Merge pull request #35 from o3LL/docs/env-configuration-reference

docs: generate the ODYSSEUS_* configuration reference from the source
This commit is contained in:
Alexandre Teixeira
2026-10-01 02:53:07 +01:00
committed by GitHub
6 changed files with 1586 additions and 0 deletions
+5
View File
@@ -1,5 +1,10 @@
# Odysseus UI — Environment Configuration
# Copy this file to .env and fill in your values.
#
# This file stays deliberately short: it is for deployment-level overrides, and
# most runtime configuration belongs in Settings inside the app. For the complete
# list of ODYSSEUS_* variables the code reads, with the default each one falls
# back to, see website/configuration-reference.md (generated from the source).
# ============================================================
# LLM Configuration
File diff suppressed because it is too large Load Diff
+1
View File
@@ -19,6 +19,7 @@ PUBLIC_GUIDES = {
"agent-migration.md",
"attachments.md",
"backup-restore.md",
"configuration-reference.md",
"email-outlook.md",
"pr-blocker-audit.md",
"security-ci.md",
+223
View File
@@ -0,0 +1,223 @@
"""Guards for the generated ODYSSEUS_* configuration reference.
`website/configuration-reference.md` is produced by
`scripts/generate_env_reference.py`. The point of these tests is that adding a
new `ODYSSEUS_*` read without documenting it fails the suite: the current state -
most of the configuration surface undiscoverable - happened because nothing
objected.
The generator's detection is exercised against a synthetic source tree rather
than against the real one, so a test failure names a behavior rather than a
count that drifted. Only the two whole-tree tests touch the repository, and they
compare generator output to the committed page instead of asserting on source
text.
"""
import re
import subprocess
import sys
from pathlib import Path
import pytest
from tests.helpers.cli_loader import load_script
REPO = Path(__file__).resolve().parent.parent
PAGE = REPO / "website" / "configuration-reference.md"
@pytest.fixture(scope="module")
def generator():
return load_script("generate_env_reference.py")
@pytest.fixture(scope="module")
def built(generator):
"""The generator run once against the real tree; reused by the slow tests."""
return generator.build()
def _write(root: Path, relative: str, body: str) -> None:
path = root / relative
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(body, encoding="utf-8")
@pytest.fixture
def fake_tree(tmp_path, generator, monkeypatch):
"""A miniature source tree covering every read pattern the generator claims."""
monkeypatch.setattr(generator, "SOURCE_ROOTS", ("app.py", "src"))
_write(tmp_path, "app.py", """
import os
DIRECT = os.environ.get("ODYSSEUS_DIRECT_GET", "on")
GETENV = os.getenv("ODYSSEUS_PLAIN_GETENV")
SUBSCRIPT = os.environ["ODYSSEUS_SUBSCRIPT"]
SPANNING = os.environ.get(
"ODYSSEUS_SPANS_TWO_LINES", "spanned"
)
os.environ["ODYSSEUS_WRITE_ONLY"] = "1"
""")
_write(tmp_path, "src/indirect.py", '''
import os
NAME_HELD_IN_CONSTANT = "ODYSSEUS_VIA_CONSTANT"
FALLBACK = 7
value = os.environ.get(NAME_HELD_IN_CONSTANT, FALLBACK)
def read_limit(name, default):
"""An env-reader helper: the generator should follow calls to this."""
raw = os.getenv(name)
return default if raw is None else int(raw)
LIMIT = read_limit("ODYSSEUS_VIA_HELPER", 5 * 1024)
def flag(environ=None):
source = os.environ if environ is None else environ
return source.get("ODYSSEUS_VIA_MAPPING_ARG", "1")
GENERATED = [
"import os",
"if os.environ.get('ODYSSEUS_INSIDE_A_STRING'): pass",
]
''')
return tmp_path
def test_finds_every_read_pattern_it_claims_to(generator, fake_tree):
found = generator.collect(fake_tree)
assert set(found) == {
"ODYSSEUS_DIRECT_GET",
"ODYSSEUS_PLAIN_GETENV",
"ODYSSEUS_SUBSCRIPT",
"ODYSSEUS_SPANS_TWO_LINES",
"ODYSSEUS_VIA_CONSTANT",
"ODYSSEUS_VIA_HELPER",
"ODYSSEUS_VIA_MAPPING_ARG",
"ODYSSEUS_INSIDE_A_STRING",
}
def test_a_plain_grep_would_miss_what_the_extra_passes_find(generator, fake_tree):
"""Pins why the generator is not a one-line grep."""
naive = generator.naive_line_scan(fake_tree)
found = set(generator.collect(fake_tree))
assert found - naive == {
"ODYSSEUS_SPANS_TWO_LINES",
"ODYSSEUS_VIA_CONSTANT",
"ODYSSEUS_VIA_HELPER",
"ODYSSEUS_VIA_MAPPING_ARG",
}
# And it over-counts in the other direction: a line-based scan cannot tell a
# write from a read, which is why the page reports the intersection.
assert naive - found == {"ODYSSEUS_WRITE_ONLY"}
def test_records_defaults_and_locations_from_the_source(generator, fake_tree):
found = generator.collect(fake_tree)
assert found["ODYSSEUS_DIRECT_GET"].primary.default == "'on'"
assert found["ODYSSEUS_SPANS_TWO_LINES"].primary.default == "'spanned'"
# One level of indirection is resolved: the name and the default both come
# from module-level constants.
assert found["ODYSSEUS_VIA_CONSTANT"].primary.default == "7"
assert found["ODYSSEUS_VIA_HELPER"].primary.default == "5 * 1024"
assert found["ODYSSEUS_PLAIN_GETENV"].primary.default is None
assert found["ODYSSEUS_DIRECT_GET"].primary.location == "app.py:4"
assert found["ODYSSEUS_VIA_HELPER"].primary.path == "src/indirect.py"
def test_environ_writes_are_not_reads(generator, fake_tree):
assert "ODYSSEUS_WRITE_ONLY" not in generator.collect(fake_tree)
def test_an_undocumented_variable_is_reported(generator, fake_tree):
"""The whole point: a new variable with no notes entry must fail loudly."""
problems = generator.check_notes(generator.collect(fake_tree))
assert problems
offender = "ODYSSEUS_VIA_HELPER"
assert any(offender in problem for problem in problems)
assert any("VARIABLE_NOTES" in problem for problem in problems)
assert any("src/indirect.py" in problem for problem in problems)
def test_a_stale_notes_entry_is_reported(generator):
problems = generator.check_notes({})
assert len(problems) == len(generator.VARIABLE_NOTES)
assert all("no longer read anywhere" in problem for problem in problems)
def test_renders_one_table_row_per_variable(generator, fake_tree, monkeypatch):
monkeypatch.setitem(
generator.VARIABLE_NOTES,
"ODYSSEUS_VIA_HELPER",
("Search", generator.USER, "A synthetic limit."),
)
found = {"ODYSSEUS_VIA_HELPER": generator.collect(fake_tree)["ODYSSEUS_VIA_HELPER"]}
page = generator.render(found, generator.naive_line_scan(fake_tree))
assert page.startswith("---\nlayout: default\n---\n")
assert "| `ODYSSEUS_VIA_HELPER` | `5 * 1024` | `src/indirect.py:16` | A synthetic limit. |" in page
assert "### Search" in page
def test_every_variable_read_in_the_repository_is_documented(built):
_, variables, problems = built
assert not problems, "\n".join(problems)
assert variables, "expected the generator to find ODYSSEUS_* reads"
def test_committed_page_matches_the_source(built):
page, _, _ = built
assert PAGE.read_text(encoding="utf-8") == page, (
"website/configuration-reference.md is stale - regenerate it with "
"`python3 scripts/generate_env_reference.py`"
)
def test_page_has_no_emoji_or_other_non_ascii(built):
page, _, _ = built
offenders = sorted({character for character in page if ord(character) > 126})
assert not offenders, f"non-ASCII in the generated page: {offenders}"
def test_check_mode_reports_a_stale_page(generator, tmp_path, monkeypatch):
stale = tmp_path / "configuration-reference.md"
stale.write_text("out of date\n", encoding="utf-8")
monkeypatch.setattr(generator, "OUTPUT_PATH", stale)
assert generator.main(["--check"]) == 1
assert generator.main([]) == 0
assert generator.main(["--check"]) == 0
def test_script_runs_as_a_subprocess_without_importing_the_app():
result = subprocess.run(
[sys.executable, "scripts/generate_env_reference.py", "--check"],
cwd=REPO, capture_output=True, text=True, timeout=180,
)
assert result.returncode == 0, result.stderr
assert re.search(r"\d+ variables", result.stdout), result.stdout
def test_page_is_linked_from_the_places_a_reader_starts():
assert "configuration-reference.md" in (REPO / "website" / "setup.md").read_text(
encoding="utf-8"
)
assert "configuration-reference.md" in (REPO / ".env.example").read_text(
encoding="utf-8"
)
+267
View File
@@ -0,0 +1,267 @@
---
layout: default
---
# Configuration reference: ODYSSEUS_* environment variables
<!-- This page is generated from the source tree by `scripts/generate_env_reference.py`. Do not edit it by hand: run the script instead. `tests/test_env_reference.py` fails when the committed page and the source disagree, or when a variable is read without an entry in the script's notes table. -->
Odysseus reads its runtime configuration from the Settings UI. The
environment variables below are the deployment-level escape hatches underneath
that: they are read directly from the process environment, mostly at import or
startup, and most installs never need any of them.
`.env.example` stays a short, deployment-level example on purpose - `APP_BIND`,
`APP_PORT`, `AUTH_ENABLED`, `DATABASE_URL` and a pre-seeded admin password. This
page is the complete list, which is a different job.
Truthiness is not uniform across the codebase. Where a variable is described as
"truthy" the read accepts `1`, `true`, `yes` and usually `on`; where it is
described as a switch that turns something off, the read rejects `0`, `false`,
`no` and `off` and treats everything else as on. The `Default` column is the
value the code falls back to when the variable is unset, quoted from the source.
The source tree reads **98** `ODYSSEUS_*` variables: 78 an operator may want to set, and 20 that are internal - sentinels, fixture switches, capture hooks and development tooling. The internal ones are listed too, in their own section, so this page can be checked against the source mechanically.
> This page is generated. Edit `scripts/generate_env_reference.py` and
> re-run it; `tests/test_env_reference.py` enforces that the committed page
> matches the source.
## Variables you can set
### Deployment and first run
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_ADMIN_PASSWORD` | `''` | `setup.py:102` (+4 more) | Password for the admin account created on first run. Setup refuses a value shorter than its minimum length rather than silently falling back. |
| `ODYSSEUS_ADMIN_USER` | `''` | `setup.py:101` (+2 more) | Username for the admin account created on first run. Setup uses env vars first, then an interactive prompt, then a random password. |
| `ODYSSEUS_ALLOW_OLLAMA_CLI_SCAN` | *unset* | `routes/cookbook_helpers.py:544` (+1 more) | On Windows only, set truthy to let the Cookbook dependency probe shell out to `ollama list`. Ignored on other platforms, where the scan always runs. |
| `ODYSSEUS_CONTAINER_NETWORK_MODE` | `''` | `app.py:1022` (+1 more) | Declares the container's Docker network mode. Set to `host` to skip host-gateway probing when discovering local model endpoints. |
| `ODYSSEUS_ENABLE_HOST_DOCKER` | `''` | `src/host_docker_access.py:41` | Security-relevant. Must be exactly `true` before tools may use a mounted host Docker socket, and the socket itself must exist. |
| `ODYSSEUS_INPROCESS_POLLERS` | `'1'` | `routes/email/email_pollers.py:1722` | The same off switch for the in-process email pollers, when `odysseus-mail poll-scheduled` is the sole external driver. |
| `ODYSSEUS_INPROCESS_TASKS` | `'1'` | `app.py:1311` | Set to 0, false, no or off to stop the in-process scheduled-task runner, for deployments where an external worker drives task firing. |
| `ODYSSEUS_MODEL_KEEPALIVE` | `''` | `app.py:1218` | Opt-in periodic model keep-alive pings. Off by default: the ping path runs model discovery, so stale LAN endpoints add background pressure. |
| `ODYSSEUS_REQUIRE_TOOL_INDEX_READY` | `''` | `src/readiness.py:61` | Set truthy to make semantic tool-index readiness gate startup. Off by default so an install stays available on deterministic tool selection. |
| `ODYSSEUS_SKIP_ADMIN_PROMPT` | *unset* | `setup.py:112` | Any non-empty value suppresses the interactive admin-credential prompt even on a TTY, for unattended installs. |
| `ODYSSEUS_SLOW_REQUEST_LOG_SECONDS` | `'0.75'` | `app.py:239` | Request duration in seconds above which the middleware logs a slow-request warning. |
| `ODYSSEUS_STARTUP_WARMUPS` | `''` | `app.py:1192` | Opt-in startup pings of the configured model endpoints. Off by default because they compete with the first seconds of UI use. |
| `ODYSSEUS_TOOL_INDEX_PREWARM` | `'1'` | `src/tool_index.py:771` | Set to 0, false, no or off to skip background initialization of semantic tool retrieval at startup. |
### Data directories and paths
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_DATA_DIR` | `get_default_data_dir()` | `src/constants.py:56` (+1 more) | Root directory for every persisted file. Prefer this over the per-path overrides; the rest of `src/constants.py` derives from it. |
| `ODYSSEUS_MAIL_ATTACHMENTS_DIR` | `os.path.join(DATA_DIR, 'mail-attachments')` | `src/constants.py:102` | Dedicated override for the mail attachment store, which otherwise lives under the data directory. |
### Model routing and providers
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_COPILOT_API_VERSION` | `'2026-06-01'` | `src/copilot.py:39` | Dated API-version header the Copilot models and chat endpoints require. |
| `ODYSSEUS_COPILOT_CLIENT_ID` | `'01ab8ac9400c4e429b23'` | `src/copilot.py:34` | GitHub OAuth client id for the Copilot device flow. The default is the public VS Code client id; override it only with your own allow-listed app. |
| `ODYSSEUS_DEEPSEEK_REASONING_EFFORT` | `'high'` | `src/llm_core.py:1727` | Reasoning effort for DeepSeek. Only `high` and `max` are accepted; any other value falls back to the default. |
| `ODYSSEUS_FIRST_TOKEN_TIMEOUT` | `''` | `src/llm_core.py:223` | Seconds to wait for the first streamed token from a local endpoint before failing. Unset keeps the generous read timeout, which makes a stalled backend look like a hung agent. |
| `ODYSSEUS_LOCAL_MODEL_GATE` | `'true'` | `src/llm_core.py:95` | On by default. Set 0, false, no or off to drop the gate that checks a local endpoint before routing a request to it. |
| `ODYSSEUS_MISTRAL_REASONING_EFFORT` | `'high'` | `src/llm_core.py:1723` | Reasoning effort sent to Mistral thinking-capable models. The API accepts high, medium, low and none. |
| `ODYSSEUS_MLX_IMAGE_VLM_MODEL` | *unset* | `scripts/mlx_image_server.py:299` | Vision-language model id for the MLX image server script. Required unless `--vlm-model` is passed on the command line. |
| `ODYSSEUS_QWEN_ROUTE_THINKING` | `'auto'` | `src/agent_loop.py:166` | Thinking policy for the Qwen routing step. An unrecognized value falls back to `auto`. |
### Agent loop and tool execution
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_DISABLE_MCP` | `''` | `src/builtin_mcp.py:89` | Truthy disables MCP entirely, as an escape hatch for compatibility problems with a server. |
| `ODYSSEUS_MAX_VISUAL_EVIDENCE_FRAMES` | `'3'` | `src/agent_loop.py:15360` | How many video frames one tool result may contribute. Clamped to 1-8. |
| `ODYSSEUS_MAX_VISUAL_EVIDENCE_IMAGES` | `'1'` | `src/agent_loop.py:15328` | How many images one tool result may contribute to the model turn. Clamped to 1-8. |
| `ODYSSEUS_MCP_ALLOWED_COMMANDS` | `''` | `src/agent_tools/admin_tools.py:140` | Security-relevant. Comma-separated allowlist of MCP launcher basenames the agent may start. Empty by default, and the deny list still wins. |
| `ODYSSEUS_PYTHON_TOOL_SITE_PACKAGES` | `''` | `src/agent_tools/subprocess_tools.py:925` | Security-relevant. Absolute package roots, separated by the platform path separator, exposed to the sandboxed Python tool. Empty exposes none. |
| `ODYSSEUS_SCRIPT_HOST` | `'localhost'` | `src/builtin_actions.py:919` | Default host for the run-script action. `localhost`, `127.0.0.1`, `local` and empty run locally; any other value runs over SSH. |
| `ODYSSEUS_TOOL_APPROVAL_GATE` | `'0'` | `src/tool_capabilities.py:645` | Security-relevant. Truthy makes tool calls pass through the approval gate. Off by default. |
### Browser automation
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_BROWSER_EXECUTABLE` | `''` | `src/builtin_mcp.py:114` | Absolute path to the Chrome or Chromium binary. Empty searches the usual names, then lets Playwright MCP pick its own browser. |
| `ODYSSEUS_BROWSER_ISOLATED` | `'1'` | `src/builtin_mcp.py:139` | Security-relevant. On by default, adding `--isolated` so each browser session starts clean. Set 0, false or no to keep a persistent profile. |
| `ODYSSEUS_BROWSER_MCP_CACHE` | `os.path.join(base_dir, 'data', 'local', 'playwright-mcp-cache')` | `src/builtin_mcp.py:229` | Cache directory handed to the browser MCP server, so its npm download survives a container rebuild. |
| `ODYSSEUS_BROWSER_MCP_REQUIRE_CACHE` | `''` | `src/builtin_mcp.py:90` | Truthy refuses to start the browser MCP server unless its npm package is already in the npx cache, instead of installing it at startup. |
| `ODYSSEUS_BROWSER_NAMESPACE` | `'odysseus-ui'` | `src/agent_tools/web_tools.py:2355` (+5 more) | Namespace for the detached agent-browser daemon's pid files, so two runtimes on one machine do not terminate each other's browsers. |
| `ODYSSEUS_BROWSER_NO_SANDBOX` | `'1'` | `src/builtin_mcp.py:142` | Security-relevant. On by default, adding `--no-sandbox` because the Docker image cannot use the Chromium sandbox. Set 0, false or no to keep it. |
| `ODYSSEUS_BROWSER_SCREENSHOT_DIR` | *unset* | `src/agent_tools/web_tools.py:3010` | Where private-browser screenshots are written. Falls back to the container path, then the system temp directory. |
### Container and workspace mounts
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_WORKSPACE_CONTAINER_ROOT` | *unset* | `src/workspace_paths.py:31` | Container-side root that the host root maps onto. An `or` fallback, not a read default, supplies `/workspace` when it is unset. |
| `ODYSSEUS_WORKSPACE_DEFAULT` | `''` | `routes/workspace_routes.py:97` | Default workspace path the admin-only workspace route reports. Empty means no default is configured. |
| `ODYSSEUS_WORKSPACE_HOST_ROOT` | *unset* | `src/workspace_paths.py:29` | Single host-side root, paired with the container root below. Simpler than the explicit mount list when there is only one mount. |
| `ODYSSEUS_WORKSPACE_MOUNTS` | `''` | `src/workspace_paths.py:19` | `host=container` path pairs separated by commas or semicolons, so the agent can translate a container path back to the host path a user typed. |
### Email
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_DOCUMENT_OWNER` | `''` | `mcp_servers/email_server.py:208` | Owner stamped on documents the email MCP server creates. Stdio MCP tools get no authenticated user, so without this a draft is invisible. |
| `ODYSSEUS_IMAP_TIMEOUT_SECONDS` | *unset* | `routes/email/email_helpers.py:1163` | IMAP socket timeout in seconds, clamped to 5-300. A non-numeric value falls back to 30 rather than failing. |
### Calendar, notes and single-user mode
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_ALLOW_PRIVATE_CALDAV` | `'0'` | `src/caldav_sync.py:52` | Security-relevant. Truthy lets CalDAV sync reach private and link-local addresses. Off by default; this is an SSRF guard. |
| `ODYSSEUS_FALLBACK_OWNER` | `'owner@localhost'` | `routes/calendar_routes.py:65` | Owner address that single-user mode attributes an unauthenticated request to. Only reachable while single-user mode is on. |
| `ODYSSEUS_SINGLE_USER` | `'1'` | `routes/calendar_routes.py:66` | Security-relevant. On by default. Set to 0 on a real multi-user install so unauthenticated calendar writes are rejected rather than absorbed. |
### Upload and media limits
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_CHAT_UPLOAD_MAX_BYTES` | `10 * 1024 * 1024` | `src/upload_limits.py:33` | Maximum bytes accepted for a chat attachment. |
| `ODYSSEUS_EDITOR_DRAFT_MAX_BYTES` | `256 * 1024 * 1024` | `src/upload_limits.py:47` | Maximum bytes accepted for a saved editor draft. |
| `ODYSSEUS_EMAIL_COMPOSE_UPLOAD_MAX_BYTES` | `25 * 1024 * 1024` | `src/upload_limits.py:56` | Maximum bytes accepted for an attachment added while composing mail. |
| `ODYSSEUS_GALLERY_TRANSFORM_UPLOAD_MAX_BYTES` | `25 * 1024 * 1024` | `src/upload_limits.py:44` (+1 more) | Maximum bytes accepted for an image handed to a gallery transform. |
| `ODYSSEUS_GALLERY_UPLOAD_MAX_BYTES` | `100 * 1024 * 1024` | `src/upload_limits.py:41` (+1 more) | Maximum bytes accepted for a gallery upload. |
| `ODYSSEUS_ICS_MAX_BYTES` | `10 * 1024 * 1024` | `src/upload_limits.py:62` | Maximum bytes accepted for an imported ICS file. |
| `ODYSSEUS_MEDIA_FRAME_TIMEOUT` | `30` | `src/media_ingress.py:146` | Seconds allowed for extracting frames from a video before giving up. |
| `ODYSSEUS_MEDIA_MAX_AUDIO_BYTES` | `32 * 1024 * 1024` | `src/media_ingress.py:129` | Largest source audio file the media pipeline will read. |
| `ODYSSEUS_MEDIA_MAX_DIMENSION` | `1600` | `src/media_ingress.py:138` | Longest edge in pixels an image is resized down to before encoding. |
| `ODYSSEUS_MEDIA_MAX_DOCUMENT_BYTES` | `32 * 1024 * 1024` | `src/media_ingress.py:126` | Largest source document the media pipeline will read. |
| `ODYSSEUS_MEDIA_MAX_DOCUMENT_CHARS` | `24000` | `src/media_ingress.py:135` | How many characters of an ingested document are inlined into the turn. |
| `ODYSSEUS_MEDIA_MAX_ENCODED_BYTES` | `24 * 1024 * 1024` | `src/media_ingress.py:132` | Budget for the encoded payload handed to the model, counted cumulatively across one turn's attachments rather than per file. |
| `ODYSSEUS_MEDIA_MAX_FILES` | `4` | `src/media_ingress.py:119` | How many local media files one agent turn may ingest. |
| `ODYSSEUS_MEDIA_MAX_IMAGE_BYTES` | `12 * 1024 * 1024` | `src/media_ingress.py:120` | Largest source image the media pipeline will read. |
| `ODYSSEUS_MEDIA_MAX_PIXELS` | `40000000` | `src/media_ingress.py:139` | Total pixel budget for a source image, as a decompression-bomb guard. |
| `ODYSSEUS_MEDIA_MAX_VIDEO_BYTES` | `128 * 1024 * 1024` | `src/media_ingress.py:123` | Largest source video the media pipeline will read. |
| `ODYSSEUS_MEDIA_MAX_VIDEO_FRAMES` | `8` | `src/media_ingress.py:140` | How many frames are sampled from a video. |
| `ODYSSEUS_MEDIA_PROBE_TIMEOUT` | `15` | `src/media_ingress.py:143` | Seconds allowed for probing a video's metadata before giving up. |
| `ODYSSEUS_MEMORY_IMPORT_MAX_BYTES` | `10 * 1024 * 1024` | `src/upload_limits.py:50` (+1 more) | Maximum bytes accepted for a memory import file. |
| `ODYSSEUS_PERSONAL_UPLOAD_MAX_BYTES` | `25 * 1024 * 1024` | `src/upload_limits.py:53` (+1 more) | Maximum bytes accepted for a personal-documents upload. |
| `ODYSSEUS_STT_MAX_AUDIO_BYTES` | `25 * 1024 * 1024` | `src/upload_limits.py:59` | Maximum bytes accepted for an audio file submitted for transcription. |
### Search
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_SEARCH_PROVIDER` | `''` | `services/search/providers.py:43` | Forces the search provider, overriding the Settings value. Empty keeps the UI authoritative, which is what a normal install wants. |
### Memory and skills
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_SKILL_SEMANTIC_RETRIEVAL` | `'1'` | `services/memory/skills.py:789` | On by default. Set 0, false, no or off to fall back to keyword-only skill retrieval when no vector store is reachable. |
| `ODYSSEUS_SKILL_SEMANTIC_THRESHOLD` | `'0.4'` | `services/memory/skills.py:800` | Minimum semantic score a skill needs to be retrieved. A non-numeric value falls back to the default. |
### Speech and vision models
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_GROUNDING_MODEL` | `'google/owlvit-base-patch32'` | `routes/gallery/gallery_routes.py:95` | Object-grounding model id the gallery loads for text-driven selection. |
| `ODYSSEUS_SAM_MODEL` | `'facebook/sam-vit-base'` | `routes/gallery/gallery_routes.py:59` | Segmentation model id the gallery loads for subject selection. |
| `ODYSSEUS_STT_MODEL` | *unset* | `src/agent_tools/media_tools.py:2184` | Default speech-to-text model for media transcription when the tool call does not name one. |
| `ODYSSEUS_TTS_CACHE_MAX_BYTES` | `500 * 1024 * 1024` | `services/tts/tts_service.py:47` | Cap on the synthesized-speech cache. A non-numeric value falls back to the default. |
### Auth and internal API
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_INTERNAL_BASE` | *unset* | `src/constants.py:178` | Base URL the in-app tool layer uses for loopback HTTP calls. Set it when the app is not reachable at the port it thinks it is bound to. |
| `ODYSSEUS_INTERNAL_TOKEN` | *unset* | `core/middleware.py:20` | Security-relevant. Token that lets the in-app tool layer reach admin-gated routes over loopback. Unset generates a fresh per-process token, which is what you want unless something outside the process needs the same value. |
### Integrations (Claude, Codex)
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_API_TOKEN` | `''` | `integrations/claude/skills/odysseus/scripts/odysseus_api.py:40` (+1 more) | API token those scripts authenticate with. Both this and the URL are required; the scripts name whichever is missing. |
| `ODYSSEUS_URL` | `''` | `integrations/claude/skills/odysseus/scripts/odysseus_api.py:39` (+1 more) | Base URL of the Odysseus instance the bundled integration scripts call. |
## Internal and development-only variables
Listed for completeness. Setting one of these on a real install is either a no-op or a way to break something quietly.
### Model routing and providers
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_COPILOT_EDITOR_VERSION` | `'Odysseus/1.0'` | `src/copilot.py:54` | Editor-version header presented to the Copilot API. Kept stable on purpose. |
| `ODYSSEUS_COPILOT_INTEGRATION_ID` | `'vscode-chat'` | `src/copilot.py:51` | Integration id presented to the Copilot API. Kept stable on purpose. |
| `ODYSSEUS_COPILOT_USER_AGENT` | `'Odysseus/1.0'` | `src/copilot.py:48` | Editor-like User-Agent presented to the Copilot API. Kept stable on purpose. |
| `ODYSSEUS_DEBUG_LLM_SHAPE` | `''` | `src/llm_core.py:3552` (+1 more) | Truthy logs the shape of streamed provider chunks. Debugging aid for provider response parsing. |
### Agent loop and tool execution
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_CAPTURE_MODEL_REQUESTS` | `''` | `src/agent_loop.py:3921` | Truthy writes model-request snapshots for local debugging. The marker file `/tmp/odysseus_capture_model_requests` enables the same thing. |
| `ODYSSEUS_EXPOSE_RAW_BROWSER_MCP` | `''` | `src/agent_loop.py:4126` | Truthy stops hiding the raw Playwright MCP tools from agent prompts when the private-browser tool is available. |
| `ODYSSEUS_TOOL_CONTRACT_ROOT` | `'<repo>/scripts'` | `src/clean_agent_preview.py:1952` (+1 more) | Directory holding the tool-contract scripts the clean-agent preview loads. The default is the repository's bundled scripts directory; set the variable to override it. |
### Email
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_EMAIL_FIXTURE` | *unset* | `mcp_servers/email_server.py:1122` (+7 more) | Exactly `1`, plus a fixture file on disk, makes the email MCP server serve fixtures instead of a real mailbox. |
### Testing, capture and development tooling
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_QA_TEACHER_ATTEMPTS` | `'3'` | `scripts/odysseus_conversation_qa.py:370` | Retry budget for the conversation-QA teacher model call. Clamped to 1-3. |
| `ODYSSEUS_QA_TEACHER_TIMEOUT` | `'120'` | `scripts/odysseus_conversation_qa.py:372` | Timeout in seconds for that call. Clamped to 15-120. |
| `ODYSSEUS_RUNTIME_REVISION` | `''` | `routes/chat_helpers.py:198` (+1 more) | Revision string stamped into each captured SFT trace record, so a trace can be tied back to the build that produced it. |
| `ODYSSEUS_SFT_DISABLE_WORKSPACE_TOOLS` | `'1'` | `src/agent_loop.py:7404` | On by default. Keeps synthetic personal-assistant fixtures out of workspace mode; set 0, false, no or off to let them through. |
| `ODYSSEUS_SFT_FORCE_UTC_TIMEZONE` | `'0'` | `routes/chat_routes.py:2070` | Truthy forces `sft_` accounts to UTC for deterministic batch generation. Interactive accounts still follow the browser timezone. |
| `ODYSSEUS_SFT_TRACE_CAPTURE` | `'1'` | `routes/chat_helpers.py:161` (+1 more) | On by default, but only for owners whose name starts with `sft_`. Set 0, false, no or off to stop writing training traces. |
| `ODYSSEUS_SFT_TRACE_DIR` | *unset* | `routes/chat_helpers.py:195` (+2 more) | Directory the SFT trace JSONL files are written to. Defaults to `sft_traces` under the data directory. |
| `ODYSSEUS_SKIP_RUN_HINT` | *unset* | `setup.py:284` | Any non-empty value suppresses the `start the server with` hint at the end of setup. `start-macos.sh` sets it because it starts the server itself. |
| `ODYSSEUS_TEST_STATIC_ORIGIN` | *unset* | `scripts/css_snapshot.py:249` (+6 more) | Origin an already-running static server is serving the repository from, so snapshot tooling reuses it instead of starting its own. |
| `ODYSSEUS_TEST_STATIC_PORT` | *unset* | `tests/conftest.py:137` | Fixed port for the test suite's static server. Unset takes an ephemeral port, which is what keeps parallel runs from colliding. |
### Build and release metadata
| Variable | Default | Read in | What it does |
|---|---|---|---|
| `ODYSSEUS_BUILD_VERSION` | `''` | `src/constants.py:15` | Overrides the build-version string the API and UI report, without touching the public application version. |
| `ODYSSEUS_SOURCE_COMMIT` | `''` | `src/constants.py:33` | Overrides the source commit reported for runtime provenance, for builds that ship without a git directory. |
## How this page is generated
The generator walks the Python sources under `app.py`, `launcher.py`, `setup.py`, `companion`, `config`, `core`, `integrations`, `mcp_servers`, `routes`, `scripts`, `services`, `src`, `tests` and finds
reads three ways, because no single pattern covers the codebase:
- Direct reads: `os.getenv(...)`, and any `.get` / `.setdefault` / `.pop` call or
subscript keyed by an `ODYSSEUS_*` literal, including names held in a
module-level constant. The receiver is not required to be `os.environ`, because
several call sites read through a mapping passed in as an argument
(`src/tool_index.py`, `src/host_docker_access.py`).
- Calls to env-reader helpers - any function that forwards one of its own
parameters to an environment read. This is detected rather than hardcoded, so a
new helper needs no change here. It is what finds the upload caps in
`src/upload_limits.py` and the media-ingress overrides in
`src/media_ingress.py`.
- A regex sweep of the raw file text, for reads the AST cannot see.
`routes/cookbook_helpers.py` builds an Ollama probe script as a list of source
lines, so one read lives inside a string literal.
The three passes are not redundancy. A line-based grep for a direct
`os.environ.get("ODYSSEUS_...` call finds 70 of the 98 variables on this
page. What it misses is reads through an env-reader helper, reads whose call
spans more than one line, reads whose variable name is held in a module
constant, and reads through a mapping passed in as an argument - which is the
whole reason this page is generated rather than maintained.
The `Default` column shows the expression as written, with one level of
indirection resolved: a module-level constant and a dataclass field default are
replaced by the literal they hold, so `defaults.max_media_files` shows as `4`.
Anything computed at import time - `get_default_data_dir()` - is shown as
written, because that is the honest answer. A few call sites supply their
fallback with `or` rather than a default argument; those show as *unset* and say
so in the last column.
Regenerate it with:
```bash
python3 scripts/generate_env_reference.py
```
+6
View File
@@ -718,6 +718,12 @@ Key settings:
All upload-limit vars are validated (must be a positive integer) and optional; an invalid value fails fast at startup.
The table above is the short list. The source tree reads a lot more `ODYSSEUS_*`
variables than this - browser automation, model routing, workspace mounts, media
limits, a few security switches - and the complete list, generated from the code
with the default each one falls back to, is in the
[configuration reference](configuration-reference.md).
### Built-in MCP servers (optional setup)
Odysseus auto-registers a few built-in MCP servers at startup. The npx-based ones (currently the browser server, `@playwright/mcp`) only start when their npm package is already in the local npx cache. If a package isn't cached, that server is skipped with a startup log message explaining what to do, so a fresh install does not block on a multi-minute npm download or hang if Playwright system deps are missing.