Give dispatcher-owned workers a tool-capable reporting opportunity before the
hard iteration cap, without accepting arbitrary diffs or weakening failure
counting. Add opt-in per-turn iteration checkpoints for ordinary agents.
Persist checkpoint text with the fresh tool result, never rewrite cached rows.
Salvages the opt-in ratio and per-turn reset implementation from #104683;
credits the earlier default-off signpost proposal in #92438.
Local fixture wire A/B: Kanban ready/1 failure -> done/0; deliberately stuck
workers still reach blocked/2 after two runs. Default-off control unchanged.
Targeted and affected-directory suites queued behind campaign test lock.
Co-authored-by: fangliquanflq <fangliquan@qq.com>
Co-authored-by: C. Michael Gibbs <252231331+MikeGibbsOnyx@users.noreply.github.com>
Persist paused state, timestamp, reason and no first trigger in the original
locked creation write. Forward the same boolean contract across CLI, tool,
gateway API and dashboard API, validating at the store boundary. Preserve
explicit operator force-run behavior and normal enabled creation.
The live CLI probe also caught the command shim dropping failure return codes;
forward them so invalid creation reports exit 1 rather than success.
Credit earlier atomic-creation work in #78935 and #94952 and the focused
implementation in #104578. The broader manifest staging layer is not imported.
Co-authored-by: Konstantin Khlopkov <konstantin.khlopkov93@gmail.com>
Co-authored-by: Chloé DuPont <321112755+misschloedupont@users.noreply.github.com>
Based on the earliest batching proposal by BrunoBza (#104686) and JoaoMarcos44 structured correction (#104703). Slim redo into topical siblings and shared TUI poller/post-turn routing. Reported by Xipong (#104671). Local shell-to-loopback probes demonstrate 12 to 1 turn dispatches; suites await the campaign test lock.
Co-authored-by: joaomarcos <joaomarcosdias444@gmail.com>
`hermes_cli/banner.py::_git_run` is the shared spawn path for every banner and
passive update-check git probe (rev-parse, rev-list, remote get-url, ls-remote).
It carried the UTF-8 text contract but not `creationflags=windows_hide_flags()`,
so on Windows each probe run from a GUI-hosted backend (desktop-spawned
`hermes serve`, `tui_gateway` import kicking off `prefetch_update_check`) flashes
a console window. Every other short-lived helper in `hermes_cli/` already passes
the flag; this brings the banner path in line.
Surfaced by CI on this PR: the stray `git ... origin` spawn from the prefetch
daemon landed in `test_env_probe_run_hides_console_window`'s process-wide
`subprocess.run` capture and tripped its call-count assertion. The test now
scopes its assertion through the module's `_spawns` helper like its siblings,
so an unrelated daemon spawn cannot fail it (the production fix is what makes
that stray spawn carry the flag in the first place).
A/B: base `_git_run` -> no `creationflags` kwarg; fixed -> 0x08000000.
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>
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).
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.
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)
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>
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>
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>
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>
Salvaged from #104272. Preserve restart and fatal-exit policy while classifying the planned restart code as success. Earlier analysis in #13604 by Justin Kausel.
Carry the existing write fence across Hermes-owned spawn boundaries without
dropping board routing or changing credential policy. Grant dispatcher and
managed tool runtimes explicit task scope; align CLI task mutations with tools.
Verify real shell/CLI descendants, dispatcher startup, and supervised stdio
transport against isolated SQLite boards. This is cooperative runtime scoping,
not OS confinement.
Refs #103974, #104058, #104904
Salvage #101887 after native Actions 34097643131 reproduced WinError 32 using a ready Electron app with its cwd inside the live release. Reuse the existing install-scoped process cleanup before promotion and wait after forced termination, preserving rollback.
Co-authored-by: fangliquan <fangliquan@qq.com>
Three orchestrator failures traced through the Sep 7 gpt-6-astra campaign sessions:
1. delegation.independent_completions (new, default false). #104299 made every
ungrouped task its own completion message, so a 15-task call woke the
orchestrator up to 15 times; one chain received 132 notices and answered
130 of them with "already incorporated". A multi-task call now returns as
ONE consolidated message unless the flag is on; `group` is inert until then.
2. Queued units were killed before they started. Units of one call share a
pool slot but the executor was still sized by slots, so with 15 units live
a new unit queued behind a full pool; the stale monitor's clock ran from
dispatch, interrupted it at 450 s, and the child exited `interrupted 0.02s`
when its thread finally came up (13 such lanes in one session). The
executor now grows to the number of live units and the stall clock arms
when the runner actually starts.
3. The tool text said "do not wait or poll — just continue" without saying
that completions are delivered only BETWEEN turns. A model that never ends
its turn (one 203-minute turn, 717 API calls) never received 40 finished
results. Tool description, dispatch note and completion header now say to
finish independent work, give a one-line status, and end the turn.
Adapt the config-only portion of #104347; omit its environment flag and unrelated docs. Explicit update commands remain independent.
Co-authored-by: Rohith Pariki <rohithpariki@gmail.com>
Slim adaptation of #83772 to the current schema and failure-hint table.
Generated helpers are module exports on every execution path, not globals.
Correct schema, recovery hints and CLI tip rather than injecting names or
changing the execution boundary. Two registry-driven invariants reproduce
both misleading instructions on main and execute the corrected guidance.
Additional tool fix discovered during campaign #104904.
Original diagnosis and correction: @yuzilongleif-collab (#83772).
Co-authored-by: yuzilongleif-collab <235949691+yuzilongleif-collab@users.noreply.github.com>
Discover systemd targets before stopping old processes, restart even when
there are no gateway PIDs, and require successful scope listings plus active
verification. Pending launchd recovery also retains failures for inaccessible
listings and installed jobs without supervision. Keep existing PID cleanup
intact but before recovery so it cannot kill freshly verified workers.
Slim redo informed by #104274, #104283, and #104285.
Co-authored-by: fangliquanflq <fangliquan@qq.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Preserve producer descriptions without identity wrappers and size the existing themed tooltip to the viewport. Replace skipped and structural tests with two behavioral invariants. Native Electron before/after hover, click and keyboard verification passed; campaign suite validation remains queued.
Slim adaptation of anombyte93/hermes-agent@d06d2a49c5; use the canonical board resolver instead of inferring the slug from a path. Live isolated CLI probe confirms current-file, env and explicit board banners; event delivery remains live.
Co-authored-by: Hayden (Atlas agents) <212644172+anombyte93@users.noreply.github.com>
check_for_skill_updates() fetched every lock-file entry remotely, even
when the entry's install directory no longer existed, and each fetch had
no wall-clock bound — a few dead sources turned a routine
`hermes skills update` into a multi-minute stall (#104291).
- Entries whose recorded install_path resolves but does not exist are
reported as "orphaned" and skipped without a remote fetch;
unresolvable paths keep the previous fetch behavior.
- Each fetch now runs under a daemon helper thread with a hard timeout
(default 30 s) and degrades to "unavailable" when abandoned.
- `hermes skills check` prints a removal hint for orphaned entries.
Fixes#104291
Retain partial-line output, UTF-8 decoding, failure output and cancellation cleanup. Based on streaming investigations by Artemonim (#101850) and lEWFkRAD (#104843); gateway tee adapted from fangliquanflq (#97402). Live Linux child/tee probe: withheld or dropped on base, visible in 0.02 seconds after. Campaign-locked tests and native Windows proof are pending.
Eva