feat(provider): add Morph as a gateway provider for large open-source models by shreybirmiwalmorph · Pull Request #4245 · Kilo-Org/cloud

shreybirmiwalmorph · 2026-06-25T02:25:06Z

Adds morph as gateway provider.

Kilo will need to set MORPH_API_KEY

Models added

public_id	internal gateway id	context
`morph/qwen3.5-397b`	`morph-qwen35-397b`	262K
`morph/qwen3.6-27b`	`morph-qwen36-27b`	131K
`morph/minimax-m2.7`	`morph-minimax27-230b`	196K
`morph/minimax-m3`	`morph-minimax3-428b`	256K
`morph/glm-5.2`	`morph-glm52-744b`	450K
`morph/deepseek-v4-flash`	`morph-dsv4flash`	1M

kilo-code-bot · 2026-06-25T02:28:21Z

+};
+
+export const morph_minimax_m27_model: KiloExclusiveModel = {
+  public_id: 'morph/minimax-m2.7',


WARNING: Morph MiniMax models will fail for OpenCode clients

getGatewayOpenCodeSettings() treats any *minimax* model as ai_sdk_provider: 'anthropic', and CustomLlmProviderSchema documents that as the Messages API. Because MORPH.supportedChatApis only exposes chat_completions, requests for both morph/minimax-m2.7 and morph/minimax-m3 are rejected by apiKindNotSupportedResponse before they ever reach Morph. Either override these ids to an OpenAI-compatible provider or add /messages support for the Morph gateway.

Reply with @kilocode-bot fix it to have Kilo Code address this issue.

Good catch — fixed in 40795bd.

getAiSdkProvider mapped any *minimax* id to the Anthropic Messages API, which the Morph gateway (chat_completions only) rejects via apiKindNotSupportedResponse. Rather than patch just the two MiniMax ids, I pinned every Morph model to openai-compatible at the top of getAiSdkProvider, encoding the gateway invariant and guarding the whole class (also protects future gpt/grok-named ids from being routed to the Responses API). Added regression coverage asserting all six Morph models resolve to a chat_completions-compatible OpenCode provider.

Also verified live against api.morphllm.com: all six models return 200 with correct output + usage, and the two vision-flagged models (qwen3.5-397b, minimax-m3) correctly process image input.

kilo-code-bot · 2026-06-25T02:28:29Z

Code Review Summary

Status: No Issues Found | Recommendation: Merge

Files Reviewed (1 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts

Previous Review Summaries (9 snapshots, latest commit 29ffb5c)

Current summary above is authoritative. Previous snapshots are kept for context only.

Previous review (commit `29ffb5c`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (1 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts

Previous review (commit `4ee98f1`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (2 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts
apps/web/src/lib/ai-gateway/providers/morph.ts

Previous review (commit `6f9ce6c`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (1 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts

Previous review (commit `40795bd`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (2 files)

apps/web/src/lib/ai-gateway/providers/model-settings.ts
apps/web/src/lib/ai-gateway/providers/morph.test.ts

Previous review (commit `aada3de`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (2 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts
apps/web/src/lib/ai-gateway/providers/morph.ts

Previous review (commit `f632630`)

Status: 1 Issues Found | Recommendation: Address before merge

Overview

Severity	Count
CRITICAL	0
WARNING	1
SUGGESTION	0

Issue Details (click to expand)

WARNING

File	Line	Issue
`apps/web/src/lib/ai-gateway/providers/morph.ts`	63	Morph MiniMax models still advertise the Anthropic/Messages path to OpenCode even though the Morph gateway only supports Chat Completions.

Files Reviewed (1 files)

apps/web/src/lib/ai-gateway/providers/morph.ts - 1 issue

Fix these issues in Kilo Cloud

Previous review (commit `aff4c19`)

Status: No Issues Found | Recommendation: Merge

Files Reviewed (2 files)

apps/web/src/lib/ai-gateway/providers/morph.test.ts
apps/web/src/lib/ai-gateway/providers/morph.ts

Previous review (commit `f942d39`)

Status: 1 Issues Found | Recommendation: Address before merge

Overview

Severity	Count
CRITICAL	0
WARNING	1
SUGGESTION	0

Issue Details (click to expand)

WARNING

File	Line	Issue
`apps/web/src/lib/ai-gateway/providers/morph.ts`	63	Morph MiniMax models still advertise the Anthropic/Messages path to OpenCode even though the Morph gateway only supports Chat Completions.

Files Reviewed (4 files)

apps/web/src/lib/ai-gateway/models.ts
apps/web/src/lib/ai-gateway/providers/morph.ts - 1 issue
apps/web/src/lib/ai-gateway/providers/provider-definitions.ts
apps/web/src/lib/ai-gateway/providers/types.ts

Fix these issues in Kilo Cloud

Previous review (commit `deb5357`)

Status: 1 Issues Found | Recommendation: Address before merge

Overview

Severity	Count
CRITICAL	0
WARNING	1
SUGGESTION	0

Issue Details (click to expand)

WARNING

File	Line	Issue
`apps/web/src/lib/ai-gateway/providers/morph.ts`	63	Morph MiniMax models are advertised through the Messages API even though the Morph provider only supports Chat Completions.

Files Reviewed (4 files)

apps/web/src/lib/ai-gateway/models.ts
apps/web/src/lib/ai-gateway/providers/morph.ts - 1 issue
apps/web/src/lib/ai-gateway/providers/provider-definitions.ts
apps/web/src/lib/ai-gateway/providers/types.ts

Fix these issues in Kilo Cloud

_{Reviewed by gpt-5.4-20260305 · Input: 71.4K · Output: 4.3K · Cached: 237.6K}

_{Review guidance: REVIEW.md from base branch main}

… models Adds Morph (https://api.morphllm.com/v1, OpenAI-compatible) as a first-party gateway provider and registers the large open-source models Morph serves on its own fleet: Qwen3.5 397B, Qwen3.6 27B, MiniMax M2.7, MiniMax M3, GLM-5.2, and DeepSeek V4 Flash. Excludes Morph's proprietary models (apply/v3, compactor, warp-grep, embeddings). Routing reuses the existing gateway->provider resolution in get-provider.ts; 'morph' is already a recognized inference-provider id. Kilo holds the key via MORPH_API_KEY. Pricing and context windows mirror Morph's published numbers. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Reconcile Morph gateway pricing against the canonical source (https://www.morphllm.com/api/models/json + landing/src/lib/pricing.ts cost functions): - GLM-5.2: set input_cache_read to $0.35/1M. Morph's calculateChatGlm52Cost bills cached input at this rate (LMCache prefix reuse); the models JSON currently omits the field, so the prior null under-priced cache reads. - Verified the other five models: qwen3.5 keeps its $0.30 cache rate; the rest (qwen3.6, minimax m2.7/m3, deepseek-v4-flash) have no cache-read billing in Morph's cost functions, so they correctly stay null. The minimax cache rates present in MODEL_PRICING config are never applied by the cost functions, so they are intentionally not exposed here. Adds morph.test.ts covering: Morph provider config, the six registered open-source models (and exclusion of proprietary apply/compactor/etc.), gateway->provider resolution to PROVIDERS.MORPH (the same lookup get-provider.ts uses), and per-model pricing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Match Morph's canonical context (MODEL_CONTEXT_WINDOWS / api/models/json): GLM-5.2 serves a 1,048,576-token window, not 450k. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

…l source Reconcile all six Morph gateway models against the canonical source of truth (https://www.morphllm.com/api/models/json). Per-1M prompt/completion/cache-read rates and context windows already match exactly; no pricing change needed. The canonical JSON marks qwen3.5-397b and minimax-m3 as image-capable (input_modalities: ["text","image"]), so add the 'vision' flag to those two and assert vision support (and reasoning) for every model in the test matrix. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

…ents getAiSdkProvider maps any '*minimax*' id to the Anthropic Messages API (and gpt/grok ids to the OpenAI Responses API). Morph's gateway only exposes chat_completions (MORPH.supportedChatApis), so OpenCode requests for morph/minimax-m2.7 and morph/minimax-m3 were rejected by apiKindNotSupportedResponse before reaching Morph. Pin every Morph model to the 'openai-compatible' AI SDK provider at the top of getAiSdkProvider, encoding the gateway's real invariant and guarding the whole bug class (not just minimax). Add regression coverage asserting all six Morph models resolve to a chat_completions-compatible OpenCode provider. Reported-by: kilo-code-bot on PR Kilo-Org#4245. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

…t_mUsd Add cost-calculation coverage proving the stored per-million rates produce the right micro-USD bills, not just that the numbers are present: - qwen3.5/glm-5.2 cache reads bill at the discounted cache_read rate (< prompt) - models without a cache_read price (e.g. deepseek-v4-flash) fall back to the prompt rate for cache hits (not free) - a mixed uncached + cache-hit + output bill matches the expected total Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

…/json) The canonical models JSON advertises a cache rate only for qwen3.5 (0.3); GLM-5.2 has none. Set input_cache_read_per_million to null and update the test so GLM-5.2 bills cache hits at the prompt rate, like the other non-cache models. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Drop the Morph provider unit test (all assertions passed; removing per request to keep the PR to the provider addition itself). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Add back the deterministic unit test (26 cases): provider config, the 6 registered models, gateway->PROVIDERS.MORPH routing, pricing vs canonical (GLM no-cache, qwen3.5 0.3), vision flags, and cache billing. No network/key needed — safe for CI. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

bhaktatejas922 · 2026-06-25T23:21:26Z

@shreybirmiwalmorph this stuff should pull from the live endpoint https://www.morphllm.com/api/models/json

bhaktatejas922 · 2026-06-26T23:25:23Z

@arimesser

kilo-code-bot Bot reviewed Jun 25, 2026

View reviewed changes

shreybirmiwalmorph force-pushed the feat/morph-gateway-provider branch from deb5357 to f942d39 Compare June 25, 2026 02:35

shreybirmiwalmorph and others added 9 commits June 24, 2026 20:23

fix(provider): GLM-5.2 context window 450k -> 1M

f632630

Match Morph's canonical context (MODEL_CONTEXT_WINDOWS / api/models/json): GLM-5.2 serves a 1,048,576-token window, not 450k. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

chore(provider): remove morph.test.ts

29ffb5c

Drop the Morph provider unit test (all assertions passed; removing per request to keep the PR to the provider addition itself). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Merge branch 'main' into feat/morph-gateway-provider

2a437b8

Uh oh!

Conversation

shreybirmiwalmorph commented Jun 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Models added

Uh oh!

kilo-code-bot Bot Jun 25, 2026

Choose a reason for hiding this comment

Uh oh!

shreybirmiwalmorph Jun 25, 2026

Choose a reason for hiding this comment

Uh oh!

kilo-code-bot Bot commented Jun 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Code Review Summary

Previous review (commit 29ffb5c)

Previous review (commit 4ee98f1)

Previous review (commit 6f9ce6c)

Previous review (commit 40795bd)

Previous review (commit aada3de)

Previous review (commit f632630)

Overview

WARNING

Previous review (commit aff4c19)

Previous review (commit f942d39)

Overview

WARNING

Previous review (commit deb5357)

Overview

WARNING

Uh oh!

bhaktatejas922 commented Jun 25, 2026

Uh oh!

bhaktatejas922 commented Jun 26, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

shreybirmiwalmorph commented Jun 25, 2026 •

edited

Loading

kilo-code-bot Bot commented Jun 25, 2026 •

edited

Loading

Previous review (commit `29ffb5c`)

Previous review (commit `4ee98f1`)

Previous review (commit `6f9ce6c`)

Previous review (commit `40795bd`)

Previous review (commit `aada3de`)

Previous review (commit `f632630`)

Previous review (commit `aff4c19`)

Previous review (commit `f942d39`)

Previous review (commit `deb5357`)