mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-09-18 21:02:50 +03:00

Files

initguru f3acf4f811 fix(sse): inject global system prompt once, post-translation, across all target shapes (#12904 )

* fix(sse): inject global system prompt post-translation for codex/Responses path

codex/Responses requests carry input[]+instructions, not messages[]. The
existing injectSystemPrompt runs PRE-translation (chatCore.ts) and only
handles messages[]/system fields, so the Global System Prompt (After Prompt =
suffixPrompt) never reached the provider for codex — verified 0/84 call logs
while the catalog base_instructions reached 84/84.

Add injectSystemPromptPostTranslation() and call it after prepareUpstreamBody
on the resolved messages[]. With multiple system/developer messages (codex
normalises its per-item developer roles to system), prefix goes on the FIRST
and suffix on the LAST so the After Prompt retains the highest recency
position — the semantics injectSystemPrompt's single-findIndex buries.

Also wire OMNIROUTE_SYSTEM_INSTRUCTION_APPEND on the /v1/messages (Claude
Messages -> OpenAI Chat Completions) translation path. The directive was
previously only wired on the Responses API path, so DeepSeek-V4 kept leaking
English planning/chain-of-thought into the content field on Claude Code
sessions that route through /v1/messages. Mirror the openai-responses.ts
pattern: append to string system, append a text block for array content, or
unshift a new system message when none exists.

Tests: 23/23 (19 system-prompt incl. 6 postTranslation + codex regression;
4 claude-to-openai directive append). typecheck:core clean.

* test(sse): reproduce global prompt double injection — single-injection contract tests

* fix(sse): unify global prompt injection to single post-translation pass

* fix(sse): carry single global-prompt injection across claude/gemini/responses target shapes

* fix(sse): restore global-prompt coverage for carrier-less targets via gated pre-translation pass

* fix(sse): cover codex/gemini source shapes in the carrier-less pre-translation gate

* fix(types): preserve generic system prompt return

* fix(sse): correct file reference in claude-to-openai.ts comment and add changelog fragment

Points the #reasoning-bilingual comment at the real companion file
(translator/response/openai-to-claude.ts's directivePreambleStripper.ts
from #12905) instead of the nonexistent "openai-responses.ts", and adds
the changelog fragment referenced in the PR body but missing from the
diff.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Co-authored-by: Jihyun Son <jihyun.son@sk.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

2026-09-17 02:30:35 -03:00

architecture

fix(db): bound health scans and isolate native diagnostics (#13717 )

2026-09-16 12:59:45 -03:00

assets

feat(i18n): 7 new locales — Hausa, Yoruba, Igbo, Amharic, Uzbek, Georgian, Armenian (66 locales) (#13727 )

2026-09-15 09:50:01 -03:00

changelog/fragments

feat(resilience): add hierarchical concurrency admission (#11493 )

2026-08-25 07:19:09 -03:00

comparison

feat(i18n): locale-expansion tooling — add-locale orchestrator, aliases, translation-ratio gate; retire duplicate 'in' locale (#12496 )

2026-09-02 17:45:50 -03:00

compression

feat(dashboard): adaptive context-budget dial on compression panel (#12488 )

2026-09-03 12:40:02 -03:00

diagrams

chore: reconcile the JxnLexn merge wave with the release tip (#13921 )

2026-09-16 16:43:44 -03:00

frameworks

fix(cli): add POST /api/mcp/restart and mcp enable/disable subcommands (#13012 ) (#13770 )

2026-09-16 06:17:04 -03:00

getting-started

fix(free-tiers): remove obsolete Together $25 signup credit (#12526 ) (#13407 )

2026-09-15 00:01:27 -03:00

guides

fix(cli): translate the CLI for every locale (38 catalogs were nearly empty) (#13892 )

2026-09-16 12:27:59 -03:00

i18n

fix(db): bound health scans and isolate native diagnostics (#13717 )

2026-09-16 12:59:45 -03:00

ops

fix(redis): namespace warmup circuit-breaker keys with REDIS_KEY_PREFIX (#13328 )

2026-09-16 21:09:38 -03:00

plans

feat(search): add fallback-only AnySearch provider (webSearch + webFetch) (#11690 )

2026-08-26 17:54:57 -03:00

providers

docs(providers): add Microsoft 365 Copilot (BizChat) provider guide (#12779 ) (#13340 )

2026-09-14 23:24:59 -03:00

reference

fix(sse): inject global system prompt once, post-translation, across all target shapes (#12904 )

2026-09-17 02:30:35 -03:00

routing

feat: adaptive reasoning effort (auto) — gateway-resolved, per-turn pinned, all harnesses (#13448 )

2026-09-16 15:18:36 -03:00

screenshots

fix(free-tiers): remove obsolete Together $25 signup credit (#12526 ) (#13407 )

2026-09-15 00:01:27 -03:00

security

fix(auth): close the JWT_SECRET bootstrap chain — real-peer loopback, obsidian always-protected, DATA_DIR vault refusal (#13791 )

2026-09-15 16:58:24 -03:00

DEVELOPER-ENVIRONMENT.md

fix(ollama): route models by advertised capability (#11088 )

2026-08-23 11:45:01 -03:00

DEVIN_CLAUDE_BRIDGE.md

chore(providers): bump Claude Code wire identity + Devin bridge pin to 2.1.258 (#12604 )

2026-09-03 13:49:46 -03:00

meta.json

Release v3.8.40

2026-06-29 08:40:06 -03:00

OMNIROUTE_ALLOCATION_HANDOFF.md

fix(ollama): route models by advertised capability (#11088 )

2026-08-23 11:45:01 -03:00

OMNIROUTE_PROVIDER_FAILOVER.md

fix(ollama): route models by advertised capability (#11088 )

2026-08-23 11:45:01 -03:00

OMNIROUTE_QUOTA_TELEMETRY.md

fix(ollama): route models by advertised capability (#11088 )

2026-08-23 11:45:01 -03:00

OMNIROUTE_ROUTING_POLICY.md

fix(ollama): route models by advertised capability (#11088 )

2026-08-23 11:45:01 -03:00

openapi.yaml

feat(proxies): show how many egress IPs actually served a proxy pool (#13581 )

2026-09-15 19:48:52 -03:00

README.md

feat(i18n): 7 new locales — Hausa, Yoruba, Igbo, Amharic, Uzbek, Georgian, Armenian (66 locales) (#13727 )

2026-09-15 09:50:01 -03:00

README.md

title, version, lastUpdated

title	version	lastUpdated
OmniRoute Documentation	3.8.40	2026-06-28

OmniRoute Documentation

Navigable index of the OmniRoute documentation set. Topics are grouped by intent so you can find what you need quickly.

Looking for the project overview, install steps, or release notes? See the root README.md, ROADMAP.md, CHANGELOG.md, and CONTRIBUTING.md.

For Non-Tech Users

Simple guides for using OmniRoute — no technical background needed.

getting-started/

QUICK-START.md — install and run OmniRoute in 3 minutes.
AUTO-COMBO-GUIDE.md — let OmniRoute pick the best AI for you.
PROVIDERS-GUIDE.md — how to connect AI providers.
FREE-TIERS-GUIDE.md — get free AI with no credit card.
WEB-COOKIE-GUIDE.md — web cookie providers (session-credential setup).

guides/

SETUP_GUIDE.md — first-time setup of OmniRoute.
USER_GUIDE.md — daily usage of the dashboard and API.
THINKING_BUDGET.md — thinking/reasoning budget modes (passthrough vs auto-strip).
FEATURES.md — dashboard feature gallery.
CHAOS-MODE.md — multi-model parallel/collaborative execution (setup, permissions, API).
TIERS.md — OmniRoute tiers explained (user guide).
USAGE_QUOTA_GUIDE.md — usage, quota & spend tracking.
COST_TRACKING.md — cost and spend tracking.
FREE_PROVIDER_RANKINGS.md — free provider rankings (Arena ELO).
DOCKER_GUIDE.md — running OmniRoute under Docker, including runtime RAM for coding agents.
ELECTRON_GUIDE.md — desktop (Electron) builds.
TERMUX_GUIDE.md — running on Android via Termux.
PWA_GUIDE.md — installing the dashboard as a PWA.
REMOTE-MODE.md — exposing OmniRoute remotely + scoped tokens.
CLI-INTEGRATIONS.md — master table of setup-* CLI integrations.
OPENCODE-V2-PLUGIN.md — installing and configuring the OpenCode v2 plugin.
CLAUDE-CODE-CONFIGURATION.md — Claude Code CLI with OmniRoute.
CODEX-CLI-CONFIGURATION.md — Codex CLI with OmniRoute.
KIRO_SETUP.md — Kiro setup.
ANTIGRAVITY-ONBOARDING.md — Antigravity (Google One AI) onboarding.
MANAGEMENT-AUTH.md — management authentication.
I18N.md — translation and locale workflow.
TROUBLESHOOTING.md — detailed troubleshooting reference.
UNINSTALL.md — clean removal steps.

For Tech Users

Technical documentation for developers and contributors.

architecture/

How the system is put together — read these to understand the runtime, code layout, and resilience model.

ARCHITECTURE.md — high-level system architecture (request pipeline, layers, modules).
CODEBASE_DOCUMENTATION.md — engineering reference for the codebase.
REPOSITORY_MAP.md — directory-by-directory navigation guide.
AUTHZ_GUIDE.md — authorization pipeline (route classifier + policy engine).
RESILIENCE_GUIDE.md — provider circuit breaker, connection cooldown, and model lockout.
QUALITY_GATES.md — quality-gate scripts and CI jobs inventory.
MONITORING_SECTIONS.md — monitoring/costs dashboard navigation.
cluster-decisions.md — optional sidecar/cluster profile decisions.
DESIGN_SYSTEM.md — design system & visual identity.
ROUTER_BACKENDS.md — router backends & embedded services architecture contract (ADR).
admission-lanes.md — the two admission-lane systems and what gates each.
persistence-backend-boundary.md — pluggable persistence boundary (ADR).

reference/

Lookup material — API surface, environment variables, CLI flags, provider catalog.

API_REFERENCE.md — REST API endpoints and shapes.
PROVIDER_REFERENCE.md — auto-generated provider catalog (do not edit by hand).
REMOVED_PROVIDERS.md — providers removed at their operator's request; never reintroduce without written permission.
PROVIDER_PLUGIN_MANIFEST.md — sidecar-safe provider plugin contract for Bifrost and CLIProxyAPI migration.
openapi.yaml — OpenAPI spec for the public API.
ENVIRONMENT.md — environment variables reference.
FEATURE_FLAGS.md — feature flags and their defaults.
CLI-TOOLS.md — bundled CLI commands.
FREE_TIERS.md — free-tier LLM provider directory.
FREE_PROXIES_API.md — free proxies API.
RELAY_BACKEND_STRATEGY.md — relay backend strategy.
RELAY_TROUBLESHOOTING.md — relay troubleshooting.

frameworks/

Pluggable subsystems exposed to clients, agents, and operators.

MCP-SERVER.md — Model Context Protocol server.
A2A-SERVER.md — Agent-to-Agent (A2A) JSON-RPC server.
ACP.md — Agent Client Protocol.
AGENT_PROTOCOLS_GUIDE.md — A2A / ACP / Cloud agent overview.
AGENTBRIDGE.md — IDE agent bridge.
AGENT-SKILLS.md — agent skills catalog.
CLOUD_AGENT.md — cloud agent runtime and providers.
SKILLS.md — Skills framework (sandboxed extension).
MEMORY.md — persistent memory (FTS5 + Qdrant).
WEBHOOKS.md — webhook events and dispatch.
EVALS.md — eval suites.
GAMIFICATION.md — gamification & leaderboard system.
EMBEDDED-SERVICES.md — embedded sidecar services (9Router, CLIProxyAPI).
NOTION_CONTEXT.md — Notion context source.
OBSIDIAN_CONTEXT.md — Obsidian context source.
LOCAL_CORPUS_CONTEXT.md — local corpus context source (approved directory exposed to MCP).
OPENCODE.md — OpenCode integration.
OPEN_SSE_ARCHITECTURE.md — open-sse streaming engine internals.
PLAYGROUND_STUDIO.md — Playground Studio UI.
SEARCH_TOOLS_STUDIO.md — Search Tools Studio UI.
TRAFFIC_INSPECTOR.md — traffic inspector (MITM).
PLUGINS.md — CLI plugin system overview.
PLUGIN_SDK.md — plugin SDK reference.
PLUGIN_MARKETPLACE.md — plugin marketplace.
RADAR.md — Radar free-model catalog overlay (optional, off by default).

routing/

Combo routing, scoring, and replay.

AUTO-COMBO.md — Auto-Combo (multi-factor scoring, 19 strategies).
QUOTA_SHARE.md — quota sharing engine.
REASONING_REPLAY.md — reasoning replay cache.
REASONING_ROUTING.md — reasoning routing rules (effort/budget rule engine).

security/

Guardrails, compliance, stealth, and the mandatory patterns for handling public credentials and error messages.

GUARDRAILS.md — PII, prompt injection, vision guardrails.
COMPLIANCE.md — audit trails and compliance.
STEALTH_GUIDE.md — TLS / fingerprint stealth.
PUBLIC_CREDS.md — mandatory pattern for embedding public upstream OAuth client_id/secret + Firebase Web keys without tripping secret scanners.
ERROR_SANITIZATION.md — mandatory pattern for routing every error response through sanitizeErrorMessage to prevent stack-trace exposure.
ROUTE_GUARD_TIERS.md — route-guard classification tiers.
CLI_TOKEN.md — CLI machine-ID token (HMAC + legacy SHA-256) auth.
EGRESS_POLICY.md — egress IP family (IPv4/IPv6) policy.
BAN_DETECTION.md — account-ban / banned-keyword detection.
AGENTROUTER_WAF.md — agentrouter.org WAF.
CORS.md — CORS configuration & security.
MITM-TPROXY-DECRYPT.md — transparent MITM decrypt.
SUPPLY_CHAIN.md — supply-chain gates (SLSA, SBOM, Trivy, osv-scanner, Scorecard).
SOCKET_DEV_FINDINGS.md — supply-chain finding attestations.

compression/

Prompt compression engines, rules, and language packs.

COMPRESSION_GUIDE.md — top-level compression overview.
COMPRESSION_ENGINES.md — available compression engines.
COMPRESSION_RULES_FORMAT.md — rule file format.
COMPRESSION_LANGUAGE_PACKS.md — language packs.
RTK_COMPRESSION.md — RTK engine deep dive.
CONTEXT_EDITING.md — delegated context editing (Anthropic).
EXTENDING_COMPRESSION.md — adding a custom compression engine.

providers/

Provider-specific integration guides.

CLAUDE_WEB.md — Claude Web (cookie-auth) provider.
CHATGPT_WEB.md — ChatGPT Web (Codex) provider and common-provider retirement note.
COPILOT-M365.md — Microsoft 365 Copilot (BizChat) provider.
ALIBABA-QWEN-PROVIDER-FAMILIES.md — Alibaba and Qwen provider families.
AGENTROUTER.md — AgentRouter setup.
ZED-DOCKER.md — Zed IDE integration under Docker.
CURSOR-DOCKER.md — Cursor model listing under Docker.

comparison/

OMNIROUTE_VS_ALTERNATIVES.md — how OmniRoute compares to alternatives.

ops/

Release, deployment, proxies, tunnels, coverage, database, monitoring.

RELEASE_CHECKLIST.md — release flow checklist.
RELEASE_GREEN.md — keeping the PR queue and release branch green.
BRANCHING_MODEL.md — branching & release model.
MERGE_TRAIN.md — merge queue & manual merge-train runbook.
HOMOLOGATION.md — homologation suite (npm run homolog).
QUALITY_GATE_PLAYBOOK.md — quality-gate playbook.
RUNNER_BOX.md — self-hosted runner box operations.
BRANCH_PROTECTION_MAIN.md — main branch protection.
CONTRIBUTION_GOLDEN_PATH.md — contribution golden path (focused checks per change type).
COVERAGE_PLAN.md — test coverage plan.
DATABASE_GUIDE.md — DB schema and operations.
SQLITE_RUNTIME.md — SQLite driver resolution chain.
REDIS_PRODUCTION_CONFIG.md — Redis production configuration.
MONITORING_GUIDE.md — monitoring & observability.
FLY_IO_DEPLOYMENT_GUIDE.md — Fly.io deployment.
VM_DEPLOYMENT_GUIDE.md — generic VM deployment.
PROXY_GUIDE.md — upstream proxy configuration.
TUNNELS_GUIDE.md — Cloudflare tunnel and friends.

diagrams/

Mermaid sources and exported SVG/PNG diagrams referenced from the docs above. See diagrams/README.md.

i18n/

Translated mirrors of the documentation in 65 locales (plus the English originals — 66 languages in total). See i18n/README.md for the supported language list.

screenshots/

Static screenshots used by the dashboard and the README. Not part of the doc body.

Auto-generated artifacts

reference/PROVIDER_REFERENCE.md is generated by scripts/docs/gen-provider-reference.ts from src/shared/constants/providers.ts. Do not edit by hand.
The /docs UI is backed by Fumadocs MDX source generation from the subfolders above.