Skip to content
This repository was archived by the owner on Jul 4, 2026. It is now read-only.

feat(web): HERMES_SESSION_TOKEN env override for reverse-proxied deployments - #3

Merged
kingsleydon merged 1 commit into
mainfrom
feat/env-session-token
Apr 15, 2026
Merged

feat(web): HERMES_SESSION_TOKEN env override for reverse-proxied deployments#3
kingsleydon merged 1 commit into
mainfrom
feat/env-session-token

Conversation

@kingsleydon

Copy link
Copy Markdown

Summary

Lets operators pin the web-server's session token to a stable value via
the HERMES_SESSION_TOKEN env var, so reverse-proxied deployments where
the UI lives on a different origin can authenticate against /api/* without
scraping the HTML injection.

Why

_SESSION_TOKEN is currently secrets.token_urlsafe(32) — random at process
start, dies with the process, only surfaced via the window.__HERMES_SESSION_TOKEN__
script tag baked into the SPA HTML.

This is elegant for the single-user hermes web flow: one process serves the
SPA and the API, same origin, so the browser naturally picks up the token from
HTML on first load and uses it for all /api/* calls.

It breaks for reverse-proxied deployments (Clawdi is our motivating case —
one dashboard at app.clawdi.ai talking to many per-pod Hermes instances at
{app_id}-18793.{gateway}.phala.network). The dashboard is a separate Next.js
app on a different origin — it never loads the Hermes SPA HTML, so
window.__HERMES_SESSION_TOKEN__ is never set on its side, and it has no way
to learn the ephemeral token the Python process generated.

Teknium's auth_middleware (added 2026-04-14) correctly gates /api/*
behind this token, which is great for security, but completes the mismatch:
the dashboard can prove it's an authenticated Clawdi user (via its own JWT
flow), but it cannot authenticate to hermes-web.

Design

One-line change with a fallback:

_SESSION_TOKEN = os.environ.get("HERMES_SESSION_TOKEN") or secrets.token_urlsafe(32)
  • Single-user hermes web: env var unset → fall back to random token →
    zero behaviour change. Comment block explains both flows so future readers
    know why the fallback exists.
  • Reverse-proxied deployments: operator sets HERMES_SESSION_TOKEN to a
    stable value (on Clawdi we derive it alongside API_SERVER_KEY from the
    same per-pod MASTER_KEY via HKDF, so hermes-agent and hermes-web share
    one token without needing to coordinate).

Docstring updated to explain both code paths and when each applies.

Test plan

  • Unset env var → hermes web single-user flow unaffected (token still random)
  • HERMES_SESSION_TOKEN=foo hermes web_SESSION_TOKEN == "foo", SPA HTML embeds "foo", curl -H 'Authorization: Bearer foo' /api/env → 200
  • Empty env var (HERMES_SESSION_TOKEN=) → falls back to random (truthy-or)
  • Existing hmac.compare_digest timing-safe comparison path unchanged

…d deployments

The in-memory random _SESSION_TOKEN works for the single-user `hermes web`
flow because the SPA is served from the same process and reads the token
from the `window.__HERMES_SESSION_TOKEN__` HTML injection — token lives
and dies with the Python process, no external coordination needed.

For deployments where the UI lives on a different origin (e.g. a platform
dashboard talking to many per-pod Hermes instances over the network), the
downstream caller can't read that HTML injection and has no way to learn
the ephemeral token.

This patch lets operators set `HERMES_SESSION_TOKEN` in the environment
to pin the token to a stable, externally-known value. When the env var
is unset, the existing random fallback is preserved, so stand-alone CLI
behavior is unchanged.
@kingsleydon
kingsleydon merged commit 8620ab3 into main Apr 15, 2026
6 of 7 checks passed
@kingsleydon
kingsleydon deleted the feat/env-session-token branch April 15, 2026 11:29
h4x3rotab pushed a commit that referenced this pull request Apr 20, 2026
…lls/

- Rename skill to touchdesigner-mcp (matches blender-mcp convention)
- Move from skills/creative/ to optional-skills/creative/
- Fix duplicate pitfall numbering (#3 appeared twice)
- Update SKILL.md cross-references for renumbered pitfalls
- Update setup.sh path for new directory location
kingsleydon pushed a commit that referenced this pull request May 9, 2026
## Summary
- Forwards chat-completions `timeout` into the Codex Responses stream call.
- Adds total elapsed-time enforcement while the Responses stream is still yielding events.
- Closes the underlying client on timeout to unblock stalled streams, then raises `TimeoutError`.
- Adds focused tests for timeout forwarding and total timeout enforcement.

## Why
The Codex auxiliary adapter can be used by non-interactive auxiliary work such as context compression. If the stream keeps yielding progress-like events but never completes, SDK socket/read timeouts do not necessarily protect the full operation. This makes the CLI look stuck until the user force-interrupts the whole session.

This is a refreshed upstream-ready version of the earlier fork fix around `d3f08e9a0` / PR #3.

## Verification
- `python -m py_compile agent/auxiliary_client.py tests/agent/test_auxiliary_client.py`
- `python -m pytest -o addopts='' tests/agent/test_auxiliary_client.py::TestCodexAuxiliaryAdapterTimeout -q`
- `git diff --check`
kingsleydon pushed a commit that referenced this pull request May 27, 2026
…y prefixed

Companion to the NousResearchGH-25255 incoming-strip fix from @hayka-pacha. Without
this, build_anthropic_kwargs unconditionally added 'mcp_' to every tool
name in step 3, so a native MCP server tool registered as
'mcp_composio_X' was sent as 'mcp_mcp_composio_X' on the wire. The
incoming strip only removes ONE prefix, which still worked on first
call, but on subsequent calls the model pattern-matched the
single-prefixed form from message history and produced names that
stripped to 'composio_X' — registry miss, dispatch fail.

The history-rewrite block (#4) already has this guard. Apply the same
guard to the schema-rewrite block (#3) so round-trip is symmetric.

Added 4 outgoing-side tests. Existing 7 incoming-side tests still pass.

Author map: hayka-pacha added for PR NousResearch#25270 salvage attribution.

Refs NousResearchGH-25255.
kingsleydon pushed a commit that referenced this pull request May 29, 2026
… OAuth gates

Two parallel public-path allowlists drifted: _PUBLIC_API_PATHS in
hermes_cli/web_server.py (legacy _SESSION_TOKEN middleware) and
_GATE_PUBLIC_PREFIXES in hermes_cli/dashboard_auth/middleware.py
(OAuth gate). The legacy list included /api/status (documented as a
non-sensitive read-only liveness target); the OAuth gate's list did not.

Effect: every wildcard-subdomain agent surfaced as STARTING/down to the
portal even though the dashboard was serving correctly. Nous account
service (src/server/agents/fly-provider.ts
getInstanceRuntimeStatus) fetches ``/api/status`` without a cookie
as its sole liveness probe; the OAuth gate's 401 looked identical to
'agent dead' on the portal side.

Fix: lift the allowlist into hermes_cli/dashboard_auth/public_paths.py
and have both middlewares import it. _path_is_public now consults
the shared frozenset first, then falls back to the gate's
auth-bootstrap/static prefix list. Future additions to the public list
hit both gates automatically.

Endpoint inventory (verified safe to remain public):

* /api/status            — version, gateway state, active session count,
                           auth-gate shape. Portal liveness probe target.
* /api/config/defaults   — config-defaults feed for the SPA's Config page
* /api/config/schema     — config schema for the SPA's Config page
* /api/model/info        — model catalogue metadata (context windows)
* /api/dashboard/themes  — theme manifests for the skin engine
* /api/dashboard/plugins — plugin manifests for the dashboard

No user data, no session content, no secrets. Same shape an external
monitoring agent would hit on /healthz.

Tests:

* New: test_gated_status_is_public (regression guard with the NAS
  fly-provider.ts liveness-probe rationale spelled out in the docstring)
* New: test_other_public_api_paths_are_public_under_gate (parametrised
  over the rest of PUBLIC_API_PATHS — proves 401 / 302-to-login is
  never the response)
* New: docker integration check #3 in
  test_dashboard_oauth_gate_engaged_by_default — /api/status
  remains 200 under the gate AND reports auth_required=True so the
  portal can distinguish modes
* Updated: test_full_login_round_trip_unlocks_gated_api now probes
  /api/sessions instead of /api/status (status is public, so it
  can no longer distinguish 'logged in' from 'gate accidentally
  disabled')
* Updated: TestApi401Envelope (the no-cookie / invalid-cookie /
  dead-cookie tests) probes /api/sessions for the same reason
* Updated: docker integration check #2 in
  test_dashboard_oauth_gate_engaged_by_default probes
  /api/sessions to prove the gate is intercepting
* Removed: dead _login() helper in
  test_dashboard_auth_status_endpoint.py (no longer needed since
  /api/status is reachable cold)

Companion to docs/handover/hermes-agent-dashboard-s6-insecure-fix.md
(the --insecure flag fix that shipped earlier).
kingsleydon pushed a commit that referenced this pull request May 29, 2026
…hain probe (NousResearch#34340)

* fix(codex): surface error code in Responses 'failed' status errors

When a Codex Responses turn ends with status=failed, the response carries
the failure details under `response.error` as
`{code, message, param, ...}`. The previous extractor pulled only
`message`, so users seeing a rate-limit failure got a bare "Slow down"
string indistinguishable from a generic stream truncation; an
internal_error with empty message degraded to a dict dump
("{'code': 'internal_error', 'message': ''}").

Extract a `_format_responses_error()` helper that:
- prefixes `code` when both code and message are present
  (e.g. 'rate_limit_exceeded: Slow down')
- falls back to the bare `code` when message is empty
- accepts both dict and attribute-style payloads (SDK and JSON-RPC paths)
- preserves the prior status-only fallback when no error payload exists

Apply the same helper at the sibling site in
`codex_app_server_session.run_turn()` so codex-CLI subprocess turn
failures get the same treatment.

Tests:
- 8 new unit tests for `_format_responses_error` covering both shapes,
  empty/missing fields, non-string fields, and the status-only fallback.
- 2 regression tests on `_normalize_codex_response` for failed status
  with and without a code, asserting the exact RuntimeError message.
- All 3603 tests in tests/agent/ pass.

Adapted from anomalyco/opencode#28757.

* feat(prompt): universal task-completion guidance + local Python toolchain probe

Two cross-model failure modes get a single-line answer in the cached
system prompt. Both gated by config (default on), both add zero overhead
when not needed, both verified via real AIAgent prompt builds.

## What changed

`TASK_COMPLETION_GUIDANCE` — short prompt block applied to ALL models.
Targets two failure modes observed on a real Sarasota real-estate build
task: (1) Opus stopped after writing an 85-byte stub and gave a prose
response with finish_reason=stop on call #3 of 90; (2) DeepSeek pushed
through a PEP-668 wall, then returned fabricated listings instead of
admitting the blocker. Both behaviors are model-family-agnostic, so the
guidance lives outside the existing tool_use_enforcement gate (~192
tokens, paid once per session via prefix cache).

`tools/env_probe.py` — local Python toolchain probe. Detects
python3/pip/uv/PEP-668 state and emits ONE short line in the system
prompt when something is non-default. Emits NOTHING when the env is
clean (zero token cost for normal users). Skipped entirely for remote
terminal backends (docker/modal/ssh) — they have their own probe.

Example output on a broken environment (the actual case):

    Python toolchain: python3=3.11.15 (no pip module),
    python=missing (use python3), pip→python3.12 (mismatch),
    PEP 668=yes (use venv or uv).

## Config

Both flags live under `agent.` in config.yaml, default True:

    agent:
      task_completion_guidance: true   # universal "finish the job" block
      environment_probe: true          # local Python toolchain hints

Neither addition required a `_config_version` bump — deep-merge fills
defaults in for existing user configs.

## Validation

| Test surface | Result |
|---|---|
| tests/tools/test_env_probe.py | 10/10 pass (probe unit) |
| tests/run_agent/test_run_agent.py — new classes | 8/8 pass (integration) |
| TestToolUseEnforcementConfig | 17/17 pass (no regression) |
| TestBuildSystemPrompt | 9/9 pass (no regression) |
| TestInvalidateSystemPrompt | 2/2 pass (no regression) |
| tests/agent/test_prompt_builder.py | 124/124 pass (no regression) |
| tests/hermes_cli/ | 5662/5662 pass (config defaults) |
| E2E AIAgent build (broken env) | Both blocks present, 2,178 chars |
| E2E AIAgent build (clean env) | 771-char net overhead, env probe silent |
kingsleydon pushed a commit that referenced this pull request Jun 3, 2026
A bare `/resume` printed the recent-sessions list but armed no selection
state, so typing just `3` on the next line was sent to the agent as chat
instead of resuming session #3. `/resume 3` worked, but the natural
list-then-pick flow did not.

Arm a one-shot pending-resume prompt when bare `/resume` shows the list,
and consume the next bare numeric input as the selection (out-of-range is
reported, non-numeric/other commands disarm it). Resolves against the same
_list_recent_sessions(limit=10) list used everywhere else.

Closes NousResearch#34584.
kingsleydon pushed a commit that referenced this pull request Jun 3, 2026
…NousResearch#34192) (NousResearch#34382)

NousResearch#34192 reports Hostinger's 'Hermes WebUI' catalog crashes on startup
with:

  /usr/bin/tini: No such file or directory

The image moved from tini to s6-overlay as PID 1 (/init) earlier in
2026. Orchestration templates that still pin /usr/bin/tini as the
entrypoint \u2014 like the Hostinger Hermes WebUI catalog \u2014 have no
binary to exec and the container crashes immediately.

Hermes has no control over the Hostinger catalog template, but we can
make the image backward-compatible by symlinking /usr/bin/tini -> /init
during the s6-overlay install step. External wrappers that exec
/usr/bin/tini will land on the same s6-overlay reaper they would have
landed on if they'd used the canonical /init entrypoint.

The image's own ENTRYPOINT continues to be /init verbatim \u2014 the shim
is purely for legacy external wrappers, not for the image's own
runtime path. Once affected catalogs are updated, the symlink can be
removed.

Other issues NousResearch#34192 raises that are NOT addressed by this PR:

  * Problem #2 (UID 1024 vs 10000 mismatch): already fixed by NousResearch#33148
    (S6_KEEP_ENV=1) and NousResearch#32412 (with-contenv shebangs). The Hostinger
    template likely needs to update its env-var propagation.

  * Problem #3 (incompatible session formats): RFC for pluggable
    SessionDB is tracked in NousResearch#23717.

  * Problem #4 (Telegram polling conflict): an operations problem on
    Hostinger's side, not in this codebase.

This PR is scoped to the one issue that can be fixed inside
Dockerfile: the missing /usr/bin/tini binary.

Tests (3 in test_dockerfile_tini_compat_shim.py):

  - test_tini_compat_symlink_present
    Guard: the symlink line must exist in Dockerfile.
  - test_tini_compat_comment_explains_why
    The NousResearch#34192 anchor comment must be present so future readers know
    why the shim is there (avoid accidental removal).
  - test_entrypoint_still_init_not_tini
    Sanity check: ENTRYPOINT remains /init (s6-overlay). The shim is
    only for external wrappers.

Refs: NousResearch#34192
Partial fix: addresses the immediate tini-binary crash. Catalog-side
fixes still needed by Hostinger for the UID and session-format
problems documented in the issue.

Co-authored-by: Cursor <cursoragent@cursor.com>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant