Commit Graph

32586 Commits

Author SHA1 Message Date
Teknium a46ddf0f32 test: keep quickstart preflight independent of host acceleration 2026-09-07 08:23:08 -07:00
Teknium f94307a7f7 fix: ignore malformed MCP OAuth metadata caches
Guard device metadata subtype selection with a dictionary check so valid
non-object JSON reaches the existing validation-and-ignore path. Preserve
null handling, cache contents, and normal/device metadata cold-load types.
Extend the existing corrupt-cache invariant rather than adding test functions.

Live filesystem A/B reproduces list/string/number/boolean AttributeError on
the prior head and clean ignore after this change. Nine CLI OAuth wire
scenarios, browser S256 and profile-scoped storage controls pass locally.
2026-09-07 08:22:35 -07:00
Teknium 965f18b02f fix: restore prior device OAuth state if persistence fails 2026-09-07 08:22:35 -07:00
Teknium f5afe8bd40 feat: authorize MCP servers with device codes from the CLI
Add explicit RFC 8628 device login and oauth.flow selection while keeping
browser PKCE and the SDK runtime refresh path. Reuse issuer/resource
validation, configured client authentication and profile-scoped storage.
Only persist an approved, validated grant; never echo endpoint error bodies.

Slim redo of #104752 by @wjorgensen, replacing duplicate HTTP/storage
wrappers with the existing SDK and two real-wire invariant tests.

Refs #104742
Co-authored-by: Wes Hermes <weshermes@Wess-Mac-mini.localdomain>
2026-09-07 08:22:35 -07:00
Teknium a460b44c93 docs(desktop): document directive action hover grace 2026-09-07 08:21:57 -07:00
Teknium 3a42722c84 test: verify SSH update checks with real PTY authentication controls 2026-09-07 08:21:24 -07:00
liuhao1024 9197afe44d test(cli): pin git identity in the insteadOf regression test setup
The regression test builds its scratch repo under GIT_CONFIG_GLOBAL/
GIT_CONFIG_SYSTEM = /dev/null, so the init commit has no configured
identity. On CI runners the auto-detected ident is rejected
(user@<bare-hostname>.(none)) and 'git commit' exits 128, failing the
test that passes locally. Pin user.email/user.name on the commit, the
same pattern the install-script tests already use.
2026-09-07 08:21:24 -07:00
liuhao1024 9f0bf22ce2 fix(cli): pin core.sshCommand to BatchMode ssh in the noninteractive git env
ssh bypasses stdin=DEVNULL and GIT_TERMINAL_PROMPT: when a git child
dials an SSH remote whose host key is unknown, ssh opens /dev/tty
directly and its yes/no prompt steals the caller's terminal — exactly
what noninteractive_git_env exists to prevent. Pin core.sshCommand to
"ssh -o BatchMode=yes" at the config-injection layer so the ssh child
fails instead of prompting; an agent-authenticated ssh still succeeds,
and an explicit user GIT_SSH_COMMAND env var still takes precedence
(#104591).
2026-09-07 08:21:24 -07:00
liuhao1024 03c20babba fix(cli): probe update-check origin URL under the fetch's isolated git env
The startup update check resolved `git remote get-url origin` with the
user's global config in scope while the subsequent fetch runs under
noninteractive_git_env (GIT_CONFIG_GLOBAL=/dev/null). A global
url.<https>.insteadOf rewrite therefore made an SSH origin masquerade as
HTTPS, the SSH-avoiding fast path was skipped, and the fetch dialed the
raw SSH origin — whose host-key prompt opens /dev/tty directly and
steals the CLI's keystrokes (#104591).

Probe the origin URL under the same isolated env so both sides observe
the URL the fetch will actually dial.
2026-09-07 08:21:24 -07:00
Teknium 89c85b8466 fix(update): settle stale receipt warnings from matching live gateways
Reconcile receipt-only restart obligations at the shared warning/catch-up
predicate, requiring every historical runtime/profile identity to have a
current live gateway successor. Preserve missing and unknown obligations,
non-gateway identities, and independently authoritative pending markers.

Keep failed receipts unchanged instead of recording an unverified success.
Live isolated two-process A/B reproduces the warning on base and settles
it after the fix; stale, unknown, and missing-profile controls still warn.

Reported-by: duanzhiwei0315
Inspired-by: zengzheqing (#104295), RootZ3n (#100249)
2026-09-07 08:20:46 -07:00
Teknium 50cd1190ef test: pass snapshot listings to the catch-up restart budget probe
Main now snapshots systemd unit listings before stopping old processes
and passes them into _restart_systemd_gateway_units_best_effort; the
catch-up budget test and eval call the new two-argument shape while
still asserting the unit's stop+start budget reaches the client timeout.
2026-09-07 08:20:09 -07:00
Teknium 08f2c78d92 fix(update): cover catch-up restart clients with the unit budget 2026-09-07 08:20:09 -07:00
Teknium bb12ee7a5a test: retain native systemd restart budget probe 2026-09-07 08:20:09 -07:00
Teknium 6ab2245f69 chore: credit systemd restart budget contributor 2026-09-07 08:20:09 -07:00
doryani-agent 2a980fbcbd fix(update): let systemd clients outwait legitimate unit transactions
Salvage the unit-budget implementation from #104745, replacing its test
matrix with two invariant tests and covering the sibling graceful start.
Keep unprivileged property reads, finite fallbacks, real manager errors,
and post-restart health verification.

Native disposable user unit: old client timed out after 15.03 seconds;
new client completed the same 16-second stop transaction in 16.13 seconds.
The unit stayed active with a new PID; missing-unit errors stayed errors.

Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
2026-09-07 08:20:09 -07:00
Teknium bbbcde8173 fix(process): stop late forks escaping deadline tree cleanup 2026-09-07 08:19:32 -07:00
Teknium db529aa256 test(cron): exercise historical error redaction in live probe 2026-09-07 08:18:56 -07:00
Teknium e1a161538a fix(cron): make failed runs diagnosable without verbose delivery errors
Persist a redacted chained traceback in the private run output and expose
redacted last_error in tool and slash listings, including historical errors.
Keep the run_job concise error return unchanged for delivery classification.

Slim redo of liuhao1024's earliest #104545; adds forced redaction and keeps
formatting in a topical sibling. Local SDK/socket A/B verifies diagnosis
visibility plus healthy-script, clearing, and private-file controls.
Canonical tests queued under the campaign lock at commit time.

Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
2026-09-07 08:18:56 -07:00
Teknium e3710c1593 fix(cron): preserve continuity across silent audit ticks
Slim redo of #104546 and #104551: scan newest-first, match suppression only before payload separators, and keep error context. Covers wake gates and empty outputs without reading every historical file twice.

Co-authored-by: PRATHAMESH75 <prathamesh290504@gmail.com>

Co-authored-by: Konstantin Khlopkov <konstantin.khlopkov93@gmail.com>
2026-09-07 08:18:20 -07:00
Teknium 549e6aab38 fix(bot-mode): preserve refusal reasons across local delivery
Emit the one-shot reason marker outside the CLI facade; parse whole codes before falling back to legacy prose. Explicit coordination and unknown codes cannot be labeled target_busy.

Fixes #104784
Co-authored-by: William Echo <2054936695@qq.com>
2026-09-07 08:15:32 -07:00
Teknium 8aaf1aca62 fix(schemas): preserve required intent without invalid boolean flags
Normalize boolean required only at schema positions; lift true property flags into parent arrays. Preserve literal default/const/extension data.

Fixes #104796
Inspired by #104831 and the lifting proposal by @AdJIa.
2026-09-07 08:14:51 -07:00
Teknium ab98a92a45 fix(notifications): report applied skill batch operations
Use successful applied result records rather than requested operations, and keep staged writes silent. Include legacy delete/write messages.

Fixes #104506
Co-authored-by: Konstantin Khlopkov <konstantin.khlopkov93@gmail.com>
2026-09-07 08:14:14 -07:00
Teknium 7876d183c9 fix(approval): recover legacy list values without character grants
Recover legacy stringified lists with a warning. Reject malformed shapes and nonstring members without admitting approvals or rewriting user config on read.

Fixes #104779
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
2026-09-07 08:13:38 -07:00
Hermes Agent ab1a6d016a test(display): encode provenance contract in tilde assertions
Two tests still encoded the pre-PR behaviour that the PR removes:

- tests/test_tui_gateway_server.py: the mirrored fixture carries no
  `context_estimated` flag, so under the PR's rule it is provider-reported
  usage and must render without `~`. The old expectation asserted the
  unconditional tilde main used to emit. Assert the flag-less case is
  unmarked and, in the same test, flip `context_estimated` both ways to
  pin that only the estimate carries `~` in the count and the percent.

- ui-tui appChromeStatusRule.test.tsx: `text.includes('~')` matched the
  `~/repo` cwd label, so the "not estimated" arm was always true. Extract
  the rendered context token and assert the tilde on that token only.
2026-09-07 08:13:01 -07:00
Teknium 9da8c63b1a fix(display): preserve localized estimate markers and headroom labels 2026-09-07 08:13:01 -07:00
Teknium 62f64ae5b0 fix(display): retain provider provenance for persisted fallback readings 2026-09-07 08:13:01 -07:00
Teknium b4e2ae9e76 test(display): exercise real usage and usage-less provider controls 2026-09-07 08:13:01 -07:00
Teknium 04767e7aaa fix(display): distinguish estimated context from provider usage 2026-09-07 08:13:01 -07:00
Hermes Agent 283e677ed6 style(honcho): drop trailing blank lines at EOF in recall test
`git diff --check origin/main..HEAD` reported
`tests/honcho_plugin/test_recall_sync.py:130: new blank line at EOF.`
Whitespace-only; no test logic changed.
2026-09-07 08:12:23 -07:00
Teknium 4f54a6d157 test(honcho): exercise config precedence through local SDK recall 2026-09-07 08:12:23 -07:00
Teknium 99f7d2b4df fix(honcho): isolate recall generations and reject unscoped fallback 2026-09-07 08:12:23 -07:00
funky-xamarin 707267095a feat(honcho): add bounded opt-in current-query recall 2026-09-07 08:12:23 -07:00
Teknium 42da1f2cf4 chore: map Charles Ji contributor email 2026-09-07 08:10:36 -07:00
Teknium 1eb1b795b5 test(gemini): verify alias routing and compatible endpoint controls 2026-09-07 08:10:36 -07:00
Charles Ji a745101e5f fix(gemini): route google-alias fallback providers through GeminiNativeClient
fallback_providers entries using the "google" alias for the gemini
profile were falling through to the generic OpenAI-SDK client because
the native-client gate only matched the literal string "gemini". That
client posts straight to the raw REST endpoint, sending thinking_config
as an unnested top-level field, which Gemini rejects with:

  Invalid JSON payload received. Unknown name "thinking_config": Cannot find field.

Broaden the check to the same alias set the gemini profile itself
registers (mirrors _GEMINI_NATIVE_PROVIDER_NAMES already used for this
in auxiliary_client.py).

Fixes #104583
2026-09-07 08:10:36 -07:00
Teknium cd0b5b9add docs: record independently repeated input-ownership wire probe 2026-09-07 08:09:57 -07:00
Teknium a9ef4a7625 fix(codex): keep transport echoes out of durable user history
Port the exact submitted-wire-text ownership boundary from #93546 onto
current topical runtime code. Do not add the candidate's mocked-result
fallback or storage-level content deduplication. Preserve later distinct
and identical user events, separate identical accepted turns, and keyless
inputs. Add two regression invariants and offline subprocess-wire A/B.

Local wire A/B: 4/8 control matrix passing on base, 8/8 after.
Broader tests queued behind campaign lock; not ready for merge.

Refs #104653
Original diagnosis: @gitszabolcs (#38254)
Original implementation: #43127, submitted by @vashkartik
Focused salvage and wire-text correction: @fancyboi999 (#93546)
Current-main carry-forward considered: #104698

Co-authored-by: Xinmin Zeng <135568692+fancyboi999@users.noreply.github.com>
Co-authored-by: VECTOR <vector.hq@outlook.com>
2026-09-07 08:09:57 -07:00
Teknium 5904c7a395 fix(threats): keep unrelated role prose in context files
Salvage the bounded target-slot design from #104617, using mandatory
word separators to avoid ambiguous repeated matches. Preserve long
payload detection and execution-verb boundaries. Replace the three
candidate tests with two context-loader invariants and document the
heuristic's limits.

Fixes #104609
Co-authored-by: Konstantin Khlopkov <konstantin.khlopkov93@gmail.com>
2026-09-07 08:09:20 -07:00
Teknium 1491342661 style: remove blank line left by snapshot setting removal 2026-09-07 08:08:41 -07:00
Teknium 7a5fc1b2a9 fix: remove automatic session JSON snapshots 2026-09-07 08:08:41 -07:00
Teknium bbbccd3935 fix: failed probe credentials cannot fall through to configured auth 2026-09-07 08:08:04 -07:00
Teknium 7d44fe9c74 fix: capability probes send minted credentials instead of callable representations
Extend #104477 to the native thinking, vision, metadata, and local header paths identified by #87641. Materialize only at probe boundaries; leave the chat callable and cache ownership untouched. Local-wire A/B: thinking and vision show requests change from 403 to 200, while static credentials and callable chat retain success. Target suites queued.

Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
2026-09-07 08:08:04 -07:00
Teknium 07ddfaa2d6 test: fix CI red — pool fixtures carry source, refresh assertion binds the failed key
Two test-only corrections for the failures on run 34105317301:

- tests/agent/test_anthropic_adapter.py::TestResolveAnthropicToken: the new
  skip_borrowed branch reads ``entry.source``. ``PooledCredential.source`` is a
  required dataclass field that ``from_dict`` always materializes (defaults to
  SOURCE_MANUAL) and ``_available_entries`` returns only PooledCredential, so a
  production entry can never lack it. The three SimpleNamespace doubles were the
  incomplete side; build them via ``PooledCredential.from_dict`` instead of
  duck-typing production with getattr.

- tests/agent/test_auxiliary_client.py::test_stale_anthropic_fallback_refreshes_and_retries:
  the PR itself now passes ``failed_api_key=<client.api_key>`` into
  ``_refresh_provider_credentials`` so an unrelated borrowed login never owns the
  refresh; the assertion still expected the bare ``("anthropic")`` call. Give the
  stale client an explicit api_key and assert the request-bound call. Main's
  auxiliary changes since the PR base (ebe4e7bb44, b40998bc3c..cb1a42d33b) did not
  move this call.
2026-09-07 08:07:26 -07:00
Teknium b14315ab6b test: exercise owned OAuth recovery through the unchanged ladder surface 2026-09-07 08:07:26 -07:00
Teknium bdf45abd7c fix: prefer owned Anthropic grants and bind auxiliary refresh to request credentials
Port owned-before-borrowed resolution from #104624, crediting the root cause in #104622. Include the synchronous and asynchronous auxiliary fallback recovery sites: forward the failed request key so an unrelated borrowed login never owns that refresh. Local-wire probes preserve the borrowed file and exchange only the owned grant. Broader validation remains queued; do not treat this commit as ready.

Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>

Co-authored-by: d-bow-dev <24577047+dwb1991@users.noreply.github.com>
2026-09-07 08:07:26 -07:00
Teknium 134b173efa fix: reject independent Nous account refresh without clearing cooldown 2026-09-07 08:06:48 -07:00
Teknium c13c37a699 test: isolate external auth stores in pool command fixtures 2026-09-07 08:06:48 -07:00
Teknium f087cb8055 test: exercise credential controls through PTY and local OAuth wire 2026-09-07 08:06:48 -07:00
Teknium de25786dc7 fix: place reauthenticated credentials by their saved identity 2026-09-07 08:06:48 -07:00
Brian Le 32a59f3bf7 feat: refresh one pooled OAuth grant from the CLI 2026-09-07 08:06:48 -07:00