blindxfish/devplacepy
1
0
Fork 0
forked from retoor/devplacepy
Code Pull Requests Activity

Update

Browse Source
This commit is contained in:
retoor
2026-07-09 02:52:54 +02:00
parent 818568c609
commit 48bb6c2ec2
95 changed files with 6115 additions and 267 deletions
Download Patch File Download Diff File Expand all files Collapse all files
devplacepy/services/devii/actions/catalog/gateway.py
+21 -7
View File
@@ -27,7 +27,7 @@ GATEWAY_ACTIONS: tuple[Action, ...] = (
summary="Create or update a gateway provider (admin only)",
description=(
"Adds or updates a named upstream provider. base_url is the OpenAI-compatible "
"chat-completions endpoint; the embeddings endpoint is derived from it."
"chat-completions endpoint; the embeddings and images endpoints are derived from it."
),
handler="http",
requires_admin=True,
@@ -60,7 +60,8 @@ GATEWAY_ACTIONS: tuple[Action, ...] = (
summary="List OpenAI gateway model routes (admin only)",
description=(
"Returns JSON: every source-model route with its provider, target model, kind "
"(chat/embed), optional vision model, context window, and per-model pricing economy."
"(chat/embed/image), optional vision model, context window, and per-model pricing economy "
"(including any tiered/off-peak pricing configured on it)."
),
handler="http",
requires_admin=True,
@@ -73,9 +74,14 @@ GATEWAY_ACTIONS: tuple[Action, ...] = (
summary="Create or update a gateway model route (admin only)",
description=(
"Maps a requested source_model onto a provider + target_model, each with its own "
"pricing. kind is 'chat' or 'embed'. A vision_model adds image-to-text augmentation "
"for chat routes. Prices are USD per 1,000,000 tokens; chat uses cache-hit/cache-miss/"
"output, embeddings use input, vision uses input/output."
"pricing. kind is 'chat', 'embed', or 'image'. A vision_model adds image-to-text augmentation "
"for chat routes. Prices are USD per 1,000,000 tokens for chat/embed/vision; image routes "
"use price_input_per_m as a flat USD per generated image. Optionally, a route can also "
"charge a different (tier-2) rate once the request's input tokens exceed "
"context_tier_threshold_tokens, and/or apply a percentage discount during a fixed "
"UTC off-peak window - leave the tier2/off-peak fields unset to keep the flat rates "
"above at all times. off_peak_start_minute and off_peak_end_minute must be set "
"together (both or neither) or the call is rejected."
),
handler="http",
requires_admin=True,
@@ -83,14 +89,22 @@ GATEWAY_ACTIONS: tuple[Action, ...] = (
body("source_model", "Model name clients request.", required=True),
body("provider", "Provider name, or blank for the default upstream."),
body("target_model", "Model name sent upstream.", required=True),
body("kind", "Route kind: 'chat' or 'embed'."),
body("kind", "Route kind: 'chat', 'embed', or 'image'."),
body("vision_provider", "Provider for image description, or blank for the route provider."),
body("vision_model", "Vision model name (blank disables the merge)."),
Param(name="context_window", location="body", description="Max context tokens (0 = unknown).", required=False, type="integer"),
Param(name="price_cache_hit_per_m", location="body", description="USD per 1M cache-hit input tokens.", required=False, type="number"),
Param(name="price_cache_miss_per_m", location="body", description="USD per 1M cache-miss input tokens.", required=False, type="number"),
Param(name="price_output_per_m", location="body", description="USD per 1M output tokens.", required=False, type="number"),
Param(name="price_input_per_m", location="body", description="USD per 1M input tokens (embed/vision).", required=False, type="number"),
Param(name="price_input_per_m", location="body", description="USD per 1M input tokens (embed/vision), or flat USD per image for image routes.", required=False, type="number"),
Param(name="context_tier_threshold_tokens", location="body", description="Input tokens above which tier-2 rates apply (0 disables tiering).", required=False, type="integer"),
Param(name="price_cache_hit_per_m_tier2", location="body", description="Tier-2 USD per 1M cache-hit input tokens (unset = keep tier-1 rate above threshold).", required=False, type="number"),
Param(name="price_cache_miss_per_m_tier2", location="body", description="Tier-2 USD per 1M cache-miss input tokens (unset = keep tier-1 rate above threshold).", required=False, type="number"),
Param(name="price_output_per_m_tier2", location="body", description="Tier-2 USD per 1M output tokens (unset = keep tier-1 rate above threshold).", required=False, type="number"),
Param(name="price_input_per_m_tier2", location="body", description="Tier-2 USD per 1M input tokens, embed/vision (unset = keep tier-1 rate above threshold).", required=False, type="number"),
Param(name="off_peak_start_minute", location="body", description="Off-peak window start, UTC minutes since midnight (0-1439). Must be set together with off_peak_end_minute.", required=False, type="integer"),
Param(name="off_peak_end_minute", location="body", description="Off-peak window end, UTC minutes since midnight (0-1439). A value less than the start wraps past midnight.", required=False, type="integer"),
Param(name="off_peak_discount_pct", location="body", description="Percentage discount (0-100) applied to the active tier's rates during the off-peak window.", required=False, type="number"),
Param(name="is_active", location="body", description="Whether the route is active ('1' or '0').", required=False, type="boolean"),
),
),