apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-25 00:36:34 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

deploy: e5751d6b13

Browse source
This commit is contained in:
adilhafeez 2026-03-30 20:47:27 +00:00
parent 3912e68349
commit ecd4c36ec2
4 changed files with 176 additions and 221 deletions
Download patch file Download diff file Expand all files Collapse all files

21
_downloads/c86f9e8fb1f2994b1ba4a0b98481410e/plano_config_full_reference.yaml
View file

@ -36,35 +36,20 @@ model_providers:
# can select the best model for each request based on intent. Requires the
# Arch-Router model (or equivalent) to be configured in overrides.llm_routing_model.
# Each preference has a name (short label) and a description (used for intent matching).
- model: openai/gpt-4o
name: gpt-4o-coding # Optional friendly name to distinguish multiple entries for same model
access_key: $OPENAI_API_KEY
- model: groq/llama-3.3-70b-versatile
access_key: $GROQ_API_KEY
routing_preferences:
- name: code generation
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
- name: code review
description: reviewing, analyzing, and suggesting improvements to existing code
- model: anthropic/claude-sonnet-4-0
name: claude-sonnet-reasoning
access_key: $ANTHROPIC_API_KEY
routing_preferences:
- name: reasoning
description: complex multi-step reasoning, math, logic puzzles, and analytical tasks
# passthrough_auth: forwards the client's Authorization header upstream instead of
# using the configured access_key. Useful for LiteLLM or similar proxy setups.
- model: openai/gpt-4o-litellm
base_url: https://litellm.example.com
passthrough_auth: true
# provider_interface: specifies the API format when the provider doesn't match
# the default inferred from the model name. Supported: openai, claude, gemini,
# mistral, groq, deepseek, plano
- model: groq/llama-3.3-70b-versatile
access_key: $GROQ_API_KEY
provider_interface: groq
# Custom/self-hosted endpoint with explicit http_host override
- model: openai/llama-3.3-70b
base_url: https://api.custom-provider.com
@ -179,7 +164,7 @@ overrides:
# Trim conversation history to fit within the model's context window
optimize_context_window: true
# Use Plano's agent orchestrator for multi-agent request routing
use_agent_orchestrator: true
use_agent_orchestrator: false
# Connect timeout for upstream provider clusters (e.g., "5s", "10s"). Default: "5s"
upstream_connect_timeout: 10s
# Path to the trusted CA bundle for upstream TLS verification

23
includes/llms.txt
View file

@ -1,6 +1,6 @@
Plano Docs v0.4.14
llms.txt (auto-generated)
Generated (UTC): 2026-03-30T19:25:35.189116+00:00
Generated (UTC): 2026-03-30T20:47:23.688799+00:00
Table of contents
- Agents (concepts/agents)
@ -6332,35 +6332,20 @@ model_providers:
# can select the best model for each request based on intent. Requires the
# Arch-Router model (or equivalent) to be configured in overrides.llm_routing_model.
# Each preference has a name (short label) and a description (used for intent matching).
- model: openai/gpt-4o
name: gpt-4o-coding # Optional friendly name to distinguish multiple entries for same model
access_key: $OPENAI_API_KEY
- model: groq/llama-3.3-70b-versatile
access_key: $GROQ_API_KEY
routing_preferences:
- name: code generation
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
- name: code review
description: reviewing, analyzing, and suggesting improvements to existing code
- model: anthropic/claude-sonnet-4-0
name: claude-sonnet-reasoning
access_key: $ANTHROPIC_API_KEY
routing_preferences:
- name: reasoning
description: complex multi-step reasoning, math, logic puzzles, and analytical tasks
# passthrough_auth: forwards the client's Authorization header upstream instead of
# using the configured access_key. Useful for LiteLLM or similar proxy setups.
- model: openai/gpt-4o-litellm
base_url: https://litellm.example.com
passthrough_auth: true
# provider_interface: specifies the API format when the provider doesn't match
# the default inferred from the model name. Supported: openai, claude, gemini,
# mistral, groq, deepseek, plano
- model: groq/llama-3.3-70b-versatile
access_key: $GROQ_API_KEY
provider_interface: groq
# Custom/self-hosted endpoint with explicit http_host override
- model: openai/llama-3.3-70b
base_url: https://api.custom-provider.com
@ -6475,7 +6460,7 @@ overrides:
# Trim conversation history to fit within the model's context window
optimize_context_window: true
# Use Plano's agent orchestrator for multi-agent request routing
use_agent_orchestrator: true
use_agent_orchestrator: false
# Connect timeout for upstream provider clusters (e.g., "5s", "10s"). Default: "5s"
upstream_connect_timeout: 10s
# Path to the trusted CA bundle for upstream TLS verification

351
resources/configuration_reference.html
View file

@ -205,190 +205,175 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
</span><span id="line-36"><span class="linenos"> 36</span><span class="w"> </span><span class="c1"># can select the best model for each request based on intent. Requires the</span>
</span><span id="line-37"><span class="linenos"> 37</span><span class="w"> </span><span class="c1"># Arch-Router model (or equivalent) to be configured in overrides.llm_routing_model.</span>
</span><span id="line-38"><span class="linenos"> 38</span><span class="w"> </span><span class="c1"># Each preference has a name (short label) and a description (used for intent matching).</span>
</span><span id="line-39"><span class="linenos"> 39</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
</span><span id="line-40"><span class="linenos"> 40</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-coding</span><span class="w"> </span><span class="c1"># Optional friendly name to distinguish multiple entries for same model</span>
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
</span><span id="line-43"><span class="linenos"> 43</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code generation</span>
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">generating new code snippets, functions, or boilerplate based on user prompts or requirements</span>
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code review</span>
</span><span id="line-46"><span class="linenos"> 46</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reviewing, analyzing, and suggesting improvements to existing code</span>
</span><span id="line-47"><span class="linenos"> 47</span>
</span><span id="line-48"><span class="linenos"> 48</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-0</span>
</span><span id="line-49"><span class="linenos"> 49</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">claude-sonnet-reasoning</span>
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
</span><span id="line-52"><span class="linenos"> 52</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reasoning</span>
</span><span id="line-53"><span class="linenos"> 53</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">complex multi-step reasoning, math, logic puzzles, and analytical tasks</span>
</span><span id="line-54"><span class="linenos"> 54</span>
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="c1"># passthrough_auth: forwards the client's Authorization header upstream instead of</span>
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="c1"># using the configured access_key. Useful for LiteLLM or similar proxy setups.</span>
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-litellm</span>
</span><span id="line-58"><span class="linenos"> 58</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
</span><span id="line-59"><span class="linenos"> 59</span><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-60"><span class="linenos"> 60</span>
</span><span id="line-61"><span class="linenos"> 61</span><span class="w"> </span><span class="c1"># provider_interface: specifies the API format when the provider doesn't match</span>
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="c1"># the default inferred from the model name. Supported: openai, claude, gemini,</span>
</span><span id="line-63"><span class="linenos"> 63</span><span class="w"> </span><span class="c1"># mistral, groq, deepseek, plano</span>
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama-3.3-70b-versatile</span>
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
</span><span id="line-66"><span class="linenos"> 66</span><span class="w"> </span><span class="nt">provider_interface</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq</span>
</span><span id="line-67"><span class="linenos"> 67</span>
</span><span id="line-68"><span class="linenos"> 68</span><span class="w"> </span><span class="c1"># Custom/self-hosted endpoint with explicit http_host override</span>
</span><span id="line-69"><span class="linenos"> 69</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/llama-3.3-70b</span>
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://api.custom-provider.com</span>
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.custom-provider.com</span>
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$CUSTOM_API_KEY</span>
</span><span id="line-73"><span class="linenos"> 73</span>
</span><span id="line-74"><span class="linenos"> 74</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
</span><span id="line-75"><span class="linenos"> 75</span><span class="nt">model_aliases</span><span class="p">:</span>
</span><span id="line-76"><span class="linenos"> 76</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
</span><span id="line-77"><span class="linenos"> 77</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
</span><span id="line-78"><span class="linenos"> 78</span>
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
</span><span id="line-80"><span class="linenos"> 80</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-81"><span class="linenos"> 81</span>
</span><span id="line-82"><span class="linenos"> 82</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
</span><span id="line-83"><span class="linenos"> 83</span><span class="nt">listeners</span><span class="p">:</span>
</span><span id="line-84"><span class="linenos"> 84</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
</span><span id="line-85"><span class="linenos"> 85</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">agent</span>
</span><span id="line-86"><span class="linenos"> 86</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">travel_booking_service</span>
</span><span id="line-87"><span class="linenos"> 87</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8001</span>
</span><span id="line-88"><span class="linenos"> 88</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
</span><span id="line-89"><span class="linenos"> 89</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
</span><span id="line-91"><span class="linenos"> 91</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
</span><span id="line-92"><span class="linenos"> 92</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">virtual assistant for retrieval augmented generation tasks</span>
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span>
</span><span id="line-94"><span class="linenos"> 94</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-95"><span class="linenos"> 95</span>
</span><span id="line-96"><span class="linenos"> 96</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
</span><span id="line-97"><span class="linenos"> 97</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
</span><span id="line-98"><span class="linenos"> 98</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model_1</span>
</span><span id="line-99"><span class="linenos"> 99</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-100"><span class="linenos">100</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
</span><span id="line-101"><span class="linenos">101</span><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">30s</span><span class="w"> </span><span class="c1"># Request timeout (e.g. "30s", "60s")</span>
</span><span id="line-102"><span class="linenos">102</span><span class="w"> </span><span class="nt">max_retries</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Number of retries on upstream failure</span>
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied before forwarding to LLM</span>
</span><span id="line-104"><span class="linenos">104</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-105"><span class="linenos">105</span><span class="w"> </span><span class="nt">output_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied to LLM responses before returning to client</span>
</span><span id="line-106"><span class="linenos">106</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-107"><span class="linenos">107</span>
</span><span id="line-108"><span class="linenos">108</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
</span><span id="line-109"><span class="linenos">109</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt</span>
</span><span id="line-110"><span class="linenos">110</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt_function_listener</span>
</span><span id="line-111"><span class="linenos">111</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-112"><span class="linenos">112</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
</span><span id="line-39"><span class="linenos"> 39</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama-3.3-70b-versatile</span>
</span><span id="line-40"><span class="linenos"> 40</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code generation</span>
</span><span id="line-43"><span class="linenos"> 43</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">generating new code snippets, functions, or boilerplate based on user prompts or requirements</span>
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code review</span>
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reviewing, analyzing, and suggesting improvements to existing code</span>
</span><span id="line-46"><span class="linenos"> 46</span>
</span><span id="line-47"><span class="linenos"> 47</span><span class="w"> </span><span class="c1"># passthrough_auth: forwards the client's Authorization header upstream instead of</span>
</span><span id="line-48"><span class="linenos"> 48</span><span class="w"> </span><span class="c1"># using the configured access_key. Useful for LiteLLM or similar proxy setups.</span>
</span><span id="line-49"><span class="linenos"> 49</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-litellm</span>
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-52"><span class="linenos"> 52</span>
</span><span id="line-53"><span class="linenos"> 53</span><span class="w"> </span><span class="c1"># Custom/self-hosted endpoint with explicit http_host override</span>
</span><span id="line-54"><span class="linenos"> 54</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/llama-3.3-70b</span>
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://api.custom-provider.com</span>
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.custom-provider.com</span>
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$CUSTOM_API_KEY</span>
</span><span id="line-58"><span class="linenos"> 58</span>
</span><span id="line-59"><span class="linenos"> 59</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
</span><span id="line-60"><span class="linenos"> 60</span><span class="nt">model_aliases</span><span class="p">:</span>
</span><span id="line-61"><span class="linenos"> 61</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
</span><span id="line-63"><span class="linenos"> 63</span>
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-66"><span class="linenos"> 66</span>
</span><span id="line-67"><span class="linenos"> 67</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
</span><span id="line-68"><span class="linenos"> 68</span><span class="nt">listeners</span><span class="p">:</span>
</span><span id="line-69"><span class="linenos"> 69</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">agent</span>
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">travel_booking_service</span>
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8001</span>
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
</span><span id="line-74"><span class="linenos"> 74</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-75"><span class="linenos"> 75</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
</span><span id="line-76"><span class="linenos"> 76</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
</span><span id="line-77"><span class="linenos"> 77</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">virtual assistant for retrieval augmented generation tasks</span>
</span><span id="line-78"><span class="linenos"> 78</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span>
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-80"><span class="linenos"> 80</span>
</span><span id="line-81"><span class="linenos"> 81</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model_1</span>
</span><span id="line-84"><span class="linenos"> 84</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-85"><span class="linenos"> 85</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
</span><span id="line-86"><span class="linenos"> 86</span><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">30s</span><span class="w"> </span><span class="c1"># Request timeout (e.g. "30s", "60s")</span>
</span><span id="line-87"><span class="linenos"> 87</span><span class="w"> </span><span class="nt">max_retries</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span><span class="w"> </span><span class="c1"># Number of retries on upstream failure</span>
</span><span id="line-88"><span class="linenos"> 88</span><span class="w"> </span><span class="nt">input_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied before forwarding to LLM</span>
</span><span id="line-89"><span class="linenos"> 89</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">output_filters</span><span class="p">:</span><span class="w"> </span><span class="c1"># Filters applied to LLM responses before returning to client</span>
</span><span id="line-91"><span class="linenos"> 91</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
</span><span id="line-92"><span class="linenos"> 92</span>
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
</span><span id="line-94"><span class="linenos"> 94</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt</span>
</span><span id="line-95"><span class="linenos"> 95</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt_function_listener</span>
</span><span id="line-96"><span class="linenos"> 96</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
</span><span id="line-97"><span class="linenos"> 97</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
</span><span id="line-98"><span class="linenos"> 98</span>
</span><span id="line-99"><span class="linenos"> 99</span><span class="c1"># Reusable service endpoints</span>
</span><span id="line-100"><span class="linenos">100</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-101"><span class="linenos">101</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-102"><span class="linenos">102</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span><span id="line-104"><span class="linenos">104</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http</span><span class="w"> </span><span class="c1"># http or https</span>
</span><span id="line-105"><span class="linenos">105</span>
</span><span id="line-106"><span class="linenos">106</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
</span><span id="line-107"><span class="linenos">107</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
</span><span id="line-108"><span class="linenos">108</span>
</span><span id="line-109"><span class="linenos">109</span><span class="w"> </span><span class="nt">secure_service</span><span class="p">:</span>
</span><span id="line-110"><span class="linenos">110</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com:443</span>
</span><span id="line-111"><span class="linenos">111</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https</span>
</span><span id="line-112"><span class="linenos">112</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com</span><span class="w"> </span><span class="c1"># Override the Host header sent upstream</span>
</span><span id="line-113"><span class="linenos">113</span>
</span><span id="line-114"><span class="linenos">114</span><span class="c1"># Reusable service endpoints</span>
</span><span id="line-115"><span class="linenos">115</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-116"><span class="linenos">116</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-117"><span class="linenos">117</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
</span><span id="line-118"><span class="linenos">118</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span><span id="line-119"><span class="linenos">119</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http</span><span class="w"> </span><span class="c1"># http or https</span>
</span><span id="line-120"><span class="linenos">120</span>
</span><span id="line-121"><span class="linenos">121</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
</span><span id="line-122"><span class="linenos">122</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
</span><span id="line-123"><span class="linenos">123</span>
</span><span id="line-124"><span class="linenos">124</span><span class="w"> </span><span class="nt">secure_service</span><span class="p">:</span>
</span><span id="line-125"><span class="linenos">125</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com:443</span>
</span><span id="line-126"><span class="linenos">126</span><span class="w"> </span><span class="nt">protocol</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https</span>
</span><span id="line-127"><span class="linenos">127</span><span class="w"> </span><span class="nt">http_host</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">api.example.com</span><span class="w"> </span><span class="c1"># Override the Host header sent upstream</span>
</span><span id="line-128"><span class="linenos">128</span>
</span><span id="line-129"><span class="linenos">129</span><span class="c1"># Optional top-level system prompt applied to all prompt_targets</span>
</span><span id="line-130"><span class="linenos">130</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-131"><span class="linenos">131</span><span class="w"> </span><span class="no">You are a helpful assistant. Always respond concisely and accurately.</span>
</span><span id="line-132"><span class="linenos">132</span>
</span><span id="line-133"><span class="linenos">133</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
</span><span id="line-134"><span class="linenos">134</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-135"><span class="linenos">135</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">get_current_weather</span>
</span><span id="line-136"><span class="linenos">136</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Get current weather at a location.</span>
</span><span id="line-137"><span class="linenos">137</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-138"><span class="linenos">138</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">location</span>
</span><span id="line-139"><span class="linenos">139</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">The location to get the weather for</span>
</span><span id="line-140"><span class="linenos">140</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-141"><span class="linenos">141</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">string</span>
</span><span id="line-142"><span class="linenos">142</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
</span><span id="line-143"><span class="linenos">143</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">days</span>
</span><span id="line-144"><span class="linenos">144</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">the number of days for the request</span>
</span><span id="line-145"><span class="linenos">145</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-146"><span class="linenos">146</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">int</span>
</span><span id="line-147"><span class="linenos">147</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-148"><span class="linenos">148</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-149"><span class="linenos">149</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/weather</span>
</span><span id="line-150"><span class="linenos">150</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
</span><span id="line-151"><span class="linenos">151</span><span class="w"> </span><span class="c1"># Per-target system prompt (overrides top-level system_prompt for this target)</span>
</span><span id="line-152"><span class="linenos">152</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a weather expert. Provide accurate and concise weather information.</span>
</span><span id="line-153"><span class="linenos">153</span><span class="w"> </span><span class="c1"># auto_llm_dispatch_on_response: when true, the LLM is called again with the</span>
</span><span id="line-154"><span class="linenos">154</span><span class="w"> </span><span class="c1"># function response to produce a final natural-language answer for the user</span>
</span><span id="line-155"><span class="linenos">155</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-156"><span class="linenos">156</span>
</span><span id="line-157"><span class="linenos">157</span><span class="c1"># Rate limits - control token usage per model and request selector</span>
</span><span id="line-158"><span class="linenos">158</span><span class="nt">ratelimits</span><span class="p">:</span>
</span><span id="line-159"><span class="linenos">159</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
</span><span id="line-160"><span class="linenos">160</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-161"><span class="linenos">161</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-id</span><span class="w"> </span><span class="c1"># HTTP header key used to identify the rate-limit subject</span>
</span><span id="line-162"><span class="linenos">162</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="s">"*"</span><span class="w"> </span><span class="c1"># Wildcard matches any value; use a specific string to target one</span>
</span><span id="line-163"><span class="linenos">163</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-164"><span class="linenos">164</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100000</span><span class="w"> </span><span class="c1"># Maximum tokens allowed in the given time unit</span>
</span><span id="line-165"><span class="linenos">165</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">hour</span><span class="w"> </span><span class="c1"># Time unit: "minute", "hour", or "day"</span>
</span><span id="line-166"><span class="linenos">166</span>
</span><span id="line-167"><span class="linenos">167</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
</span><span id="line-168"><span class="linenos">168</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-169"><span class="linenos">169</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-id</span>
</span><span id="line-170"><span class="linenos">170</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">acme-corp</span>
</span><span id="line-171"><span class="linenos">171</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-172"><span class="linenos">172</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">500000</span>
</span><span id="line-173"><span class="linenos">173</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">day</span>
</span><span id="line-174"><span class="linenos">174</span>
</span><span id="line-175"><span class="linenos">175</span><span class="c1"># Global behavior overrides</span>
</span><span id="line-176"><span class="linenos">176</span><span class="nt">overrides</span><span class="p">:</span>
</span><span id="line-177"><span class="linenos">177</span><span class="w"> </span><span class="c1"># Threshold for routing a request to a prompt_target (0.0–1.0). Lower = more permissive.</span>
</span><span id="line-178"><span class="linenos">178</span><span class="w"> </span><span class="nt">prompt_target_intent_matching_threshold</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.7</span>
</span><span id="line-179"><span class="linenos">179</span><span class="w"> </span><span class="c1"># Trim conversation history to fit within the model's context window</span>
</span><span id="line-180"><span class="linenos">180</span><span class="w"> </span><span class="nt">optimize_context_window</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-181"><span class="linenos">181</span><span class="w"> </span><span class="c1"># Use Plano's agent orchestrator for multi-agent request routing</span>
</span><span id="line-182"><span class="linenos">182</span><span class="w"> </span><span class="nt">use_agent_orchestrator</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-183"><span class="linenos">183</span><span class="w"> </span><span class="c1"># Connect timeout for upstream provider clusters (e.g., "5s", "10s"). Default: "5s"</span>
</span><span id="line-184"><span class="linenos">184</span><span class="w"> </span><span class="nt">upstream_connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10s</span>
</span><span id="line-185"><span class="linenos">185</span><span class="w"> </span><span class="c1"># Path to the trusted CA bundle for upstream TLS verification</span>
</span><span id="line-186"><span class="linenos">186</span><span class="w"> </span><span class="nt">upstream_tls_ca_path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/etc/ssl/certs/ca-certificates.crt</span>
</span><span id="line-187"><span class="linenos">187</span><span class="w"> </span><span class="c1"># Model used for intent-based LLM routing (must be listed in model_providers)</span>
</span><span id="line-188"><span class="linenos">188</span><span class="w"> </span><span class="nt">llm_routing_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Arch-Router</span>
</span><span id="line-189"><span class="linenos">189</span><span class="w"> </span><span class="c1"># Model used for agent orchestration (must be listed in model_providers)</span>
</span><span id="line-190"><span class="linenos">190</span><span class="w"> </span><span class="nt">agent_orchestration_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Plano-Orchestrator</span>
</span><span id="line-191"><span class="linenos">191</span>
</span><span id="line-192"><span class="linenos">192</span><span class="c1"># State storage for multi-turn conversation history</span>
</span><span id="line-193"><span class="linenos">193</span><span class="nt">state_storage</span><span class="p">:</span>
</span><span id="line-194"><span class="linenos">194</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">memory</span><span class="w"> </span><span class="c1"># "memory" (in-process) or "postgres" (persistent)</span>
</span><span id="line-195"><span class="linenos">195</span><span class="w"> </span><span class="c1"># connection_string is required when type is postgres.</span>
</span><span id="line-196"><span class="linenos">196</span><span class="w"> </span><span class="c1"># Supports environment variable substitution: $VAR or ${VAR}</span>
</span><span id="line-197"><span class="linenos">197</span><span class="w"> </span><span class="c1"># connection_string: postgresql://user:$DB_PASS@localhost:5432/plano</span>
</span><span id="line-198"><span class="linenos">198</span>
</span><span id="line-199"><span class="linenos">199</span><span class="c1"># Input guardrails applied globally to all incoming requests</span>
</span><span id="line-200"><span class="linenos">200</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-201"><span class="linenos">201</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-202"><span class="linenos">202</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-203"><span class="linenos">203</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-204"><span class="linenos">204</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"I'm</span><span class="nv"> </span><span class="s">sorry,</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can't</span><span class="nv"> </span><span class="s">help</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">that</span><span class="nv"> </span><span class="s">request."</span>
</span><span id="line-205"><span class="linenos">205</span>
</span><span id="line-206"><span class="linenos">206</span><span class="c1"># OpenTelemetry tracing configuration</span>
</span><span id="line-207"><span class="linenos">207</span><span class="nt">tracing</span><span class="p">:</span>
</span><span id="line-208"><span class="linenos">208</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
</span><span id="line-209"><span class="linenos">209</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
</span><span id="line-210"><span class="linenos">210</span><span class="w"> </span><span class="c1"># Include internal Plano spans in traces</span>
</span><span id="line-211"><span class="linenos">211</span><span class="w"> </span><span class="nt">trace_arch_internal</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-212"><span class="linenos">212</span><span class="w"> </span><span class="c1"># gRPC endpoint for OpenTelemetry collector (e.g., Jaeger, Tempo)</span>
</span><span id="line-213"><span class="linenos">213</span><span class="w"> </span><span class="nt">opentracing_grpc_endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:4317</span>
</span><span id="line-214"><span class="linenos">214</span><span class="w"> </span><span class="nt">span_attributes</span><span class="p">:</span>
</span><span id="line-215"><span class="linenos">215</span><span class="w"> </span><span class="c1"># Propagate request headers whose names start with these prefixes as span attributes</span>
</span><span id="line-216"><span class="linenos">216</span><span class="w"> </span><span class="nt">header_prefixes</span><span class="p">:</span>
</span><span id="line-217"><span class="linenos">217</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-</span>
</span><span id="line-218"><span class="linenos">218</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-</span>
</span><span id="line-219"><span class="linenos">219</span><span class="w"> </span><span class="c1"># Static key/value pairs added to every span</span>
</span><span id="line-220"><span class="linenos">220</span><span class="w"> </span><span class="nt">static</span><span class="p">:</span>
</span><span id="line-221"><span class="linenos">221</span><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">production</span>
</span><span id="line-222"><span class="linenos">222</span><span class="w"> </span><span class="nt">service.team</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">platform</span>
</span><span id="line-114"><span class="linenos">114</span><span class="c1"># Optional top-level system prompt applied to all prompt_targets</span>
</span><span id="line-115"><span class="linenos">115</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-116"><span class="linenos">116</span><span class="w"> </span><span class="no">You are a helpful assistant. Always respond concisely and accurately.</span>
</span><span id="line-117"><span class="linenos">117</span>
</span><span id="line-118"><span class="linenos">118</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
</span><span id="line-119"><span class="linenos">119</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-120"><span class="linenos">120</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">get_current_weather</span>
</span><span id="line-121"><span class="linenos">121</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Get current weather at a location.</span>
</span><span id="line-122"><span class="linenos">122</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-123"><span class="linenos">123</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">location</span>
</span><span id="line-124"><span class="linenos">124</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">The location to get the weather for</span>
</span><span id="line-125"><span class="linenos">125</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-126"><span class="linenos">126</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">string</span>
</span><span id="line-127"><span class="linenos">127</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
</span><span id="line-128"><span class="linenos">128</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">days</span>
</span><span id="line-129"><span class="linenos">129</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">the number of days for the request</span>
</span><span id="line-130"><span class="linenos">130</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-131"><span class="linenos">131</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">int</span>
</span><span id="line-132"><span class="linenos">132</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-133"><span class="linenos">133</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-134"><span class="linenos">134</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/weather</span>
</span><span id="line-135"><span class="linenos">135</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
</span><span id="line-136"><span class="linenos">136</span><span class="w"> </span><span class="c1"># Per-target system prompt (overrides top-level system_prompt for this target)</span>
</span><span id="line-137"><span class="linenos">137</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a weather expert. Provide accurate and concise weather information.</span>
</span><span id="line-138"><span class="linenos">138</span><span class="w"> </span><span class="c1"># auto_llm_dispatch_on_response: when true, the LLM is called again with the</span>
</span><span id="line-139"><span class="linenos">139</span><span class="w"> </span><span class="c1"># function response to produce a final natural-language answer for the user</span>
</span><span id="line-140"><span class="linenos">140</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-141"><span class="linenos">141</span>
</span><span id="line-142"><span class="linenos">142</span><span class="c1"># Rate limits - control token usage per model and request selector</span>
</span><span id="line-143"><span class="linenos">143</span><span class="nt">ratelimits</span><span class="p">:</span>
</span><span id="line-144"><span class="linenos">144</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
</span><span id="line-145"><span class="linenos">145</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-146"><span class="linenos">146</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-id</span><span class="w"> </span><span class="c1"># HTTP header key used to identify the rate-limit subject</span>
</span><span id="line-147"><span class="linenos">147</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="s">"*"</span><span class="w"> </span><span class="c1"># Wildcard matches any value; use a specific string to target one</span>
</span><span id="line-148"><span class="linenos">148</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-149"><span class="linenos">149</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100000</span><span class="w"> </span><span class="c1"># Maximum tokens allowed in the given time unit</span>
</span><span id="line-150"><span class="linenos">150</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">hour</span><span class="w"> </span><span class="c1"># Time unit: "minute", "hour", or "day"</span>
</span><span id="line-151"><span class="linenos">151</span>
</span><span id="line-152"><span class="linenos">152</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
</span><span id="line-153"><span class="linenos">153</span><span class="w"> </span><span class="nt">selector</span><span class="p">:</span>
</span><span id="line-154"><span class="linenos">154</span><span class="w"> </span><span class="nt">key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-id</span>
</span><span id="line-155"><span class="linenos">155</span><span class="w"> </span><span class="nt">value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">acme-corp</span>
</span><span id="line-156"><span class="linenos">156</span><span class="w"> </span><span class="nt">limit</span><span class="p">:</span>
</span><span id="line-157"><span class="linenos">157</span><span class="w"> </span><span class="nt">tokens</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">500000</span>
</span><span id="line-158"><span class="linenos">158</span><span class="w"> </span><span class="nt">unit</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">day</span>
</span><span id="line-159"><span class="linenos">159</span>
</span><span id="line-160"><span class="linenos">160</span><span class="c1"># Global behavior overrides</span>
</span><span id="line-161"><span class="linenos">161</span><span class="nt">overrides</span><span class="p">:</span>
</span><span id="line-162"><span class="linenos">162</span><span class="w"> </span><span class="c1"># Threshold for routing a request to a prompt_target (0.0–1.0). Lower = more permissive.</span>
</span><span id="line-163"><span class="linenos">163</span><span class="w"> </span><span class="nt">prompt_target_intent_matching_threshold</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.7</span>
</span><span id="line-164"><span class="linenos">164</span><span class="w"> </span><span class="c1"># Trim conversation history to fit within the model's context window</span>
</span><span id="line-165"><span class="linenos">165</span><span class="w"> </span><span class="nt">optimize_context_window</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-166"><span class="linenos">166</span><span class="w"> </span><span class="c1"># Use Plano's agent orchestrator for multi-agent request routing</span>
</span><span id="line-167"><span class="linenos">167</span><span class="w"> </span><span class="nt">use_agent_orchestrator</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-168"><span class="linenos">168</span><span class="w"> </span><span class="c1"># Connect timeout for upstream provider clusters (e.g., "5s", "10s"). Default: "5s"</span>
</span><span id="line-169"><span class="linenos">169</span><span class="w"> </span><span class="nt">upstream_connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10s</span>
</span><span id="line-170"><span class="linenos">170</span><span class="w"> </span><span class="c1"># Path to the trusted CA bundle for upstream TLS verification</span>
</span><span id="line-171"><span class="linenos">171</span><span class="w"> </span><span class="nt">upstream_tls_ca_path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/etc/ssl/certs/ca-certificates.crt</span>
</span><span id="line-172"><span class="linenos">172</span><span class="w"> </span><span class="c1"># Model used for intent-based LLM routing (must be listed in model_providers)</span>
</span><span id="line-173"><span class="linenos">173</span><span class="w"> </span><span class="nt">llm_routing_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Arch-Router</span>
</span><span id="line-174"><span class="linenos">174</span><span class="w"> </span><span class="c1"># Model used for agent orchestration (must be listed in model_providers)</span>
</span><span id="line-175"><span class="linenos">175</span><span class="w"> </span><span class="nt">agent_orchestration_model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Plano-Orchestrator</span>
</span><span id="line-176"><span class="linenos">176</span>
</span><span id="line-177"><span class="linenos">177</span><span class="c1"># State storage for multi-turn conversation history</span>
</span><span id="line-178"><span class="linenos">178</span><span class="nt">state_storage</span><span class="p">:</span>
</span><span id="line-179"><span class="linenos">179</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">memory</span><span class="w"> </span><span class="c1"># "memory" (in-process) or "postgres" (persistent)</span>
</span><span id="line-180"><span class="linenos">180</span><span class="w"> </span><span class="c1"># connection_string is required when type is postgres.</span>
</span><span id="line-181"><span class="linenos">181</span><span class="w"> </span><span class="c1"># Supports environment variable substitution: $VAR or ${VAR}</span>
</span><span id="line-182"><span class="linenos">182</span><span class="w"> </span><span class="c1"># connection_string: postgresql://user:$DB_PASS@localhost:5432/plano</span>
</span><span id="line-183"><span class="linenos">183</span>
</span><span id="line-184"><span class="linenos">184</span><span class="c1"># Input guardrails applied globally to all incoming requests</span>
</span><span id="line-185"><span class="linenos">185</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-186"><span class="linenos">186</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-187"><span class="linenos">187</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-188"><span class="linenos">188</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-189"><span class="linenos">189</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"I'm</span><span class="nv"> </span><span class="s">sorry,</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can't</span><span class="nv"> </span><span class="s">help</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">that</span><span class="nv"> </span><span class="s">request."</span>
</span><span id="line-190"><span class="linenos">190</span>
</span><span id="line-191"><span class="linenos">191</span><span class="c1"># OpenTelemetry tracing configuration</span>
</span><span id="line-192"><span class="linenos">192</span><span class="nt">tracing</span><span class="p">:</span>
</span><span id="line-193"><span class="linenos">193</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
</span><span id="line-194"><span class="linenos">194</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
</span><span id="line-195"><span class="linenos">195</span><span class="w"> </span><span class="c1"># Include internal Plano spans in traces</span>
</span><span id="line-196"><span class="linenos">196</span><span class="w"> </span><span class="nt">trace_arch_internal</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-197"><span class="linenos">197</span><span class="w"> </span><span class="c1"># gRPC endpoint for OpenTelemetry collector (e.g., Jaeger, Tempo)</span>
</span><span id="line-198"><span class="linenos">198</span><span class="w"> </span><span class="nt">opentracing_grpc_endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://localhost:4317</span>
</span><span id="line-199"><span class="linenos">199</span><span class="w"> </span><span class="nt">span_attributes</span><span class="p">:</span>
</span><span id="line-200"><span class="linenos">200</span><span class="w"> </span><span class="c1"># Propagate request headers whose names start with these prefixes as span attributes</span>
</span><span id="line-201"><span class="linenos">201</span><span class="w"> </span><span class="nt">header_prefixes</span><span class="p">:</span>
</span><span id="line-202"><span class="linenos">202</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-user-</span>
</span><span id="line-203"><span class="linenos">203</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">x-org-</span>
</span><span id="line-204"><span class="linenos">204</span><span class="w"> </span><span class="c1"># Static key/value pairs added to every span</span>
</span><span id="line-205"><span class="linenos">205</span><span class="w"> </span><span class="nt">static</span><span class="p">:</span>
</span><span id="line-206"><span class="linenos">206</span><span class="w"> </span><span class="nt">environment</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">production</span>
</span><span id="line-207"><span class="linenos">207</span><span class="w"> </span><span class="nt">service.team</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">platform</span>
</span></code></pre></div>
</div>
</div>

2
searchindex.js
View file

File diff suppressed because one or more lines are too long