7b6c5d4",
"session_id": "demo-session-001", "session_id": "demo-session-001",

4
demos/llm_routing/model_routing_service/config.yaml
View file

@ -13,7 +13,7 @@ model_providers:
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
@ -26,5 +26,5 @@ routing_preferences:
- name: code_generation - name: code_generation
description: generating new code, writing functions, or creating boilerplate description: generating new code, writing functions, or creating boilerplate
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- openai/gpt-4o - openai/gpt-4o

2
demos/llm_routing/model_routing_service/config_k8s.yaml
View file

@ -23,7 +23,7 @@ model_providers:
- name: complex_reasoning - name: complex_reasoning
description: complex reasoning tasks, multi-step analysis, or detailed explanations description: complex reasoning tasks, multi-step analysis, or detailed explanations
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: code_generation - name: code_generation

2
demos/llm_routing/model_routing_service/demo.sh
View file

@ -102,7 +102,7 @@ curl -s "$PLANO_URL/routing/v1/chat/completions" \
{ {
"name": "coding", "name": "coding",
"description": "code generation, writing functions, debugging", "description": "code generation, writing functions, debugging",
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o", "openai/gpt-4o-mini"], "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o", "openai/gpt-4o-mini"],
"selection_policy": {"prefer": "fastest"} "selection_policy": {"prefer": "fastest"}
} }
] ]

4
demos/llm_routing/model_routing_service/metrics_server.py
View file

@ -12,13 +12,13 @@ from http.server import HTTPServer, BaseHTTPRequestHandler
PROMETHEUS_METRICS = """\ PROMETHEUS_METRICS = """\
# HELP model_latency_p95_seconds P95 request latency in seconds per model # HELP model_latency_p95_seconds P95 request latency in seconds per model
# TYPE model_latency_p95_seconds gauge # TYPE model_latency_p95_seconds gauge
model_latency_p95_seconds{model_name="anthropic/claude-sonnet-4-20250514"} 0.85 model_latency_p95_seconds{model_name="anthropic/claude-sonnet-4-6"} 0.85
model_latency_p95_seconds{model_name="openai/gpt-4o"} 1.20 model_latency_p95_seconds{model_name="openai/gpt-4o"} 1.20
model_latency_p95_seconds{model_name="openai/gpt-4o-mini"} 0.40 model_latency_p95_seconds{model_name="openai/gpt-4o-mini"} 0.40
""".encode() """.encode()
COST_DATA = { COST_DATA = {
"anthropic/claude-sonnet-4-20250514": { "anthropic/claude-sonnet-4-6": {
"input_per_million": 3.0, "input_per_million": 3.0,
"output_per_million": 15.0, "output_per_million": 15.0,
}, },

2
demos/llm_routing/model_routing_service/test.rest
View file

@ -30,7 +30,7 @@ POST http://localhost:12000/routing/v1/messages
Content-Type: application/json Content-Type: application/json
{ {
"model": "claude-sonnet-4-20250514", "model": "claude-sonnet-4-6",
"max_tokens": 1024, "max_tokens": 1024,
"messages": [{"role": "user", "content": "Write a REST API in Go using Gin"}] "messages": [{"role": "user", "content": "Write a REST API in Go using Gin"}]
} }

2
demos/llm_routing/preference_based_routing/config.yaml
View file

@ -17,7 +17,7 @@ model_providers:
- name: code understanding - name: code understanding
description: understand and explain existing code snippets, functions, or libraries description: understand and explain existing code snippets, functions, or libraries
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: code generation - name: code generation

10
docs/routing-api.md
View file

@ -21,7 +21,7 @@ POST /v1/chat/completions
{ {
"name": "code generation", "name": "code generation",
"description": "generating new code snippets", "description": "generating new code snippets",
"models": ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o", "openai/gpt-4o-mini"] "models": ["anthropic/claude-sonnet-4-6", "openai/gpt-4o", "openai/gpt-4o-mini"]
}, },
{ {
"name": "general questions", "name": "general questions",
@ -55,7 +55,7 @@ POST /v1/chat/completions
```json ```json
{ {
"models": [ "models": [
"anthropic/claude-sonnet-4-20250514", "anthropic/claude-sonnet-4-6",
"openai/gpt-4o", "openai/gpt-4o",
"openai/gpt-4o-mini" "openai/gpt-4o-mini"
], ],
@ -100,7 +100,7 @@ Requires `version: v0.4.0` or above. Models listed under `routing_preferences` m
version: v0.4.0 version: v0.4.0
model_providers: model_providers:
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
@ -112,7 +112,7 @@ routing_preferences:
- name: code generation - name: code generation
description: generating new code snippets or boilerplate description: generating new code snippets or boilerplate
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- openai/gpt-4o - openai/gpt-4o
- name: general questions - name: general questions
@ -149,7 +149,7 @@ Response when pinned:
```json ```json
{ {
"models": ["anthropic/claude-sonnet-4-20250514"], "models": ["anthropic/claude-sonnet-4-6"],
"route": "code generation", "route": "code generation",
"trace_id": "...", "trace_id": "...",
"session_id": "a1b2c3d4-5678-...", "session_id": "a1b2c3d4-5678-...",

8
docs/source/concepts/llm_providers/supported_providers.rst
View file

@ -179,14 +179,14 @@ Anthropic
- model: anthropic/* - model: anthropic/*
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_PROD_API_KEY access_key: $ANTHROPIC_PROD_API_KEY
routing_preferences: routing_preferences:
- name: code_generation - name: code_generation
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
DeepSeek DeepSeek
~~~~~~~~ ~~~~~~~~
@ -823,7 +823,7 @@ You can configure specific models with custom settings even when using wildcards
# Override specific model with custom settings # Override specific model with custom settings
# This model will NOT be included in the wildcard expansion above # This model will NOT be included in the wildcard expansion above
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_PROD_API_KEY access_key: $ANTHROPIC_PROD_API_KEY
# Another specific override # Another specific override
@ -834,7 +834,7 @@ You can configure specific models with custom settings even when using wildcards
- name: code_generation - name: code_generation
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
**Custom Provider Wildcards:** **Custom Provider Wildcards:**

2
docs/source/resources/includes/plano_config_state_storage_example.yaml
View file

@ -13,7 +13,7 @@ model_providers:
default: true default: true
# Anthropic Models # Anthropic Models
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
# State storage configuration for v1/responses API # State storage configuration for v1/responses API

24
skills/AGENTS.md
View file

@ -171,7 +171,7 @@ Plano translates requests between its internal format and each provider's API. T
| Model prefix | Wire format | Example | | Model prefix | Wire format | Example |
|---|---|---| |---|---|---|
| `openai/*` | OpenAI | `openai/gpt-4o` | | `openai/*` | OpenAI | `openai/gpt-4o` |
| `anthropic/*` | Anthropic | `anthropic/claude-sonnet-4-20250514` | | `anthropic/*` | Anthropic | `anthropic/claude-sonnet-4-6` |
| `gemini/*` | Google Gemini | `gemini/gemini-2.0-flash` | | `gemini/*` | Google Gemini | `gemini/gemini-2.0-flash` |
| `mistral/*` | Mistral | `mistral/mistral-large-latest` | | `mistral/*` | Mistral | `mistral/mistral-large-latest` |
| `groq/*` | Groq | `groq/llama-3.3-70b-versatile` | | `groq/*` | Groq | `groq/llama-3.3-70b-versatile` |
@ -199,7 +199,7 @@ model_providers:
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
default: true default: true
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: gemini/gemini-2.0-flash - model: gemini/gemini-2.0-flash
@ -262,7 +262,7 @@ model_providers:
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
default: true default: true
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
state_storage: state_storage:
@ -431,7 +431,7 @@ model_providers:
default: true default: true
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
model_aliases: model_aliases:
@ -442,7 +442,7 @@ model_aliases:
target: gpt-4o # High capability — for complex reasoning target: gpt-4o # High capability — for complex reasoning
plano.creative.v1: plano.creative.v1:
target: claude-sonnet-4-20250514 # Strong creative writing and analysis target: claude-sonnet-4-6 # Strong creative writing and analysis
plano.v1: plano.v1:
target: gpt-4o # Default production alias target: gpt-4o # Default production alias
@ -1419,7 +1419,7 @@ listeners:
port: 12000 port: 12000
model_providers: model_providers:
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
default: true default: true
@ -1432,7 +1432,7 @@ routing_preferences:
Writing code, debugging, code review, explaining concepts, Writing code, debugging, code review, explaining concepts,
answering programming questions, general development tasks. answering programming questions, general development tasks.
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- anthropic/claude-opus-4-6 - anthropic/claude-opus-4-6
- name: complex architecture - name: complex architecture
description: > description: >
@ -1440,11 +1440,11 @@ routing_preferences:
architectural decisions, performance optimization, security audits. architectural decisions, performance optimization, security audits.
models: models:
- anthropic/claude-opus-4-6 - anthropic/claude-opus-4-6
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
model_aliases: model_aliases:
claude.fast.v1: claude.fast.v1:
target: claude-sonnet-4-20250514 target: claude-sonnet-4-6
claude.smart.v1: claude.smart.v1:
target: claude-opus-4-6 target: claude-opus-4-6
@ -1838,7 +1838,7 @@ model_providers:
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
# --- Shared routing_preferences (top-level, v0.4.0+) --- # --- Shared routing_preferences (top-level, v0.4.0+) ---
@ -1851,11 +1851,11 @@ routing_preferences:
description: Multi-step analysis, code generation, research synthesis description: Multi-step analysis, code generation, research synthesis
models: models:
- openai/gpt-4o - openai/gpt-4o
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- name: long documents - name: long documents
description: Summarizing or analyzing very long documents, PDFs, transcripts description: Summarizing or analyzing very long documents, PDFs, transcripts
models: models:
- anthropic/claude-sonnet-4-20250514 - anthropic/claude-sonnet-4-6
- openai/gpt-4o - openai/gpt-4o
# --- Listener 1: OpenAI-compatible API gateway --- # --- Listener 1: OpenAI-compatible API gateway ---

2
skills/rules/advanced-multi-listener.md
View file

@ -42,7 +42,7 @@ model_providers:
- name: complex reasoning - name: complex reasoning
description: Multi-step analysis, code generation, research synthesis description: Multi-step analysis, code generation, research synthesis
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
routing_preferences: routing_preferences:
- name: long documents - name: long documents

4
skills/rules/cli-agent.md
View file

@ -43,7 +43,7 @@ listeners:
port: 12000 port: 12000
model_providers: model_providers:
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
default: true default: true
routing_preferences: routing_preferences:
@ -62,7 +62,7 @@ model_providers:
model_aliases: model_aliases:
claude.fast.v1: claude.fast.v1:
target: claude-sonnet-4-20250514 target: claude-sonnet-4-6
claude.smart.v1: claude.smart.v1:
target: claude-opus-4-6 target: claude-opus-4-6

4
skills/rules/config-providers.md
View file

@ -14,7 +14,7 @@ Plano translates requests between its internal format and each provider's API. T
| Model prefix | Wire format | Example | | Model prefix | Wire format | Example |
|---|---|---| |---|---|---|
| `openai/*` | OpenAI | `openai/gpt-4o` | | `openai/*` | OpenAI | `openai/gpt-4o` |
| `anthropic/*` | Anthropic | `anthropic/claude-sonnet-4-20250514` | | `anthropic/*` | Anthropic | `anthropic/claude-sonnet-4-6` |
| `gemini/*` | Google Gemini | `gemini/gemini-2.0-flash` | | `gemini/*` | Google Gemini | `gemini/gemini-2.0-flash` |
| `mistral/*` | Mistral | `mistral/mistral-large-latest` | | `mistral/*` | Mistral | `mistral/mistral-large-latest` |
| `groq/*` | Groq | `groq/llama-3.3-70b-versatile` | | `groq/*` | Groq | `groq/llama-3.3-70b-versatile` |
@ -42,7 +42,7 @@ model_providers:
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
default: true default: true
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
- model: gemini/gemini-2.0-flash - model: gemini/gemini-2.0-flash

2
skills/rules/config-secrets.md
View file

@ -40,7 +40,7 @@ model_providers:
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
default: true default: true
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
state_storage: state_storage:

4
skills/rules/routing-aliases.md
View file

@ -47,7 +47,7 @@ model_providers:
default: true default: true
- model: openai/gpt-4o - model: openai/gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
model_aliases: model_aliases:
@ -58,7 +58,7 @@ model_aliases:
target: gpt-4o # High capability — for complex reasoning target: gpt-4o # High capability — for complex reasoning
plano.creative.v1: plano.creative.v1:
target: claude-sonnet-4-20250514 # Strong creative writing and analysis target: claude-sonnet-4-6 # Strong creative writing and analysis
plano.v1: plano.v1:
target: gpt-4o # Default production alias target: gpt-4o # Default production alias

6
skills/test-cases.json
View file

@ -92,7 +92,7 @@
"testCase": { "testCase": {
"description": "Detect and fix: \"Register Model Providers with Correct Format Identifiers\"", "description": "Detect and fix: \"Register Model Providers with Correct Format Identifiers\"",
"input": "model_providers:\n - model: gpt-4o # Missing openai/ prefix — Plano cannot route this\n access_key: $OPENAI_API_KEY\n\n - model: claude-3-5-sonnet # Missing anthropic/ prefix\n access_key: $ANTHROPIC_API_KEY", "input": "model_providers:\n - model: gpt-4o # Missing openai/ prefix — Plano cannot route this\n access_key: $OPENAI_API_KEY\n\n - model: claude-3-5-sonnet # Missing anthropic/ prefix\n access_key: $ANTHROPIC_API_KEY",
"expected": "model_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n - model: anthropic/claude-sonnet-4-20250514\n access_key: $ANTHROPIC_API_KEY\n\n - model: gemini/gemini-2.0-flash\n access_key: $GOOGLE_API_KEY\n\nmodel_providers:\n - model: custom/llama3\n base_url: http://host.docker.internal:11434/v1 # Ollama endpoint\n provider_interface: openai # Ollama speaks OpenAI format\n default: true", "expected": "model_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n - model: anthropic/claude-sonnet-4-6\n access_key: $ANTHROPIC_API_KEY\n\n - model: gemini/gemini-2.0-flash\n access_key: $GOOGLE_API_KEY\n\nmodel_providers:\n - model: custom/llama3\n base_url: http://host.docker.internal:11434/v1 # Ollama endpoint\n provider_interface: openai # Ollama speaks OpenAI format\n default: true",
"evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Register Model Providers with Correct Format Identifiers\" and explain how to fix it." "evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Register Model Providers with Correct Format Identifiers\" and explain how to fix it."
} }
}, },
@ -112,7 +112,7 @@
"testCase": { "testCase": {
"description": "Detect and fix: \"Use Environment Variable Substitution for All Secrets\"", "description": "Detect and fix: \"Use Environment Variable Substitution for All Secrets\"",
"input": "version: v0.3.0\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: abcdefghijklmnopqrstuvwxyz... # Hardcoded — never do this\n\nstate_storage:\n type: postgres\n connection_string: \"postgresql://admin:mysecretpassword@prod-db:5432/plano\"\n\nprompt_targets:\n - name: get_data\n endpoint:\n name: my_api\n http_headers:\n Authorization: \"Bearer abcdefghijklmnopqrstuvwxyz\" # Hardcoded token", "input": "version: v0.3.0\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: abcdefghijklmnopqrstuvwxyz... # Hardcoded — never do this\n\nstate_storage:\n type: postgres\n connection_string: \"postgresql://admin:mysecretpassword@prod-db:5432/plano\"\n\nprompt_targets:\n - name: get_data\n endpoint:\n name: my_api\n http_headers:\n Authorization: \"Bearer abcdefghijklmnopqrstuvwxyz\" # Hardcoded token",
"expected": "version: v0.3.0\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n - model: anthropic/claude-sonnet-4-20250514\n access_key: $ANTHROPIC_API_KEY\n\nstate_storage:\n type: postgres\n connection_string: \"postgresql://${DB_USER}:${DB_PASS}@${DB_HOST}:5432/${DB_NAME}\"\n\nprompt_targets:\n - name: get_data\n endpoint:\n name: my_api\n http_headers:\n Authorization: \"Bearer $MY_API_TOKEN\"\n\n# .env — add to .gitignore\nOPENAI_API_KEY=abcdefghijklmnopqrstuvwxyz...\nANTHROPIC_API_KEY=abcdefghijklmnopqrstuvwxyz...\nDB_USER=plano\nDB_PASS=secure-password\nDB_HOST=localhost\nMY_API_TOKEN=abcdefghijklmnopqrstuvwxyz...", "expected": "version: v0.3.0\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n - model: anthropic/claude-sonnet-4-6\n access_key: $ANTHROPIC_API_KEY\n\nstate_storage:\n type: postgres\n connection_string: \"postgresql://${DB_USER}:${DB_PASS}@${DB_HOST}:5432/${DB_NAME}\"\n\nprompt_targets:\n - name: get_data\n endpoint:\n name: my_api\n http_headers:\n Authorization: \"Bearer $MY_API_TOKEN\"\n\n# .env — add to .gitignore\nOPENAI_API_KEY=abcdefghijklmnopqrstuvwxyz...\nANTHROPIC_API_KEY=abcdefghijklmnopqrstuvwxyz...\nDB_USER=plano\nDB_PASS=secure-password\nDB_HOST=localhost\nMY_API_TOKEN=abcdefghijklmnopqrstuvwxyz...",
"evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Use Environment Variable Substitution for All Secrets\" and explain how to fix it." "evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Use Environment Variable Substitution for All Secrets\" and explain how to fix it."
} }
}, },
@ -288,7 +288,7 @@
"testCase": { "testCase": {
"description": "Detect and fix: \"Use Model Aliases for Semantic, Stable Model References\"", "description": "Detect and fix: \"Use Model Aliases for Semantic, Stable Model References\"",
"input": "# config.yaml — no aliases defined\nversion: v0.3.0\n\nlisteners:\n - type: model\n name: model_listener\n port: 12000\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n# Client code — brittle, must be updated when model changes\nclient.chat.completions.create(model=\"gpt-4o\", ...)", "input": "# config.yaml — no aliases defined\nversion: v0.3.0\n\nlisteners:\n - type: model\n name: model_listener\n port: 12000\n\nmodel_providers:\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n default: true\n\n# Client code — brittle, must be updated when model changes\nclient.chat.completions.create(model=\"gpt-4o\", ...)",
"expected": "version: v0.3.0\n\nlisteners:\n - type: model\n name: model_listener\n port: 12000\n\nmodel_providers:\n - model: openai/gpt-4o-mini\n access_key: $OPENAI_API_KEY\n default: true\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n - model: anthropic/claude-sonnet-4-20250514\n access_key: $ANTHROPIC_API_KEY\n\nmodel_aliases:\n plano.fast.v1:\n target: gpt-4o-mini # Cheap, fast — for high-volume tasks\n\n plano.smart.v1:\n target: gpt-4o # High capability — for complex reasoning\n\n plano.creative.v1:\n target: claude-sonnet-4-20250514 # Strong creative writing and analysis\n\n plano.v1:\n target: gpt-4o # Default production alias\n\n# Client code — stable, alias is the contract\nclient.chat.completions.create(model=\"plano.smart.v1\", ...)", "expected": "version: v0.3.0\n\nlisteners:\n - type: model\n name: model_listener\n port: 12000\n\nmodel_providers:\n - model: openai/gpt-4o-mini\n access_key: $OPENAI_API_KEY\n default: true\n - model: openai/gpt-4o\n access_key: $OPENAI_API_KEY\n - model: anthropic/claude-sonnet-4-6\n access_key: $ANTHROPIC_API_KEY\n\nmodel_aliases:\n plano.fast.v1:\n target: gpt-4o-mini # Cheap, fast — for high-volume tasks\n\n plano.smart.v1:\n target: gpt-4o # High capability — for complex reasoning\n\n plano.creative.v1:\n target: claude-sonnet-4-6 # Strong creative writing and analysis\n\n plano.v1:\n target: gpt-4o # Default production alias\n\n# Client code — stable, alias is the contract\nclient.chat.completions.create(model=\"plano.smart.v1\", ...)",
"evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Use Model Aliases for Semantic, Stable Model References\" and explain how to fix it." "evaluationPrompt": "Given the following Plano config or CLI usage, identify if it violates the rule \"Use Model Aliases for Semantic, Stable Model References\" and explain how to fix it."
} }
}, },

2
tests/e2e/config_memory_state_v1_responses.yaml
View file

@ -15,7 +15,7 @@ llm_providers:
default: true default: true
# Anthropic Models # Anthropic Models
- model: anthropic/claude-sonnet-4-20250514 - model: anthropic/claude-sonnet-4-6
access_key: $ANTHROPIC_API_KEY access_key: $ANTHROPIC_API_KEY
# State storage configuration for v1/responses API # State storage configuration for v1/responses API

2
tests/e2e/test_model_alias_routing.py
View file

@ -440,7 +440,7 @@ def test_anthropic_thinking_mode_streaming():
text_delta_seen = False text_delta_seen = False
with client.messages.stream( with client.messages.stream(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
max_tokens=2048, max_tokens=2048,
thinking={"type": "enabled", "budget_tokens": 1024}, # <- idiomatic thinking={"type": "enabled", "budget_tokens": 1024}, # <- idiomatic
messages=[{"role": "user", "content": "Explain briefly what 2+2 equals"}], messages=[{"role": "user", "content": "Explain briefly what 2+2 equals"}],

8
tests/e2e/test_openai_responses_api_client.py
View file

@ -489,7 +489,7 @@ def test_openai_responses_api_non_streaming_upstream_anthropic():
client = openai.OpenAI(api_key="test-key", base_url=f"{base_url}/v1") client = openai.OpenAI(api_key="test-key", base_url=f"{base_url}/v1")
resp = client.responses.create( resp = client.responses.create(
model="claude-sonnet-4-20250514", input="Hello, translate this via grok alias" model="claude-sonnet-4-6", input="Hello, translate this via grok alias"
) )
# Print the response content - handle both responses format and chat completions format # Print the response content - handle both responses format and chat completions format
@ -509,7 +509,7 @@ def test_openai_responses_api_with_streaming_upstream_anthropic():
# Simple streaming responses API request using a direct model (pass-through) # Simple streaming responses API request using a direct model (pass-through)
stream = client.responses.create( stream = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="Write a short haiku about coding", input="Write a short haiku about coding",
stream=True, stream=True,
) )
@ -566,7 +566,7 @@ def test_openai_responses_api_non_streaming_with_tools_upstream_anthropic():
] ]
resp = client.responses.create( resp = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="Call the echo tool", input="Call the echo tool",
tools=tools, tools=tools,
) )
@ -598,7 +598,7 @@ def test_openai_responses_api_streaming_with_tools_upstream_anthropic():
] ]
stream = client.responses.create( stream = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="Call the echo tool with hello_world", input="Call the echo tool with hello_world",
tools=tools, tools=tools,
stream=True, stream=True,

8
tests/e2e/test_openai_responses_api_client_with_state.py
View file

@ -35,7 +35,7 @@ def test_conversation_state_management_two_turn():
# Turn 1: Send initial message to Anthropic (non-OpenAI model) # Turn 1: Send initial message to Anthropic (non-OpenAI model)
logger.info("\n[TURN 1] Sending initial message...") logger.info("\n[TURN 1] Sending initial message...")
resp1 = client.responses.create( resp1 = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="My name is Alice and I like pizza.", input="My name is Alice and I like pizza.",
) )
@ -53,7 +53,7 @@ def test_conversation_state_management_two_turn():
f"\n[TURN 2] Sending follow-up with previous_response_id={response_id_1}" f"\n[TURN 2] Sending follow-up with previous_response_id={response_id_1}"
) )
resp2 = client.responses.create( resp2 = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="Please list all the messages you have received in our conversation, numbering each one.", input="Please list all the messages you have received in our conversation, numbering each one.",
previous_response_id=response_id_1, previous_response_id=response_id_1,
) )
@ -121,7 +121,7 @@ def test_conversation_state_management_two_turn_streaming():
# Turn 1: Send initial streaming message to Anthropic (non-OpenAI model) # Turn 1: Send initial streaming message to Anthropic (non-OpenAI model)
logger.info("\n[TURN 1] Sending initial streaming message...") logger.info("\n[TURN 1] Sending initial streaming message...")
stream1 = client.responses.create( stream1 = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="My name is Alice and I like pizza.", input="My name is Alice and I like pizza.",
stream=True, stream=True,
) )
@ -154,7 +154,7 @@ def test_conversation_state_management_two_turn_streaming():
f"\n[TURN 2] Sending follow-up streaming request with previous_response_id={response_id_1}" f"\n[TURN 2] Sending follow-up streaming request with previous_response_id={response_id_1}"
) )
stream2 = client.responses.create( stream2 = client.responses.create(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
input="Please list all the messages you have received in our conversation, numbering each one.", input="Please list all the messages you have received in our conversation, numbering each one.",
previous_response_id=response_id_1, previous_response_id=response_id_1,
stream=True, stream=True,

8
tests/e2e/test_prompt_gateway.py
View file

@ -395,7 +395,7 @@ def test_claude_v1_messages_api():
) )
message = client.messages.create( message = client.messages.create(
model="claude-sonnet-4-20250514", # Use working model from smoke test model="claude-sonnet-4-6", # Use working model from smoke test
max_tokens=50, max_tokens=50,
messages=[ messages=[
{ {
@ -414,7 +414,7 @@ def test_claude_v1_messages_api_streaming():
client = anthropic.Anthropic(api_key="test-key", base_url=base_url) client = anthropic.Anthropic(api_key="test-key", base_url=base_url)
with client.messages.stream( with client.messages.stream(
model="claude-sonnet-4-20250514", model="claude-sonnet-4-6",
max_tokens=50, max_tokens=50,
messages=[ messages=[
{ {
@ -525,7 +525,7 @@ def test_openai_gpt4o_mini_v1_messages_api_streaming():
def test_openai_client_with_claude_model_streaming(): def test_openai_client_with_claude_model_streaming():
"""Test OpenAI client using /v1/chat/completions API with Claude model (claude-sonnet-4-20250514) """Test OpenAI client using /v1/chat/completions API with Claude model (claude-sonnet-4-6)
This tests the transformation: Anthropic upstream -> OpenAI client format with proper chunk handling This tests the transformation: Anthropic upstream -> OpenAI client format with proper chunk handling
""" """
# Get the base URL from the LLM gateway endpoint # Get the base URL from the LLM gateway endpoint
@ -537,7 +537,7 @@ def test_openai_client_with_claude_model_streaming():
) )
stream = client.chat.completions.create( stream = client.chat.completions.create(
model="claude-sonnet-4-20250514", # Claude model via OpenAI client model="claude-sonnet-4-6", # Claude model via OpenAI client
max_tokens=50, max_tokens=50,
messages=[ messages=[
{ {