fix: inference geo cost on anthropic by TejasGhatte · Pull Request #5072 · maximhq/bifrost

TejasGhatte · 2026-07-09T15:09:22Z

Summary

Adds support for Anthropic's data-residency billing feature (inference_geo). When Anthropic serves inference in the US (inference_geo: "us"), a 1.1x multiplier is applied to all token and cache costs. This PR propagates the inference_geo field through the full response pipeline (chat, responses, streaming, passthrough) and wires it into the cost computation layer, including a new database column and UI override field.

A secondary fix ensures Anthropic server-tool web search request counts (ServerToolUse.WebSearchRequests) are correctly forwarded and billed in both streaming and non-streaming paths, where previously the count could be lost when the terminal chunk overwrote the accumulated usage.

Changes

inference_geo propagation: InferenceGeo *string added to BifrostChatResponse, BifrostResponsesResponse, and BifrostPassthroughUsage. The field is forwarded from AnthropicUsage in all conversion paths: non-streaming chat, non-streaming responses, streaming chat (captured across events and set on the final chunk), streaming responses (message_delta), and passthrough.
Data-residency multiplier in cost computation: serviceTier gains an inferenceGeoUS bool flag. tierFromResponse now accepts and evaluates inferenceGeo. computeTextCost applies InferenceGeoUSMultiplier to token/cache costs only — the flat per-search fee is intentionally excluded.
Database migration: migrationAddInferenceGeoMultiplierColumn adds inference_geo_us_multiplier to TableModelPricing. The column is included in the pricing sync update list and mapped through convertEntryToTablePricing / convertTablePricingToEntry.
Web search billing fix: accumulateAnthropicResponsesUsage now carries ServerToolUse.WebSearchRequests into the accumulator so the count survives the terminal-chunk overwrite on streamed Responses requests. The non-streaming chat converter also forwards the count into CompletionTokensDetails.NumSearchQueries.
UI: inference_geo_us_multiplier added to the custom pricing override sheet and PricingOverridePatch TypeScript type.
Tests: New unit tests cover the accumulator web-search fix, chat/responses converter forwarding of InferenceGeo and web search counts, multiplier application (including the no-multiplier-column safe no-op), and tierFromResponse geo detection (case-insensitive).

Type of change

Affected areas

How to test

# Core/Transports
go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/...

# UI
cd ui
pnpm i || npm i
pnpm build || npm run build

To validate end-to-end: send a request to an Anthropic model with data residency enabled. The response should include inference_geo: "us" and the computed cost should reflect the 1.1x multiplier on token/cache costs, with the per-search fee unchanged.

Breaking changes

Yes
No

Security considerations

No auth, secrets, or PII implications. The inference_geo value is sourced from Anthropic's API response and used only for billing computation.

Checklist

I read docs/contributing/README.md and followed the guidelines
I added/updated tests where appropriate
I updated documentation where needed
I verified builds succeed (Go and UI)
I verified the CI pipeline passes locally if applicable

coderabbitai · 2026-07-09T15:09:29Z

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 11 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 72e839ac-d4b4-438a-8fe3-dd069ab9010f

📥 Commits

Reviewing files that changed from the base of the PR and between aa19027 and c1a6a91.

📒 Files selected for processing (17)

core/providers/anthropic/anthropic.go
core/providers/anthropic/chat.go
core/providers/anthropic/passthrough_usage.go
core/providers/anthropic/responses.go
core/providers/anthropic/utils_test.go
core/schemas/chatcompletions.go
core/schemas/passthrough.go
core/schemas/responses.go
framework/configstore/migrations.go
framework/configstore/rdb.go
framework/configstore/tables/modelpricing.go
framework/modelcatalog/datasheet/cost.go
framework/modelcatalog/datasheet/cost_test.go
framework/modelcatalog/datasheet/overrides.go
framework/modelcatalog/datasheet/types.go
ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx
ui/lib/types/governance.ts

📝 Walkthrough

Walkthrough

Adds Anthropic inference_geo and web-search billing support: provider conversions forward inference_geo and web-search counts into Bifrost schemas and streaming outputs, pricing storage gains an inference_geo multiplier column, cost calculation applies it to token costs, and UI pricing overrides expose the new field.

Changes

Anthropic Inference Geo and Web Search Billing

Layer / File(s)	Summary
Schema fields for InferenceGeo and search queries `core/schemas/chatcompletions.go`, `core/schemas/responses.go`, `core/schemas/passthrough.go`	Adds optional `InferenceGeo` fields to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage`.
Anthropic streaming usage accumulation `core/providers/anthropic/anthropic.go`	Streaming usage accounting maps web search requests into `NumSearchQueries` and carries served `Speed`/`InferenceGeo` into final streamed chunks.
Non-streaming conversion and passthrough usage `core/providers/anthropic/chat.go`, `core/providers/anthropic/responses.go`, `core/providers/anthropic/passthrough_usage.go`, `core/providers/anthropic/utils_test.go`	Chat/responses conversion and passthrough usage preserve `InferenceGeo` and web search counts, with tests covering the forwarding behavior and terminal streamed chunk reconstruction.
Model pricing column and migration `framework/configstore/tables/modelpricing.go`, `framework/configstore/migrations.go`, `framework/configstore/rdb.go`	Adds `InferenceGeoUSMultiplier` to model pricing storage, migration, and pricing sync updates.
Cost computation and tiering `framework/modelcatalog/datasheet/cost.go`, `framework/modelcatalog/datasheet/types.go`, `framework/modelcatalog/datasheet/overrides.go`, `framework/modelcatalog/datasheet/cost_test.go`	Adds geo-aware tiering and applies the multiplier to token costs, while propagating the new field through datasheet types, overrides, and tests.
UI pricing override support `ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx`, `ui/lib/types/governance.ts`	Adds `inference_geo_us_multiplier` to pricing override field definitions and patch typing.

Estimated code review effort: 4 (Complex) | ~60 minutes

Sequence Diagram(s)

sequenceDiagram
  participant AnthropicStreamHandler
  participant UsageAccumulator
  participant Client
  AnthropicStreamHandler->>UsageAccumulator: usageToProcess (WebSearchRequests, Speed, InferenceGeo)
  UsageAccumulator-->>AnthropicStreamHandler: NumSearchQueries, servedSpeed, servedInferenceGeo
  AnthropicStreamHandler->>Client: final chunk with response.Speed and response.InferenceGeo

Possibly related PRs

maximhq/bifrost#4842: Both PRs modify Anthropic Responses streaming usage accounting in core/providers/anthropic/anthropic.go.
maximhq/bifrost#4917: Both PRs modify framework/modelcatalog/datasheet/cost.go and its related cost tests.
maximhq/bifrost#3829: Both PRs touch model pricing storage and sync behavior around TableModelPricing.

Suggested reviewers: akshaydeo, danpiths, roroghost17, Pratham-Mishra04

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 70.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Title check	✅ Passed	The title concisely and accurately summarizes the main change: Anthropic inference geo cost handling.
Description check	✅ Passed	The description covers summary, changes, testing, risk, and checklist items, with only minor omissions like screenshots and related issues.

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch 07-09-fix_inference_geo_cost_on_anthropic

_{Comment @coderabbitai help to get the list of available commands.}

TejasGhatte · 2026-07-09T15:09:37Z

fix: service tier in openai chat completion #5073
fix: inference geo cost on anthropic #5072 👈 (View in Graphite)
fix: annthropic cache rate for fast mode #5063
dev

This stack of pull requests is managed by Graphite. Learn more about stacking.

greptile-apps · 2026-07-09T15:12:06Z

Confidence Score: 4/5

This is close, but the compaction billing path should be fixed before merging.

The main Anthropic chat, responses, streaming, passthrough, pricing, and UI paths are wired through.
Compaction responses with US geography can still skip the new multiplier.
The remaining issue can cause incorrect billing for token and cache costs.

framework/modelcatalog/datasheet/cost.go and the compaction response schema

Important Files Changed

Filename	Overview
core/providers/anthropic/anthropic.go	Captures Anthropic streaming usage modifiers and web-search counts for final billing chunks.
core/providers/anthropic/responses.go	Forwards `inference_geo` from Anthropic Responses conversions.
framework/modelcatalog/datasheet/cost.go	Adds geo multiplier billing for text costs, while compaction cost extraction still omits served geography.
framework/configstore/migrations.go	Adds a nullable pricing column for the inference geo multiplier.
ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx	Adds the inference geo multiplier field to custom pricing overrides.

_{Reviews (3): Last reviewed commit: "fix: inference geo cost on anthropic" | Re-trigger Greptile}

CLAassistant · 2026-07-09T15:14:14Z

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

coderabbitai

🧹 Nitpick comments (1)

core/providers/anthropic/anthropic.go (1)
886-889: 📐 Maintainability & Code Quality | 🔵 Trivial

Web search accumulation duplicated across two sites; minor pointer-idiom inconsistency.

The max-tracking-and-set logic for NumSearchQueries here (lines 966-973) is structurally identical to accumulateAnthropicResponsesUsage (lines 624-643) but operates on BifrostLLMUsage instead of ResponsesResponseUsage. Also, &n is used at line 971 instead of schemas.Ptr(n), which is used consistently in the sibling accumulator function in this same file.

Not blocking — behavior is correct in both places — but consider extracting a small shared helper to avoid future divergence, and align on schemas.Ptr() for consistency.

Also applies to: 965-980, 1142-1148
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@core/providers/anthropic/anthropic.go` around lines 886 - 889, The
`NumSearchQueries` max-tracking and assignment logic is duplicated between
`accumulateAnthropicResponsesUsage` and the `BifrostLLMUsage` accumulator in
`anthropic.go`, and the latter also uses `&n` instead of the file’s consistent
`schemas.Ptr()` pattern. Extract the shared web-search accumulation into a small
helper that both paths call, keep the max-of-values behavior identical for both
usage types, and update the pointer assignment in the `BifrostLLMUsage` path to
use `schemas.Ptr()` so the two accumulator sites stay aligned.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@core/providers/anthropic/anthropic.go`:
- Around line 886-889: The `NumSearchQueries` max-tracking and assignment logic
is duplicated between `accumulateAnthropicResponsesUsage` and the
`BifrostLLMUsage` accumulator in `anthropic.go`, and the latter also uses `&n`
instead of the file’s consistent `schemas.Ptr()` pattern. Extract the shared
web-search accumulation into a small helper that both paths call, keep the
max-of-values behavior identical for both usage types, and update the pointer
assignment in the `BifrostLLMUsage` path to use `schemas.Ptr()` so the two
accumulator sites stay aligned.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 9ff0ab71-3796-492c-85cf-41f43044f743

📥 Commits

Reviewing files that changed from the base of the PR and between 406f85a and 7b0bd1e.

📒 Files selected for processing (17)

core/providers/anthropic/anthropic.go
core/providers/anthropic/chat.go
core/providers/anthropic/passthrough_usage.go
core/providers/anthropic/responses.go
core/providers/anthropic/utils_test.go
core/schemas/chatcompletions.go
core/schemas/passthrough.go
core/schemas/responses.go
framework/configstore/migrations.go
framework/configstore/rdb.go
framework/configstore/tables/modelpricing.go
framework/modelcatalog/datasheet/cost.go
framework/modelcatalog/datasheet/cost_test.go
framework/modelcatalog/datasheet/overrides.go
framework/modelcatalog/datasheet/types.go
ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx
ui/lib/types/governance.ts

coderabbitai

🧹 Nitpick comments (1)

core/providers/anthropic/anthropic.go (1)
970-971: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

Minor: use schemas.Ptr for pointer consistency.

accumulateAnthropicResponsesUsage (Line 633/640) uses schemas.Ptr(n) for the same field, but here the address operator is used. Aligning both keeps the pattern consistent within this change.
-				if n := usageToProcess.ServerToolUse.WebSearchRequests; usage.CompletionTokensDetails.NumSearchQueries == nil || n > *usage.CompletionTokensDetails.NumSearchQueries {
-					usage.CompletionTokensDetails.NumSearchQueries = &n
-				}
+				if n := usageToProcess.ServerToolUse.WebSearchRequests; usage.CompletionTokensDetails.NumSearchQueries == nil || n > *usage.CompletionTokensDetails.NumSearchQueries {
+					usage.CompletionTokensDetails.NumSearchQueries = schemas.Ptr(n)
+				}
Based on learnings, prefer bifrost.Ptr()/schemas.Ptr() over the address operator & even when & is syntactically valid, applied consistently across code paths.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@core/providers/anthropic/anthropic.go` around lines 970 - 971, The
NumSearchQueries assignment in accumulateAnthropicResponsesUsage is using the
address operator directly instead of the pointer helper used elsewhere in this
change. Update the WebSearchRequests handling in the Anthropic usage
accumulation path to use schemas.Ptr(n) when setting
CompletionTokensDetails.NumSearchQueries, matching the existing pointer style
used in the same function and keeping pointer creation consistent across code
paths.
Source: Learnings

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@core/providers/anthropic/anthropic.go`:
- Around line 970-971: The NumSearchQueries assignment in
accumulateAnthropicResponsesUsage is using the address operator directly instead
of the pointer helper used elsewhere in this change. Update the
WebSearchRequests handling in the Anthropic usage accumulation path to use
schemas.Ptr(n) when setting CompletionTokensDetails.NumSearchQueries, matching
the existing pointer style used in the same function and keeping pointer
creation consistent across code paths.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 5a9f7e52-a220-4800-9fc9-774e3cdfbf77

📥 Commits

Reviewing files that changed from the base of the PR and between 7b0bd1e and aa19027.

📒 Files selected for processing (17)

core/providers/anthropic/anthropic.go
core/providers/anthropic/chat.go
core/providers/anthropic/passthrough_usage.go
core/providers/anthropic/responses.go
core/providers/anthropic/utils_test.go
core/schemas/chatcompletions.go
core/schemas/passthrough.go
core/schemas/responses.go
framework/configstore/migrations.go
framework/configstore/rdb.go
framework/configstore/tables/modelpricing.go
framework/modelcatalog/datasheet/cost.go
framework/modelcatalog/datasheet/cost_test.go
framework/modelcatalog/datasheet/overrides.go
framework/modelcatalog/datasheet/types.go
ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx
ui/lib/types/governance.ts

🚧 Files skipped from review as they are similar to previous changes (15)

ui/lib/types/governance.ts
core/schemas/responses.go
core/schemas/chatcompletions.go
framework/modelcatalog/datasheet/overrides.go
framework/configstore/tables/modelpricing.go
core/providers/anthropic/responses.go
framework/configstore/rdb.go
core/schemas/passthrough.go
framework/modelcatalog/datasheet/types.go
core/providers/anthropic/chat.go
core/providers/anthropic/passthrough_usage.go
ui/app/workspace/custom-pricing/overrides/pricingOverrideSheet.tsx
framework/configstore/migrations.go
framework/modelcatalog/datasheet/cost.go
framework/modelcatalog/datasheet/cost_test.go

akshaydeo · 2026-07-09T16:10:22Z

Merge activity

Jul 9, 4:10 PM UTC: A user started a stack merge that includes this pull request via Graphite.
Jul 9, 4:12 PM UTC: Graphite rebased this pull request as part of a merge.
Jul 9, 4:13 PM UTC: Graphite couldn't merge this PR because it was not satisfying all requirements (PR does not have required approvals).
Jul 9, 4:27 PM UTC: A user started a stack merge that includes this pull request via Graphite.
Jul 9, 4:27 PM UTC: @akshaydeo merged this pull request with Graphite.

The base branch was changed.

## Summary Adds support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves inference in the US (`inference_geo: "us"`), a 1.1x multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field through the full response pipeline (chat, responses, streaming, passthrough) and wires it into the cost computation layer, including a new database column and UI override field. A secondary fix ensures Anthropic server-tool web search request counts (`ServerToolUse.WebSearchRequests`) are correctly forwarded and billed in both streaming and non-streaming paths, where previously the count could be lost when the terminal chunk overwrote the accumulated usage. ## Changes - **`inference_geo` propagation**: `InferenceGeo *string` added to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage`. The field is forwarded from `AnthropicUsage` in all conversion paths: non-streaming chat, non-streaming responses, streaming chat (captured across events and set on the final chunk), streaming responses (`message_delta`), and passthrough. - **Data-residency multiplier in cost computation**: `serviceTier` gains an `inferenceGeoUS bool` flag. `tierFromResponse` now accepts and evaluates `inferenceGeo`. `computeTextCost` applies `InferenceGeoUSMultiplier` to token/cache costs only — the flat per-search fee is intentionally excluded. - **Database migration**: `migrationAddInferenceGeoMultiplierColumn` adds `inference_geo_us_multiplier` to `TableModelPricing`. The column is included in the pricing sync update list and mapped through `convertEntryToTablePricing` / `convertTablePricingToEntry`. - **Web search billing fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into the accumulator so the count survives the terminal-chunk overwrite on streamed Responses requests. The non-streaming chat converter also forwards the count into `CompletionTokensDetails.NumSearchQueries`. - **UI**: `inference_geo_us_multiplier` added to the custom pricing override sheet and `PricingOverridePatch` TypeScript type. - **Tests**: New unit tests cover the accumulator web-search fix, chat/responses converter forwarding of `InferenceGeo` and web search counts, multiplier application (including the no-multiplier-column safe no-op), and `tierFromResponse` geo detection (case-insensitive). ## Type of change - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI ## Affected areas - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ## How to test ```sh # Core/Transports go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... # UI cd ui pnpm i || npm i pnpm build || npm run build ``` To validate end-to-end: send a request to an Anthropic model with data residency enabled. The response should include `inference_geo: "us"` and the computed cost should reflect the 1.1x multiplier on token/cache costs, with the per-search fee unchanged. ## Breaking changes - [ ] Yes - [x] No ## Security considerations No auth, secrets, or PII implications. The `inference_geo` value is sourced from Anthropic's API response and used only for billing computation. ## Checklist - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

## Summary Adds end-to-end support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves a request with `inference_geo: "us"`, a 1.1× multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field from the Anthropic API response through all converter paths (chat, responses, streaming, passthrough) and wires it into the cost engine so US-residency requests bill correctly. It also fixes a related streaming bug where web search request counts were lost on the terminal chunk of streamed Responses requests, causing web search to go unbilled. ## Changes - **`inference_geo` field propagation**: Added `InferenceGeo *string` to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage` schemas. All Anthropic converters (`ToBifrostChatResponse`, `ToBifrostResponsesResponse`, `ToBifrostResponsesStream`, passthrough usage) now forward `inference_geo` from the provider's usage block. - **Streaming terminal chunk fix**: In both `HandleAnthropicChatCompletionStreaming` and `HandleAnthropicResponsesStream`, `servedSpeed` and `servedInferenceGeo` are captured across events and re-applied to the terminal chunk. The terminal `response.completed` chunk is built fresh with no served modifiers, so without this re-apply, fast-mode and data-residency billing silently fell back to standard rates. - **Web search count accumulation fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into both the response usage accumulator and the mirrored billed usage. Previously the per-event count was overwritten by the terminal chunk's fresh usage, causing web search to go unbilled on streamed Responses requests. - **Cost engine**: `serviceTier` gains an `inferenceGeoUS bool` field. `tierFromResponse` accepts a third `inferenceGeo *string` argument and sets `inferenceGeoUS` when the value is `"us"` (case-insensitive). `computeTextCost` applies `InferenceGeoUSMultiplier` to all token/cache costs when `inferenceGeoUS` is true; the flat per-search fee is intentionally excluded from the multiplier. - **Database migration**: Adds `inference_geo_us_multiplier` column to `TableModelPricing` via a new migration step. The column is included in pricing sync, override patching, and the entry↔table conversion helpers. - **UI**: Exposes `inference_geo_us_multiplier` as a configurable field in the custom pricing override sheet. - **Tests**: New unit tests cover the accumulator web-search fix, the chat and responses converters forwarding `inference_geo` and web search counts, the cost engine multiplier logic (including the safe no-op when the column is unpopulated), `tierFromResponse` for `inferenceGeoUS`, and an end-to-end streaming test (`TestResponsesStream_TerminalChunkCarriesServedModifiers`) that replays `message_start → message_delta → message_stop` and asserts the terminal billed chunk carries `speed`, `inference_geo`, web search count, and cache-creation tokens. ## Type of change - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI ## Affected areas - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ## How to test ```sh # Core/Transports go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... # UI cd ui pnpm i pnpm build ``` To validate end-to-end: send a chat or responses request to an Anthropic model with data residency enabled. Confirm the response carries `inference_geo: "us"` and that the billed cost reflects the 1.1× multiplier on token/cache costs with the per-search fee unchanged. For streaming, confirm the terminal chunk carries both `speed` and `inference_geo` after `message_stop`. The `inference_geo_us_multiplier` column must be populated in the model pricing datasheet for the multiplier to apply; if the column is `null`, billing is a safe no-op (standard rates). ## Breaking changes - [x] No `tierFromResponse` gains a third parameter but is an internal function. All call sites have been updated. ## Related issues ## Security considerations No auth, secrets, or PII implications. The multiplier is a pricing configuration value stored in the existing model pricing table with the same access controls as other pricing columns. ## Checklist - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

Adds support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves inference in the US (`inference_geo: "us"`), a 1.1x multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field through the full response pipeline (chat, responses, streaming, passthrough) and wires it into the cost computation layer, including a new database column and UI override field. A secondary fix ensures Anthropic server-tool web search request counts (`ServerToolUse.WebSearchRequests`) are correctly forwarded and billed in both streaming and non-streaming paths, where previously the count could be lost when the terminal chunk overwrote the accumulated usage. - **`inference_geo` propagation**: `InferenceGeo *string` added to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage`. The field is forwarded from `AnthropicUsage` in all conversion paths: non-streaming chat, non-streaming responses, streaming chat (captured across events and set on the final chunk), streaming responses (`message_delta`), and passthrough. - **Data-residency multiplier in cost computation**: `serviceTier` gains an `inferenceGeoUS bool` flag. `tierFromResponse` now accepts and evaluates `inferenceGeo`. `computeTextCost` applies `InferenceGeoUSMultiplier` to token/cache costs only — the flat per-search fee is intentionally excluded. - **Database migration**: `migrationAddInferenceGeoMultiplierColumn` adds `inference_geo_us_multiplier` to `TableModelPricing`. The column is included in the pricing sync update list and mapped through `convertEntryToTablePricing` / `convertTablePricingToEntry`. - **Web search billing fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into the accumulator so the count survives the terminal-chunk overwrite on streamed Responses requests. The non-streaming chat converter also forwards the count into `CompletionTokensDetails.NumSearchQueries`. - **UI**: `inference_geo_us_multiplier` added to the custom pricing override sheet and `PricingOverridePatch` TypeScript type. - **Tests**: New unit tests cover the accumulator web-search fix, chat/responses converter forwarding of `InferenceGeo` and web search counts, multiplier application (including the no-multiplier-column safe no-op), and `tierFromResponse` geo detection (case-insensitive). - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ```sh go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... cd ui pnpm i || npm i pnpm build || npm run build ``` To validate end-to-end: send a request to an Anthropic model with data residency enabled. The response should include `inference_geo: "us"` and the computed cost should reflect the 1.1x multiplier on token/cache costs, with the per-search fee unchanged. - [ ] Yes - [x] No No auth, secrets, or PII implications. The `inference_geo` value is sourced from Anthropic's API response and used only for billing computation. - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

## Summary Adds end-to-end support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves a request with `inference_geo: "us"`, a 1.1× multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field from the Anthropic API response through all converter paths (chat, responses, streaming, passthrough) and wires it into the cost engine so US-residency requests bill correctly. It also fixes a related streaming bug where web search request counts were lost on the terminal chunk of streamed Responses requests, causing web search to go unbilled. ## Changes - **`inference_geo` field propagation**: Added `InferenceGeo *string` to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage` schemas. All Anthropic converters (`ToBifrostChatResponse`, `ToBifrostResponsesResponse`, `ToBifrostResponsesStream`, passthrough usage) now forward `inference_geo` from the provider's usage block. - **Streaming terminal chunk fix**: In both `HandleAnthropicChatCompletionStreaming` and `HandleAnthropicResponsesStream`, `servedSpeed` and `servedInferenceGeo` are captured across events and re-applied to the terminal chunk. The terminal `response.completed` chunk is built fresh with no served modifiers, so without this re-apply, fast-mode and data-residency billing silently fell back to standard rates. - **Web search count accumulation fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into both the response usage accumulator and the mirrored billed usage. Previously the per-event count was overwritten by the terminal chunk's fresh usage, causing web search to go unbilled on streamed Responses requests. - **Cost engine**: `serviceTier` gains an `inferenceGeoUS bool` field. `tierFromResponse` accepts a third `inferenceGeo *string` argument and sets `inferenceGeoUS` when the value is `"us"` (case-insensitive). `computeTextCost` applies `InferenceGeoUSMultiplier` to all token/cache costs when `inferenceGeoUS` is true; the flat per-search fee is intentionally excluded from the multiplier. - **Database migration**: Adds `inference_geo_us_multiplier` column to `TableModelPricing` via a new migration step. The column is included in pricing sync, override patching, and the entry↔table conversion helpers. - **UI**: Exposes `inference_geo_us_multiplier` as a configurable field in the custom pricing override sheet. - **Tests**: New unit tests cover the accumulator web-search fix, the chat and responses converters forwarding `inference_geo` and web search counts, the cost engine multiplier logic (including the safe no-op when the column is unpopulated), `tierFromResponse` for `inferenceGeoUS`, and an end-to-end streaming test (`TestResponsesStream_TerminalChunkCarriesServedModifiers`) that replays `message_start → message_delta → message_stop` and asserts the terminal billed chunk carries `speed`, `inference_geo`, web search count, and cache-creation tokens. ## Type of change - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI ## Affected areas - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ## How to test ```sh # Core/Transports go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... # UI cd ui pnpm i pnpm build ``` To validate end-to-end: send a chat or responses request to an Anthropic model with data residency enabled. Confirm the response carries `inference_geo: "us"` and that the billed cost reflects the 1.1× multiplier on token/cache costs with the per-search fee unchanged. For streaming, confirm the terminal chunk carries both `speed` and `inference_geo` after `message_stop`. The `inference_geo_us_multiplier` column must be populated in the model pricing datasheet for the multiplier to apply; if the column is `null`, billing is a safe no-op (standard rates). ## Breaking changes - [x] No `tierFromResponse` gains a third parameter but is an internal function. All call sites have been updated. ## Related issues ## Security considerations No auth, secrets, or PII implications. The multiplier is a pricing configuration value stored in the existing model pricing table with the same access controls as other pricing columns. ## Checklist - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

Adds support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves inference in the US (`inference_geo: "us"`), a 1.1x multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field through the full response pipeline (chat, responses, streaming, passthrough) and wires it into the cost computation layer, including a new database column and UI override field. A secondary fix ensures Anthropic server-tool web search request counts (`ServerToolUse.WebSearchRequests`) are correctly forwarded and billed in both streaming and non-streaming paths, where previously the count could be lost when the terminal chunk overwrote the accumulated usage. - **`inference_geo` propagation**: `InferenceGeo *string` added to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage`. The field is forwarded from `AnthropicUsage` in all conversion paths: non-streaming chat, non-streaming responses, streaming chat (captured across events and set on the final chunk), streaming responses (`message_delta`), and passthrough. - **Data-residency multiplier in cost computation**: `serviceTier` gains an `inferenceGeoUS bool` flag. `tierFromResponse` now accepts and evaluates `inferenceGeo`. `computeTextCost` applies `InferenceGeoUSMultiplier` to token/cache costs only — the flat per-search fee is intentionally excluded. - **Database migration**: `migrationAddInferenceGeoMultiplierColumn` adds `inference_geo_us_multiplier` to `TableModelPricing`. The column is included in the pricing sync update list and mapped through `convertEntryToTablePricing` / `convertTablePricingToEntry`. - **Web search billing fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into the accumulator so the count survives the terminal-chunk overwrite on streamed Responses requests. The non-streaming chat converter also forwards the count into `CompletionTokensDetails.NumSearchQueries`. - **UI**: `inference_geo_us_multiplier` added to the custom pricing override sheet and `PricingOverridePatch` TypeScript type. - **Tests**: New unit tests cover the accumulator web-search fix, chat/responses converter forwarding of `InferenceGeo` and web search counts, multiplier application (including the no-multiplier-column safe no-op), and `tierFromResponse` geo detection (case-insensitive). - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ```sh go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... cd ui pnpm i || npm i pnpm build || npm run build ``` To validate end-to-end: send a request to an Anthropic model with data residency enabled. The response should include `inference_geo: "us"` and the computed cost should reflect the 1.1x multiplier on token/cache costs, with the per-search fee unchanged. - [ ] Yes - [x] No No auth, secrets, or PII implications. The `inference_geo` value is sourced from Anthropic's API response and used only for billing computation. - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

## Summary Adds end-to-end support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves a request with `inference_geo: "us"`, a 1.1× multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field from the Anthropic API response through all converter paths (chat, responses, streaming, passthrough) and wires it into the cost engine so US-residency requests bill correctly. It also fixes a related streaming bug where web search request counts were lost on the terminal chunk of streamed Responses requests, causing web search to go unbilled. ## Changes - **`inference_geo` field propagation**: Added `InferenceGeo *string` to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage` schemas. All Anthropic converters (`ToBifrostChatResponse`, `ToBifrostResponsesResponse`, `ToBifrostResponsesStream`, passthrough usage) now forward `inference_geo` from the provider's usage block. - **Streaming terminal chunk fix**: In both `HandleAnthropicChatCompletionStreaming` and `HandleAnthropicResponsesStream`, `servedSpeed` and `servedInferenceGeo` are captured across events and re-applied to the terminal chunk. The terminal `response.completed` chunk is built fresh with no served modifiers, so without this re-apply, fast-mode and data-residency billing silently fell back to standard rates. - **Web search count accumulation fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into both the response usage accumulator and the mirrored billed usage. Previously the per-event count was overwritten by the terminal chunk's fresh usage, causing web search to go unbilled on streamed Responses requests. - **Cost engine**: `serviceTier` gains an `inferenceGeoUS bool` field. `tierFromResponse` accepts a third `inferenceGeo *string` argument and sets `inferenceGeoUS` when the value is `"us"` (case-insensitive). `computeTextCost` applies `InferenceGeoUSMultiplier` to all token/cache costs when `inferenceGeoUS` is true; the flat per-search fee is intentionally excluded from the multiplier. - **Database migration**: Adds `inference_geo_us_multiplier` column to `TableModelPricing` via a new migration step. The column is included in pricing sync, override patching, and the entry↔table conversion helpers. - **UI**: Exposes `inference_geo_us_multiplier` as a configurable field in the custom pricing override sheet. - **Tests**: New unit tests cover the accumulator web-search fix, the chat and responses converters forwarding `inference_geo` and web search counts, the cost engine multiplier logic (including the safe no-op when the column is unpopulated), `tierFromResponse` for `inferenceGeoUS`, and an end-to-end streaming test (`TestResponsesStream_TerminalChunkCarriesServedModifiers`) that replays `message_start → message_delta → message_stop` and asserts the terminal billed chunk carries `speed`, `inference_geo`, web search count, and cache-creation tokens. ## Type of change - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI ## Affected areas - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ## How to test ```sh # Core/Transports go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... # UI cd ui pnpm i pnpm build ``` To validate end-to-end: send a chat or responses request to an Anthropic model with data residency enabled. Confirm the response carries `inference_geo: "us"` and that the billed cost reflects the 1.1× multiplier on token/cache costs with the per-search fee unchanged. For streaming, confirm the terminal chunk carries both `speed` and `inference_geo` after `message_stop`. The `inference_geo_us_multiplier` column must be populated in the model pricing datasheet for the multiplier to apply; if the column is `null`, billing is a safe no-op (standard rates). ## Breaking changes - [x] No `tierFromResponse` gains a third parameter but is an internal function. All call sites have been updated. ## Related issues ## Security considerations No auth, secrets, or PII implications. The multiplier is a pricing configuration value stored in the existing model pricing table with the same access controls as other pricing columns. ## Checklist - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

Adds support for Anthropic's data-residency billing feature (`inference_geo`). When Anthropic serves inference in the US (`inference_geo: "us"`), a 1.1x multiplier is applied to all token and cache costs. This PR propagates the `inference_geo` field through the full response pipeline (chat, responses, streaming, passthrough) and wires it into the cost computation layer, including a new database column and UI override field. A secondary fix ensures Anthropic server-tool web search request counts (`ServerToolUse.WebSearchRequests`) are correctly forwarded and billed in both streaming and non-streaming paths, where previously the count could be lost when the terminal chunk overwrote the accumulated usage. - **`inference_geo` propagation**: `InferenceGeo *string` added to `BifrostChatResponse`, `BifrostResponsesResponse`, and `BifrostPassthroughUsage`. The field is forwarded from `AnthropicUsage` in all conversion paths: non-streaming chat, non-streaming responses, streaming chat (captured across events and set on the final chunk), streaming responses (`message_delta`), and passthrough. - **Data-residency multiplier in cost computation**: `serviceTier` gains an `inferenceGeoUS bool` flag. `tierFromResponse` now accepts and evaluates `inferenceGeo`. `computeTextCost` applies `InferenceGeoUSMultiplier` to token/cache costs only — the flat per-search fee is intentionally excluded. - **Database migration**: `migrationAddInferenceGeoMultiplierColumn` adds `inference_geo_us_multiplier` to `TableModelPricing`. The column is included in the pricing sync update list and mapped through `convertEntryToTablePricing` / `convertTablePricingToEntry`. - **Web search billing fix**: `accumulateAnthropicResponsesUsage` now carries `ServerToolUse.WebSearchRequests` into the accumulator so the count survives the terminal-chunk overwrite on streamed Responses requests. The non-streaming chat converter also forwards the count into `CompletionTokensDetails.NumSearchQueries`. - **UI**: `inference_geo_us_multiplier` added to the custom pricing override sheet and `PricingOverridePatch` TypeScript type. - **Tests**: New unit tests cover the accumulator web-search fix, chat/responses converter forwarding of `InferenceGeo` and web search counts, multiplier application (including the no-multiplier-column safe no-op), and `tierFromResponse` geo detection (case-insensitive). - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI - [x] Core (Go) - [ ] Transports (HTTP) - [x] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ```sh go test ./core/providers/anthropic/... ./framework/modelcatalog/datasheet/... cd ui pnpm i || npm i pnpm build || npm run build ``` To validate end-to-end: send a request to an Anthropic model with data residency enabled. The response should include `inference_geo: "us"` and the computed cost should reflect the 1.1x multiplier on token/cache costs, with the per-search fee unchanged. - [ ] Yes - [x] No No auth, secrets, or PII implications. The `inference_geo` value is sourced from Anthropic's API response and used only for billing computation. - [ ] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [ ] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable

TejasGhatte marked this pull request as ready for review July 9, 2026 15:09

TejasGhatte mentioned this pull request Jul 9, 2026

fix: annthropic cache rate for fast mode #5063

Merged

8 tasks

coderabbitai Bot requested review from akshaydeo and danpiths July 9, 2026 15:10

greptile-apps Bot reviewed Jul 9, 2026

View reviewed changes

Comment thread framework/modelcatalog/datasheet/cost.go

Comment thread core/providers/anthropic/responses.go

Comment thread core/providers/anthropic/responses.go

coderabbitai Bot reviewed Jul 9, 2026

View reviewed changes

coderabbitai Bot previously approved these changes Jul 9, 2026

View reviewed changes

TejasGhatte mentioned this pull request Jul 9, 2026

fix: service tier in openai chat completion #5073

Merged

18 tasks

TejasGhatte force-pushed the 07-09-fix_inference_geo_cost_on_anthropic branch from 7b0bd1e to aa19027 Compare July 9, 2026 15:36

greptile-apps Bot reviewed Jul 9, 2026

View reviewed changes

Comment thread framework/modelcatalog/datasheet/cost.go

coderabbitai Bot requested review from Pratham-Mishra04 and roroghost17 July 9, 2026 15:43

coderabbitai Bot reviewed Jul 9, 2026

View reviewed changes

akshaydeo previously approved these changes Jul 9, 2026

View reviewed changes

akshaydeo changed the base branch from 07-09-fix_annthropic_cache_rate_for_fast_mode to graphite-base/5072 July 9, 2026 16:10

akshaydeo changed the base branch from graphite-base/5072 to dev July 9, 2026 16:11

fix: inference geo cost on anthropic

c1a6a91

akshaydeo force-pushed the 07-09-fix_inference_geo_cost_on_anthropic branch from aa19027 to c1a6a91 Compare July 9, 2026 16:11

greptile-apps Bot reviewed Jul 9, 2026

View reviewed changes

Comment thread framework/modelcatalog/datasheet/cost.go

akshaydeo approved these changes Jul 9, 2026

View reviewed changes

coderabbitai Bot approved these changes Jul 9, 2026

View reviewed changes

akshaydeo merged commit c911b56 into dev Jul 9, 2026
15 of 16 checks passed

akshaydeo deleted the 07-09-fix_inference_geo_cost_on_anthropic branch July 9, 2026 16:27

coderabbitai Bot mentioned this pull request Jul 10, 2026

fix: inference geo cost on anthropic (#5072) #5088

Merged

17 tasks

Navigation Menu

fix: inference geo cost on anthropic - #5072

fix: inference geo cost on anthropic#5072
akshaydeo merged 1 commit into
devfrom
07-09-fix_inference_geo_cost_on_anthropic

TejasGhatte commented Jul 9, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot commented Jul 9, 2026 •

edited

Loading

Review limit reached

Walkthrough

Changes

Sequence Diagram(s)

❌ Failed checks (1 warning)

Uh oh!

TejasGhatte commented Jul 9, 2026 •

edited

Loading

Uh oh!

greptile-apps Bot commented Jul 9, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

CLAassistant commented Jul 9, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot left a comment

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Uh oh!

akshaydeo commented Jul 9, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

TejasGhatte commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Type of change

Affected areas

How to test

Breaking changes

Security considerations

Checklist

Uh oh!

coderabbitai Bot commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review limit reached

Walkthrough

Changes

Sequence Diagram(s)

❌ Failed checks (1 warning)

Uh oh!

TejasGhatte commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

greptile-apps Bot commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Confidence Score: 4/5

Important Files Changed

Uh oh!

Uh oh!

Uh oh!

Uh oh!

CLAassistant commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

akshaydeo commented Jul 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merge activity

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

TejasGhatte commented Jul 9, 2026 •

edited

Loading

coderabbitai Bot commented Jul 9, 2026 •

edited

Loading

TejasGhatte commented Jul 9, 2026 •

edited

Loading

greptile-apps Bot commented Jul 9, 2026 •

edited

Loading

CLAassistant commented Jul 9, 2026 •

edited

Loading

akshaydeo commented Jul 9, 2026 •

edited

Loading