settings.yaml Reference

Complete reference for ~/.zwischen/settings.yaml. All keys are optional unless noted.

projects

List of per-directory enable/disable rules. Evaluated in order; longest matching path wins. If omitted, Zwischen is enabled everywhere.

Key	Type	Description
path	string	Directory path (tilde-expanded)
enabled	boolean	Whether Zwischen monitors sessions in this directory

defaults

Baseline configuration for all reviewed agents. Accepts all keys listed below.

profiles

Named entries that deep-merge on top of defaults for specific agents. Each profile accepts all keys listed below, plus a required agents list.

Key	Type	Description
agents	list of strings	Agent names this profile matches. Required for the profile to activate. First match wins.

Configuration keys

These keys are valid in both defaults and individual profiles entries unless noted otherwise.

Model and credentials

Key	Type	Default	Description
model	string	–	Model ID for the reviewer. See Supported Models.
api_key	string	–	Provider API key as ${ENV_VAR} reference. Resolved at runtime; held in process memory only.
auth_mode	string	"api_key"	"api_key" or "oauth". OAuth is supported for OpenAI only.
profile_id	string	"general"	defaults only. Built-in reviewer profile for agents that don't match a named profile. Valid values: general, code, research, prompt, spec. Named profiles select their built-in profile by name — see Built-in reviewer profiles.

Reviewer behavior

Key	Type	Default	Description
system_prompt	string	-	Custom prompt for the reviewer. Use this to make the reviewer more or less strict, focus on specific concerns, or adjust its blocking behavior.
system_prompt_mode	string	"replace"	"replace": replaces the server profile's prompt entirely. "append": adds your prompt after the server profile's prompt. Only meaningful when system_prompt is set.
include_claude_md	boolean	true	Forward your project's CLAUDE.md to the reviewer as context.
web_search	boolean	false	Allow the reviewer to use web search during review.
model_tuning	boolean	true	Apply provider-specific and model-specific prompt adjustments from Zwischen Labs.

Tool visibility and enforcement

Nested under the tools key. All sub-keys accept a list of tool names.

Key	Description
tools.output_visible	Tools whose full output the reviewer can see during live review.
tools.pre_review	Tools reviewed before execution. Reviewer can block the call before it runs.
tools.write_review	Like pre_review, but specialized for Edit/Write – reviewer sees the proposed diff.
tools.whitelisted	Tools passed through without blocking, still streamed as context. Available during blocks.
tools.review_exempt	Tools invisible to the reviewer – no streaming, no enforcement.

Context cycling

Nested under the cycle key.

Key	Type	Description
cycle.threshold_pct	float	Fraction of context window usage that triggers a cycle (e.g., 0.15).
cycle.tail_depth	integer	Number of recent messages carried over after a cycle.

Full example

projects:
  - path: ~/work/sensitive-repo
    enabled: false
  - path: ~/work
    enabled: true

defaults:
  model: gpt-5.4
  profile_id: general
  include_claude_md: true

profiles:
  code:
    agents: [coder, web-dev]
    model: claude-sonnet-4-6
    tools:
      output_visible: [Read, Edit, Write]
      write_review: [Edit, Write]
  research:
    agents: [general]
    model: gemini-2.5-pro
    cycle:
      threshold_pct: 0.15
  data-ops:
    agents: [file-processor]
    system_prompt: |
      This agent processes data files. Block any write outside of
      the data/staging/ directory. Block direct database operations.
    tools:
      review_exempt: [Read, Glob, Grep]