Morph MORPH
SIGN IN SIGN UP
dhruvhead / CLIProxyAPI UNCLAIMED
0 0 3 Go

COMMITS

main
August 15, 2026
L
perf(translator): switch response translators to batched raw-array insertion via `SetRawArrayItems`
Luis Pater committed
8b3b304
L
perf(translator): batch assemble translation arrays before writing JSON
Luis Pater committed
0c58c3c
L
fix(gemini): simplify OpenAI chat response content and choices serialization
Luis Pater committed
a581838
L
perf(translator): batch assemble response arrays and merge multi-choice parts
Luis Pater committed
124dab6
L
fix(claude,gemini,antigravity): centralize tool-call ID generation and harden signature sanitization
Luis Pater committed
616d1b1
L
fix(claude): deduplicate duplicate tool outputs in OpenAI-to-Claude request conversion
Luis Pater committed
1ecb7df
L
chore(models): remove GPT-5.6 Sol Work Mode registrations from model registry config
Luis Pater committed
c1ff55f
L
fix(openai): propagate environment context and sanitize antigravity generation config in interaction adapters
Luis Pater committed
10afcc8
L
fix(gemini): merge conditional schema branches during JSON schema cleanup
Luis Pater committed
f53a2b6
C
Merge pull request #4994 from router-for-me/models
Chén Mù committed
48d0218
L
fix(auth): make session-affinity updates safe for rebound sessions
Luis Pater committed
9169ad5
H
feat(models): add max_completion_tokens to model definitions and responses
hkfires committed
046b59e
L
feat(models): add GPT-5.6 Sol Work Mode model registrations and Codex client config updates
Luis Pater committed
dd21444
L
fix(openai): ensure Responses usage includes token detail fields
Luis Pater committed
e0b4956
L
fix(claude): add Anthropic unified rate-limit parsing helpers
Luis Pater committed
ac82bed
August 14, 2026
M
fix(claude): keep tool_result blocks first when injecting currentDate
mardausdennis committed
297139c
L
fix(auth): avoid cooldown for request-scoped 401 request-faults
Luis Pater committed
203f5b1
L
Merge pull request #4360 from router-for-me/perf/skip-inactive-request-interceptors
Luis Pater committed
810d4dd
L
Merge pull request #4928 from ramapitecusment/codex/websocket-transcript-allocations-v2
Luis Pater committed
8b02fed
L
fix(gemini): preserve `additionalProperties:false` for Antigravity response schemas
Luis Pater committed
61c4fd8
L
fix(openai): mark truncated/filtered responses as incomplete and avoid finalizing partial tool calls
Luis Pater committed
78f0c40
L
fix(codex): cache multi-agent spawn-agent model data and invalidate on updates
Luis Pater committed
98c98d6
L
fix(claude): map refusal and sensitive stop reasons to `content_filter`
Luis Pater committed
fab077a
L
fix(translator): strip nested `prompt_cache_breakpoint` from Codex Responses payloads
Luis Pater committed
6edf9c4
L
fix(auth): preserve custom auth-file metadata during token refresh and relogin
Luis Pater committed
b90d8ee
L
fix(translator): make Gemini tool call IDs deterministic and robustly match responses
Luis Pater committed
8d670b9
S
fix(claude): pass through caller MCP tools on alias server collision
sususu committed
bdde638
S
fix(claude): use BIP-39 words for OAuth MCP tool aliases
sususu committed
f6f03e4
L
fix(gemini): skip zero-token usage placeholders and always finalize stream reporters
Luis Pater committed
7cf9279
L
fix(claude): recover OAuth tool aliases for repeated prefixes and malformed IDs
Luis Pater committed
f2d272d