The auto-rotate proxy is intentionally conservative. It rotates only before a request or stream is committed, preserves previous_response_id, turn-state, and session affinity, and does not rotate mid-stream. OpenAI/Codex remains the default quota-aware pool. Gemini OAuth, imported Copilot profiles, Anthropic OAuth profiles, DeepSeek API keys, local OpenAI-compatible URLs, and Bedrock/custom Codex providers now have prodex quota views. Anthropic, DeepSeek, API-key Gemini, API-key Copilot, local URLs, and Bedrock/custom Codex providers still skip OpenAI quota preflight.

Runtime proxy design contract:

• Prodex stays a scoped Codex gateway, not a general-purpose LLM SDK.
• Profile selection must be visible through policy, prodex info, prodex doctor, and runtime logs.
• Pre-commit retry and fallback paths must stay bounded per request.
• Runtime hot paths must avoid broad disk reads, quota probes, or blocking state saves.
• Quota, budget, transport, and local pressure signals must stay classified separately.
• Selection, admission, affinity, backoff, and first-chunk events must be structured in runtime logs.
• Upstream HTTP/WebSocket connection reuse should be preserved where it does not change Codex semantics.
• Secrets remain profile-isolated, redacted in diagnostics, and covered by audit events for Prodex-owned mutations.

npm install -g @christiandoxa/prodex

cargo install --path .

If you install from source, make sure the codex binary in your PATH is already installed and up to date.

prodex caveman mem
prodex caveman mem rtk
prodex rtk
prodex sqz
prodex tokensavior
prodex clawcompactor
prodex presidio doctor
prodex presidio redact --text "My phone is 212-555-1234"
prodex s
prodex super
prodex claude mem
prodex claude caveman mem

Claude-Mem is used by the mem variants.

Recommended install:

npx claude-mem install

Then follow the interactive prompts.

You can also install it from inside Claude Code:

/plugin marketplace add thedotmack/claude-mem
/plugin install claude-mem

After installation, restart Claude Code or your coding CLI.

Do not use npm install -g claude-mem as the main install method. That installs the SDK/library only; it does not register the plugin hooks or start the worker service.

RTK is used by the rtk variants and by my daily prodex s / prodex super workflow.

Homebrew

brew install rtk-ai/tap/rtk

Linux/macOS quick install

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/master/install.sh | sh

If it installs to ~/.local/bin, make sure that directory is in your PATH:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc

For Zsh:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc

Cargo

cargo install --git https://github.com/rtk-ai/rtk rtk

Verify RTK

rtk --version
rtk gain

If rtk --version works but rtk gain fails, you may have installed a different package named rtk.

Remove it and reinstall from the Git URL:

cargo uninstall rtk
cargo install --git https://github.com/rtk-ai/rtk rtk

Initialize RTK

For Codex:

rtk init -g --codex

For Claude Code:

rtk init -g

Then restart your coding tool.

SQZ is used by prodex sqz and by Super mode when the sqz-mcp binary is available on PATH or under a managed optimizer checkout.

Recommended Linux/macOS install:

curl -fsSL https://raw.githubusercontent.com/ojuschugh1/sqz/main/install.sh | sh

Windows PowerShell:

irm https://raw.githubusercontent.com/ojuschugh1/sqz/main/install.ps1 | iex

Alternative npm install:

npm install -g sqz-cli

Optional source install:

cargo install sqz-cli

Initialize hooks if you also want SQZ outside Prodex:

sqz init --global
# or only for the current project
sqz init

Verify:

sqz --version
sqz gain
which sqz-mcp

Prodex auto-registers prodex-sqz for Super/Caveman overlay sessions when sqz-mcp is discoverable.

token-savior is used by prodex tokensavior and by Super mode when the token-savior binary is available on PATH or under a managed optimizer checkout.

Recommended isolated install:

git clone https://github.com/Mibayy/token-savior ~/.local/share/prodex-optimizers/token-savior
python3.12 -m venv ~/.local/share/prodex-optimizers/token-savior/.venv
~/.local/share/prodex-optimizers/token-savior/.venv/bin/pip install -e "$HOME/.local/share/prodex-optimizers/token-savior[mcp]"
ln -sf ~/.local/share/prodex-optimizers/token-savior/.venv/bin/token-savior ~/.local/bin/token-savior

Use a stable Python interpreter supported by token-savior dependencies, such as Python 3.11, 3.12, or 3.13. Avoid pointing this MCP server at experimental Python releases unless its native dependencies already support them.

Make sure ~/.local/bin is on PATH:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc

If you use Zsh:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc

Verify:

token-savior --help
which token-savior

Prodex handles MCP registration for its own overlay session when it can find the binary, so you do not need to manually edit .mcp.json just for prodex super.

claw-compactor is used by prodex clawcompactor and by Super mode as a deterministic/local context compaction aid. When discoverable, Super installs a trusted one-shot startup probe that runs claw-compactor benchmark <workspace> --json through Prodex's compatibility wrapper and uses a marker under CODEX_HOME to avoid replay after Codex conversation restarts. If the workspace has no Markdown memory files, Prodex benchmarks a temporary shadow workspace with a synthetic MEMORY.md summary instead of writing into the original directory.

Recommended source install:

git clone https://github.com/aeromomo/claw-compactor.git ~/.local/share/claw-compactor
python3 -m venv ~/.local/claw-compactor-venv
~/.local/claw-compactor-venv/bin/pip install -e "$HOME/.local/share/claw-compactor[accurate]"

If you only need exact token counting for the scripts:

~/.local/claw-compactor-venv/bin/pip install tiktoken

Expose the checkout to Prodex's managed optimizer discovery:

mkdir -p ~/.local/share/prodex-optimizers
ln -sfn ~/.local/share/claw-compactor ~/.local/share/prodex-optimizers/claw-compactor

Quick non-destructive benchmark:

python3 ~/.local/share/claw-compactor/scripts/mem_compress.py /path/to/workspace benchmark

Presidio is used by prodex presidio and by the optional Super-mode privacy prompt. It runs as local Analyzer and Anonymizer HTTP services.

Fast Docker install using Microsoft's published images:

docker pull mcr.microsoft.com/presidio-analyzer
docker pull mcr.microsoft.com/presidio-anonymizer

docker run -d --name presidio-analyzer -p 5002:3000 mcr.microsoft.com/presidio-analyzer:latest
docker run -d --name presidio-anonymizer -p 5001:3000 mcr.microsoft.com/presidio-anonymizer:latest

Source checkout with Compose:

git clone https://github.com/microsoft/presidio.git ~/.local/share/presidio
cd ~/.local/share/presidio
docker compose -f docker-compose-text.yml up -d --build

Verify with Prodex:

prodex presidio doctor
prodex presidio redact --text "My name is John Smith and my phone is 212-555-1234."
prodex presidio redact --language-mode auto --languages en,id --text "Nama saya Budi dan nomor telepon saya adalah 0812-3456-7890."
prodex presidio redact --language id --text "Nomor telepon saya adalah 0812-3456-7890."
prodex presidio enable
prodex presidio redact --language-mode auto --languages en,id --text "Nama saya Budi dan nomor telepon saya adalah 0812-3456-7890."
prodex presidio enable --language-mode auto --languages en,id
prodex presidio status
prodex presidio doctor --json
prodex presidio redact --language-mode auto --languages en,id --text "Nama saya Budi dan nomor telepon saya adalah 0812-3456-7890."
prodex presidio enable --language-mode auto --languages en,id
prodex presidio redact --language-mode auto --languages en,id --text "Nama saya Budi dan nomor telepon saya adalah 0812-3456-7890."
prodex presidio enable --language-mode auto --languages en,id
prodex presidio status
prodex presidio doctor --json
prodex presidio status
prodex presidio doctor --json

When you answer y to the prodex super / prodex s Presidio prompt or pass --presidio, Super starts a dedicated runtime proxy that redacts UTF-8 HTTP request bodies and WebSocket text frames through the local Presidio Analyzer and Anonymizer before forwarding them upstream. This is equivalent to adding the presidio prefix to the Super stack. Use --no-presidio to skip the prompt and keep redaction disabled. The runtime uses presidio.toml endpoints when configured, falls back to http://localhost:5002 and http://localhost:5001, and honors fail_mode = "open" or "closed".

If your current Codex home is already logged in:

prodex profile import-current main

prodex login
prodex profile add second
prodex login --profile second
prodex login --with-google
prodex login --with-claude

Interactive prodex login now asks for the login method before starting a browser. Choose ChatGPT browser login, device-code login, API-key login, Google sign-in for Gemini, or Claude sign-in through Claude Code OAuth. For API-key profiles, you can also set an OpenAI-compatible backend URL:

printf '%s\n' "$OPENAI_API_KEY" | prodex login --with-api-key --base-url http://localhost:11434/v1

prodex profile list
prodex quota --all
prodex session list

prodex

Or run a one-off prompt:

prodex exec "review this repo"

prodex profile import claude
prodex profile import claude --name claude-main --activate

This imports the current Claude Code OAuth credentials from CLAUDE_CONFIG_DIR or ~/.claude into a Prodex-managed Anthropic profile. You can also use prodex login --with-claude to sign in through Claude Code directly.

prodex profile import copilot
prodex profile import copilot --name copilot-main --activate

When you import a Copilot profile, Prodex does not move the Copilot token into Prodex-managed storage. It only records the provider identity and API endpoint in its own metadata.

For daily work, I use:

prodex s

prodex s is an alias for:

prodex super

This is the mode I tune and use myself every day.

It combines:

• Caveman mode
• Claude-Mem transcript watching
• RTK shell-command guidance
• full-access launch mode
• Smart Context Autopilot in the runtime proxy
• deterministic/local accommodation for sqz, token-savior, and claw-compactor low-token workflows

prodex s
prodex s exec "review this repo"
prodex s expose

prodex super expands to:

prodex caveman mem rtk sqz tokensavior clawcompactor --full-access

Before launch, Super asks whether to add Presidio redaction. Empty input or n keeps the expansion above. If you answer y, it is equivalent to:

prodex caveman mem rtk sqz tokensavior clawcompactor presidio --full-access

Use prodex super --presidio to enable Presidio without prompting, or prodex super --no-presidio to skip the prompt and keep Presidio disabled. Presidio enables runtime request-body and WebSocket text redaction through local Presidio for the session. The runtime uses presidio.toml endpoints when configured, falls back to http://localhost:5002 and http://localhost:5001, and honors fail_mode = "open" or "closed".

Full access maps to Codex's sandbox-bypass launch flag. Use it only when you intentionally want Codex to run without the normal approval and sandbox protections.

Use prodex s expose when you need to reach the live Super terminal from a browser. Prodex starts a local PTY bridge protected by a high-entropy access token, launches cloudflared tunnel --protocol http2 --url ... when cloudflared is available, and prints both the loopback and Cloudflare quick-tunnel URLs. The browser tab can close without stopping the session; reopening the same token URL reconnects to the existing PTY and replays recent scrollback. Add --no-tunnel for local-only access, --max-clients N to cap simultaneous browsers, or --command 'prodex s --no-presidio' to choose the initial terminal command.

Super's built-in optimization stack is deliberately local and deterministic. It preloads the existing Caveman and Claude-Mem pieces, exposes an overlay rtk wrapper plus RTK auto-wrappers for common noisy commands when RTK is installed, auto-registers sqz-mcp and token-savior MCP servers when those binaries are already on PATH or in a managed prodex-optimizers checkout, exposes sqz and claw-compactor wrappers when those commands/checkouts are discoverable, invokes a trusted one-shot prodex-claw-compactor-sessionstart SessionStart benchmark probe when Claw-Compactor is available, falls back to a temporary shadow MEMORY.md when the workspace has no Markdown memory files, then uses Smart Context Autopilot through a dedicated runtime proxy for lower-token request shaping. The probe delegates to prodex-claw-compactor-auto "$(pwd)" and uses a marker under CODEX_HOME so Codex conversation restarts do not replay it. Presidio redaction is added to that proxy only when you opt in at the prompt. Prodex passes token-savior cache and stats paths under PRODEX_HOME (default ~/.prodex) so compatible token-savior versions keep generated state out of worktrees.

RTK and SQZ split the token work across different sides of the flow:

• RTK works upstream/input-side. Use visible rtk <cmd> for noisy terminal commands before their output enters the model context, such as git diff, cargo test, npm test, build logs, and package-manager output. Prodex also auto-wraps common noisy commands as a fallback when RTK is installed, but that fallback does not make the TUI show an rtk prefix.
• SQZ works downstream/context-side through the auto-registered prodex-sqz MCP server. Use it for repeated workspace reads, large text blobs, and long-session context reuse instead of emitting the same full content again.

Managed optimizer checkouts are discovered from PRODEX_OPTIMIZERS_HOME, $XDG_DATA_HOME/prodex-optimizers, then ~/.local/share/prodex-optimizers.

prodex
prodex s
prodex s expose
prodex exec "review this repo"
prodex quota --all
prodex profile list
prodex session list

prodex
prodex run
prodex run --profile main
prodex run --dry-run
prodex exec "review this repo"

prodex s
prodex s exec "review this repo"
prodex super
prodex super --profile main
prodex super --dry-run

prodex quota --all
prodex quota --all --once
prodex quota --all --auth no-auth --once
prodex quota --all --detail --provider openai
prodex quota --all --provider deepseek --once
prodex quota --all --provider local --base-url http://127.0.0.1:8131/v1 --once
prodex dashboard

The live prodex quota --all --detail view accepts s to cycle sort modes and f to cycle the provider filter through all, openai, gemini, anthropic, copilot, deepseek, and local. Add --provider openai, --provider gemini, --provider anthropic, --provider copilot, --provider deepseek, or --provider local to start locked to a single provider.

prodex dashboard serves a local browser dashboard at http://127.0.0.1:8765 by default. It shows profile/account settings, lets you switch or remove profile entries, and renders live usage from the same quota collectors used by prodex quota. Use prodex dashboard --port 0 for an OS-selected free port, or pass --base-url for quota checks against a custom Codex-compatible backend. The dashboard has no password auth; keep it on localhost unless the network is trusted.

prodex session list
prodex session current
prodex session current --include-subagents

prodex update --help

prodex update passes through to codex update directly. It does not use Prodex profile selection, quota preflight, or the local runtime proxy.

prodex run 019c9e3d-45a0-7ad0-a6ee-b194ac2d44f9
printf 'context from stdin' | prodex run exec "summarize this"

Unknown top-level Codex subcommands remain managed Codex launches.

For example:

prodex remote-control

is equivalent to:

prodex run remote-control

unless Prodex explicitly owns that command.

prodex
prodex run
prodex run --profile main
prodex exec "review this repo"

prodex caveman
prodex caveman mem
prodex caveman mem rtk
prodex rtk
prodex sqz
prodex tokensavior
prodex clawcompactor
prodex caveman --dry-run
prodex caveman --profile main
prodex caveman exec "review this repo in caveman mode"
prodex caveman 019c9e3d-45a0-7ad0-a6ee-b194ac2d44f9

prodex caveman runs Codex with a temporary overlay CODEX_HOME, so the base profile home stays unchanged after the session ends.

If you use the mem variant, Prodex points an existing Claude-Mem Codex setup to the active Prodex session path instead of the default ~/.codex/sessions.

Add optimizer prefixes before Codex args when you want Prodex to inject a specific launch overlay for that session: mem, rtk, sqz, tokensavior, clawcompactor, or presidio. Top-level shortcuts such as prodex rtk and prodex sqz map to prodex caveman <prefix>.

RTK is still an external binary. Install it separately if rtk gain is unavailable.

prodex s
prodex s exec "review this repo"
ANTHROPIC_API_KEY=... prodex s --provider anthropic --model claude-sonnet-4-6
prodex profile import copilot
prodex s --provider copilot --model gpt-5.1-codex
DEEPSEEK_API_KEY=... prodex s deepseek --model deepseek-v4-pro
prodex s gemini
prodex super
prodex super --profile main
prodex super --dry-run
prodex super 019c9e3d-45a0-7ad0-a6ee-b194ac2d44f9

prodex s is the short alias for prodex super.

This is my daily mode. It is the path I keep tuning for normal work: Caveman enabled, Claude-Mem transcript watching enabled, RTK guidance enabled, full access available, and context handling handled by the runtime proxy.

Super mode uses Prodex's slim Claude-Mem Codex schema by default to avoid storing full assistant/tool output in recall context.

Use --mem-super-slim to store prompt summaries/references instead of full prompt bodies:

prodex super --mem-super-slim

Use --mem-full when you need the full transcript schema:

prodex super --mem-full

Super also enables Smart Context Autopilot in the runtime proxy.

Use --provider anthropic when you want the Codex/Super front end with Anthropic upstream:

prodex login --with-claude
prodex s --provider anthropic --model claude-sonnet-4-6
prodex s --provider anthropic --model claude-sonnet-4-6 --api-key "$ANTHROPIC_API_KEY"

If --api-key is omitted, Prodex uses the Anthropic profile created by prodex login --with-claude or prodex profile import claude. API-key mode still reads ANTHROPIC_API_KEY; ANTHROPIC_API_KEYS may contain multiple comma-, semicolon-, or newline-separated keys for round-robin request rotation and pre-commit retry on auth/quota/rate/temporary failures. This path injects a temporary prodex-anthropic Codex provider, exposes a local /v1/responses adapter to Codex, forwards to Anthropic's OpenAI-compatible chat API, and keeps quota preflight disabled. prodex quota --all --provider anthropic shows OAuth readiness for Anthropic profiles; set ANTHROPIC_ADMIN_KEY when you want Anthropic Admin rate-limit groups included.

Use --provider copilot when you want the Codex/Super front end with GitHub Copilot upstream:

prodex profile import copilot
prodex s --provider copilot --model gpt-5.1-codex

Without --api-key, Prodex uses imported Copilot CLI profiles, refreshes Copilot runtime API tokens from GitHub before launch, rotates fresh native Responses requests across eligible profiles, and binds streaming response IDs back to the owning profile for continuations. GITHUB_COPILOT_API_KEY, GITHUB_COPILOT_API_KEYS, or --api-key can be used when you already have Copilot runtime API token(s); plural keys may be comma-, semicolon-, or newline-separated and rotate before commit on auth/quota/rate/temporary failures.

Use --provider deepseek when you want the Codex/Super front end with DeepSeek as the upstream model:

prodex s deepseek --model deepseek-v4-pro --api-key "$DEEPSEEK_API_KEY"

If --api-key is omitted, Prodex reads DEEPSEEK_API_KEY; DEEPSEEK_API_KEYS may contain multiple comma-, semicolon-, or newline-separated keys for round-robin request rotation and pre-commit retry on auth/quota/rate/temporary failures. This path injects a temporary prodex-deepseek Codex provider, exposes a local /v1/responses adapter to Codex, forwards to DeepSeek's OpenAI-format chat API, and keeps quota preflight disabled. Prodex also injects a one-model Codex catalog for the selected DeepSeek model, so /model stays on that model and offers the DeepSeek-compatible high/xhigh effort choices. prodex quota --all --provider deepseek reads the same DEEPSEEK_API_KEY(S) environment and fetches DeepSeek /user/balance. The Super optional tools still run normally because they are local launch overlays around Codex. Remote compact is not implemented for this adapter yet, so the default DeepSeek context window is large and --auto-compact-token-limit defaults high.

Use --provider gemini when you want the Codex/Super front end with Gemini upstream:

prodex login --with-google
prodex s gemini
prodex s gemini --cli gemini
prodex s gemini --cli agy
GEMINI_API_KEY=... prodex s gemini --model gemini-2.5-pro
prodex s gemini --model gemini-2.5-pro --api-key "$GEMINI_API_KEY"

Without --api-key, Prodex uses the Google OAuth profile created by prodex login and routes through Google's Code Assist Gemini endpoint. Google login verifies Code Assist readiness before creating or updating the profile, and may open a second browser page if Google requires account verification. With --api-key, or GEMINI_API_KEY(S) / GOOGLE_API_KEY(S), Prodex converts Codex Responses requests to Chat Completions and sends them through Google's documented /v1beta/openai/chat/completions endpoint with Bearer authentication. Streaming, function calls, continuations, and Gemini reasoning_effort values are converted back into Codex Responses semantics. Plural key env vars may be comma-, semicolon-, or newline-separated and rotate before commit on auth/quota/rate/temporary failures. OAuth sessions keep fresh Gemini requests sticky to the previous successful profile by default for smoother Codex-style continuity; set PRODEX_GEMINI_STICKY_FRESH_OAUTH=0 to restore pure fresh-request round robin. The default model is auto, matching Gemini CLI-style model routing through Gemini 3 and stable fallbacks; launch-time Gemini modelConfigs / modelIdResolutions / modelChains are projected into the Codex catalog and runtime fallback snapshot when configured. The injected catalog exposes Gemini reasoning efforts with the 2.5 default thinking budget of 8192 where budget mode is used. prodex quota reads the same Google OAuth profile and fetches Gemini Code Assist retrieveUserQuota bucket data. The Super optional tools still run as local Codex overlays on this path.

prodex s gemini --cli gemini launches the native Google Gemini CLI instead of Codex, defaults its native tools to YOLO approval mode, and routes Code Assist requests through Prodex OAuth profile rotation. This native CLI path currently requires a Google OAuth profile and does not accept --api-key. Set PRODEX_GEMINI_BIN to override the gemini executable.

prodex s gemini --cli agy launches the native Antigravity CLI with --dangerously-skip-permissions so tool permission prompts are auto-approved. Antigravity CLI owns its authentication through the system keyring/Google Sign-In and does not expose an endpoint or token override, so Prodex account auto-rotation and Presidio proxying are not available on this path. Set PRODEX_AGY_BIN to override the agy executable.

The OAuth bridge also maps native Gemini computerUse, code execution, grounding/citation/URL-context metadata, generated images, video metadata, multimodal file inputs, log-probability metadata, tool-use and cached-token accounting, safety metadata, and Gemini finish reasons into Codex-compatible request, response, and SSE shapes. Citations are emitted as a separate completed output item after Gemini supplies a finish reason. Assistant followups retain native Gemini code, media, video, cache, and thought-signature parts without replaying citation display text as model history.

@path and bounded read_many_files context honor default binary/build/dependency exclusions plus ordered root .gitignore, .geminiignore, and custom ignore files, including later negation overrides. Large tool outputs are masked before replaying them into Gemini history and are written to PRODEX_GEMINI_TOOL_OUTPUT_DIR or the OS temp directory; set PRODEX_GEMINI_TOOL_OUTPUT_MASK_THRESHOLD=0 to disable this guard. Codex /responses/compact requests use a tool-free unary Gemini semantic-compaction turn on the Gemini CLI chat-compression-default alias and return Codex replacement history; a bounded deterministic local summary is used only when semantic compaction fails before commit. Invalid pre-commit Gemini streams are retried with bounded backoff before model fallback.

Gemini CLI compatibility helpers accept inline gemini_memory / gemini_policy / gemini_session request metadata, file-based gemini_*_file imports, and PRODEX_GEMINI_SESSION_FILE or PRODEX_GEMINI_CHECKPOINT_FILE import paths. Gemini memory is loaded by default from ~/.gemini/GEMINI.md, ancestor GEMINI.md files, .gemini/memory/MEMORY.md, and .gemini/memory/INBOX.md; set PRODEX_GEMINI_DISABLE_MEMORY=1, PRODEX_GEMINI_DISABLE_CONTEXT_FILES=1, or request metadata gemini_load_memory=false to opt out. Gemini settings are read in CLI precedence order from system defaults, global, ancestor project, cwd-local, and system override settings, honoring GEMINI_CLI_HOME, GEMINI_CLI_SYSTEM_SETTINGS_PATH, and GEMINI_CLI_SYSTEM_DEFAULTS_PATH; extension manifests and extension policy TOML files are also read when present to apply Gemini tool allow/exclude, hard command-specific tool-call blocking, and defaultApprovalMode behavior.

Before Codex launches, the Gemini provider projects Gemini CLI settings and extension surfaces into the active CODEX_HOME: system/global/project mcpServers and extension mcpServers become generated Codex [mcp_servers.gemini_*] entries with settings taking precedence over extension servers of the same Gemini name; system/global/project and extension command hooks are merged into hooks.json for Codex /hooks review; ~/.gemini/commands, project .gemini/commands, and extension commands/*.toml become Codex custom prompts with Gemini command aliases preserved where possible; extension skills/*/SKILL.md are copied into generated Codex skill folders under .agents/skills; and extension agents/*.md become generated Codex custom agents under agents/*.toml. Built-in /prompts:gemini-refresh, /prompts:gemini-memory-show, /prompts:gemini-memory-refresh, /prompts:gemini-memory-inbox, /prompts:gemini-remember, /prompts:gemini-checkpoint-create, /prompts:gemini-checkpoint-restore, /prompts:gemini-checkpoint-export, and /prompts:gemini-rewind cover reload/admin, memory, and checkpoint workflows. Generated helper scripts in CODEX_HOME/bin include prodex-gemini-refresh, prodex-gemini-checkpoint-create, and prodex-gemini-checkpoint-restore. Set PRODEX_GEMINI_EXTENSIONS=none or an allow-list of extension names to control extension loading, PRODEX_GEMINI_EXTENSION_DIRS to add extension roots, or PRODEX_GEMINI_DISABLE_CLI_COMPAT=1 to skip the launch-time Codex surface projection.

Gemini Live realtime websocket sessions translate Codex audio, transcript, text, function-call, function-result, interruption, cancellation, housekeeping, and turn-completion events to and from Gemini BidiGenerateContent; one Gemini auth/profile is selected before upgrade and remains fixed for the session. PRODEX_GEMINI_LIVE_MODEL overrides the default Live model, while PRODEX_GEMINI_LIVE_URL is available for a custom or test Live endpoint. prodex doctor --runtime recognizes provider bridge and Gemini markers such as local_rewrite_provider_model_fallback, local_rewrite_gemini_quota_rotate, local_rewrite_gemini_invalid_stream_retry, and local_rewrite_gemini_live_error.

Run npm run test:gemini-schema after changing Gemini request, response, SSE, semantic compact, exact-output, tool-schema, or Live translation. Run PRODEX_LIVE_GEMINI=1 npm run test:gemini-live for a credentialed end-to-end Gemini adapter smoke request; set PRODEX_BIN or PRODEX_LIVE_GEMINI_MODEL to override the binary or model. Add PRODEX_LIVE_GEMINI_EXTENDED=1 for command-output-only, file edit, apply_patch, reference-repo clone/inspection, optional-tool update discipline, semantic compact, and explicit exec resume checks. Add PRODEX_LIVE_GEMINI_MCP=1 and/or PRODEX_LIVE_GEMINI_MULTIMODAL=1 when the local environment should also exercise MCP and image-input paths.

Before launch, Super asks whether to add Presidio redaction. Empty input or n keeps Presidio disabled; answer y or pass --presidio to add the presidio prefix. Use --no-presidio to make the disabled choice explicit for non-interactive use.

Prodex now supports multi-language Presidio redaction, including automatic detection and multi-language merging. The runtime uses presidio.toml endpoints and language configuration when available, falling back to http://localhost:5002 and http://localhost:5001 for Analyzer/Anonymizer URLs, and English (en) for language if not specified. It honors fail_mode = "open" or "closed".

Example presidio.toml with multi-language support (English and Indonesian):

enabled = true
analyzer_url = "http://localhost:5002"
anonymizer_url = "http://localhost:5001"
language_mode = "auto"
languages = ["en", "id"]
fail_mode = "open"

Note that the default Microsoft Presidio Docker images typically only support English (en). To support other languages like Indonesian (id), you must use a custom Presidio Analyzer image with the necessary language models and recognizers installed. Prodex routing and configuration support the languages, but the actual detection quality depends on your Analyzer.

It keeps exact pass-through for continuation-sensitive requests. When safe, it uses adaptive token budgeting, artifact-backed large tool outputs, duplicate suppression, blob/noise detection, stable cache-friendly context framing, and critical-signal self-checks to reduce token load without dropping failure details.

The Super optimization stack is meant to stay deterministic and local by default. It auto-registers sqz-mcp and token-savior MCP servers when those binaries are already on PATH or in a managed prodex-optimizers checkout, exposes sqz and claw-compactor wrappers when discoverable, routes compatible token-savior cache/state under PRODEX_HOME instead of the workspace, and uses a dedicated runtime proxy for local compaction, stable references, and lower-token context shaping rather than hidden remote summarization.

RTK handles upstream/input command output before it enters the context window, using visible rtk <cmd> commands and overlay auto-wrappers when available. Auto-wrappers are only a backstop; write rtk <cmd> explicitly when you want the TUI/transcript to show RTK usage. SQZ handles downstream/context reuse after content is already in the session, using prodex-sqz when the MCP server is available.

Managed optimizer checkouts are discovered from PRODEX_OPTIMIZERS_HOME, $XDG_DATA_HOME/prodex-optimizers, then ~/.local/share/prodex-optimizers.

prodex claude -- -p "summarize this repo"
prodex claude mem -- -p "recall past work on this repo"
prodex claude caveman
prodex claude caveman mem
prodex claude caveman -- -p "summarize this repo briefly"
prodex claude caveman mem -- -p "summarize this repo briefly"
prodex claude --profile second caveman -- -p "review the latest diff briefly"
prodex claude --profile second -- -p --output-format json "show the latest diff"

prodex claude uses the normal Claude Code flow while keeping state under Prodex-managed configuration.

prodex claude caveman enables Caveman for that session while keeping state under the Prodex-managed CLAUDE_CONFIG_DIR, not the global ~/.claude.

prodex claude caveman mem combines Caveman and Claude-Mem.

prodex claude is only supported with the default OpenAI/Codex provider.

prodex profile list
prodex profile add second
prodex profile import-current main
prodex login --profile second
prodex use --profile main
prodex logout --profile main

prodex profile import copilot
prodex profile export
prodex profile remove second
prodex profile remove --all

Prodex can launch Super mode against a local OpenAI-compatible server:

prodex super --url http://127.0.0.1:8131

You can use this with a local server such as llama-server.

By default, Prodex:

• injects a temporary prodex-local Codex provider
• appends /v1 when the URL has no path
• disables non-function native tools that local servers commonly reject
• advertises a conservative 16k local context window
• skips quota/proxy routing for that launch

Check local server reachability with:

prodex quota --all --provider local --base-url http://127.0.0.1:8131/v1 --once

The default local model id is:

unsloth/qwen3.5-35b-a3b

Override it with --model:

prodex super --url http://127.0.0.1:8131 --model local/qwen

Use --context-window and --auto-compact-token-limit if your local server is configured with a larger context window.

See LOCAL.md for self-hosted model setup and testing.

prodex info
prodex doctor --install
prodex doctor --runtime
prodex doctor --bundle ./prodex-doctor.json --redacted
prodex setup --dry-run
prodex capability list
prodex context audit
prodex context compress ~/.codex/AGENTS.md --dry-run
git diff | prodex context compact-output --kind git-diff

For full policy keys, environment overrides, and runtime log path resolution, see docs/runtime-policy.md.

When a support case appears to come from upstream Codex itself, run codex doctor --json in the same environment as Prodex. Codex 0.135.0 and newer reports richer environment, Git, terminal, app-server, and thread-inventory diagnostics than Prodex's runtime-proxy doctor owns.

Managed Prodex profiles keep account credentials isolated per profile, but Codex-owned shared state uses the native Codex home by default.

On Unix-like systems, this is usually:

~/.codex

In practice, profile history.jsonl, sessions, archived_sessions, config.toml, managed_config.toml, environments.toml, plugins, skills, app-server plugin state, memory-extension state, remote-control enrollment, and Codex runtime SQLite files such as state_*, goals_*, logs_*, and memories_* link to the same Codex home that direct Codex uses.

Codex cloud-managed config bundle caches are identity/account scoped and remain profile-local. System-level Codex requirements and managed config files remain owned by upstream Codex and the operating system.

Prodex does not synthesize legacy Codex [profiles.*] behavior. File-based Codex profile config selected by --profile stays in shared Codex state, while Prodex-owned account selection remains in Prodex profile metadata.

Prodex also leaves packaged Codex runtime resources alone, including Codex 0.136.0 and newer bundled zsh runtime helpers under the Codex package layout. Do not set zsh_path through Prodex unless you are intentionally debugging direct Codex config.

This matches direct Codex behavior: logging out or switching accounts does not hide chat history.

Older Prodex state from $PRODEX_HOME/.codex is merged into the native Codex home on the next managed-profile launch.

Set PRODEX_SHARED_CODEX_HOME only when you intentionally want a different shared Codex root.

Auto-rotate and quota checks apply to supported OpenAI/Codex profiles. prodex quota also supports Google Gemini OAuth profiles, Anthropic OAuth profiles, imported Copilot accounts, DeepSeek API-key balances, local OpenAI-compatible health snapshots, and configured custom providers.

If a profile's config.toml sets model_provider to a non-OpenAI backend such as amazon-bedrock, prodex run and prodex caveman launch Codex directly without quota preflight or the local auto-rotate proxy.

Bedrock quota, credentials, regions, and provider errors are handled by Codex and the upstream provider, not by Prodex.

prodex quota shows the configured provider metadata for those profiles instead of failing the view.

Prodex respects system and environment proxy settings for upstream OpenAI quota, auth, and runtime HTTP by default, including:

HTTP_PROXY
HTTPS_PROXY
NO_PROXY

Runtime WebSocket upstream connections also honor HTTPS_PROXY and https_proxy via HTTP CONNECT and respect NO_PROXY and no_proxy.

The local Codex-to-Prodex broker connection always receives NO_PROXY entries for:

127.0.0.1
localhost
::1

This prevents a user proxy from intercepting the local runtime proxy.

Use --no-proxy on prodex run, prodex caveman, prodex super, or prodex claude only when you explicitly want Prodex upstream requests to bypass proxy settings.

This repository is a Cargo workspace.

The binary crate stays at the root, while reusable leaf crates live under crates/ to reduce rebuild scope when those components change.

Contributor testing guidance lives in docs/testing.md, including the fast/serial split and runtime parallel-safety assumptions.