The schema initializer now replays SCHEMA_SQL through executescript (the
single-authority path from #94701's follow-up), which bypasses the
execute()-level DDL failure injection — the regression stopped raising.
Bind the same simulated failure onto the executescript path so the
connect-close-on-init-failure contract stays pinned for both replay
mechanisms.
Review follow-up on #94701: the delegation tool's _initialize_schema
still carried its own CREATE TABLE + ALTER column list for
async_delegations, leaving a second durable-shape authority even with
the column declared in SCHEMA_SQL. Its legacy ALTER added
origin_session_id as bare TEXT (nullable, no default); reconciliation
repairs missing column names only, so a database first opened through
the tool kept a non-canonical shape forever (#94691).
Remove the private DDL entirely. The tool's initializer now calls a new
reconcile_state_schema() in hermes_state_schema, which replays the
canonical SCHEMA_SQL (idempotent CREATE IF NOT EXISTS for every table,
canonical indexes included) and reuses SessionDB's declarative
_reconcile_columns for missing-column backfill — one reconciliation
implementation, one authority. Because _parse_schema_columns
reconstructs each column's full constraint expression (type, NOT NULL,
DEFAULT), the tool-first legacy path now adds origin_session_id as
TEXT NOT NULL DEFAULT '' — the canonical shape — and SQLite backfills
existing rows with the '' default.
Opening-order regressions compare FULL PRAGMA table_info metadata
(type, notnull, dflt_value, pk) plus the canonical index set across
fresh SessionDB→tool, legacy→SessionDB, and legacy→tool→SessionDB,
each preserving a pre-existing legacy delegation row.
The delegation tool carries its own CREATE TABLE for async_delegations
(tools/async_delegation.py _initialize_schema) plus a lazy ALTER TABLE
ADD COLUMN for the tables it finds already existing. Its column list
had drifted ahead of the canonical SCHEMA_SQL: origin_session_id
(raw api_server session id of the originating request, the wake
self-post target) existed only through the tool's lazy path, so two
databases at the same schema_version had different
async_delegations shapes depending solely on whether the delegation
tool had ever run. Rebuild/replay pipelines that reconstruct state.db
from the canonical schema then hit the column with no version gate to
explain it (#94691).
Declare the column in SCHEMA_SQL with the same TEXT NOT NULL DEFAULT ''
shape the tool uses. Fresh installs now carry it canonically; the
declarative _reconcile_columns backfills it into legacy databases on
the next writable open (same pattern as earlier additive columns); the
tool's lazy ALTER keeps serving pre-reconciliation databases. The two
schema authorities now agree, pinned by a test that runs the tool's
initializer over a canonical database and asserts the shape is
unchanged.
Fixes#94691
The corruption explainer filled `{db_path}` from `_default_db_path()`, the
process default. A Desktop `serve` backend launched on the root home hosts
named-profile sessions whose SessionDB is `profiles/<name>/state.db`, so the
operator was told to inspect/repair a different profile's database. Pass the
agent's own `_session_db.db_path` from the turn finalizer; the process
default remains the fallback for agents without a bound store.
Reported in #105887.
Reading a session by id that missed the caller's store fell through to
_locate_session_db(), which opened every profile's state.db read-only and
returned the first owner's full transcript — no opt-in, no profile named, and
the miss path even fired after an explicit non-matching profile= read. Any
caller holding an id (ids appear in logs and tool output) could read a
foreign profile's conversation. Profiles are isolated islands by design.
A miss now stays a miss, with a hint to name the owning profile
(profile=<name> / @session:<profile>/<id>), which remains the sanctioned,
explicit cross-profile read. The schema eval runner no longer needs to fake
the scan.
Reported by the #106761 filer; reproduced by @kokhlo. Refs #87779.
The salvaged #102534 test patched hermes_state.get_shared_session_db, a seam
main dropped (server._get_db now calls hermes_state_registry.acquire), so the
fixture errored at setup and the file reported 0 passed. Assert on the real
handle's db_path and on the foreign home staying untouched instead of on a
fake factory; red with the pin reverted, green with it.
close_all_under returned after the last release dropped the generation
and before the physical close finished, so rmtree still saw the open
handle. Wait directory-matching teardown barriers the same way close_all
does.
delete_profile already force-closes holographic memory_store.db in this
process, but the shared SessionDB registry kept state.db open. Recreate
then failed with a replaced/locked database. Close every shared handle
under the doomed directory, same contract as MemoryStore.release_all_under.
Co-authored-by: Cursor <cursoragent@cursor.com>
Since 0.21.0 reads go through mode=ro pooled connections. A read-only OPEN already
rides out the millisecond WAL transition window (checkpoint / WAL reset / frame flush
by a sibling process; the ro reader cannot rewrite the -shm index) with a bounded retry
(#100436), but a WARM pooled reader hitting the same window while its SELECT executes
propagated `disk I/O error` straight out of get_session(): 37 identical tracebacks on a
multi-process WSL2 ext4-on-vhdx install, each followed by "compression session recovery
failed", with quick_check=ok (#100871). The reporter's A/B shows the operator
workaround (journal_mode=delete) collapses read throughput ~30000x, so the flake has to
be absorbed on the read path.
_read_one/_read_all now replay the idempotent statement within the existing read-only
IOERR budget (3 x 50 ms) on the SAME connection -- close+reopen would cancel this
process's POSIX locks for every sibling connection -- and a persistent IOERR still
propagates. No quarantine: EIO on a read is busy, not broken. Every SELECT in the
SessionDB siblings (63 call sites) reaches the pool through these two helpers, so the
class is covered without a wrapper type.
Same-connection retry per #100882's analysis (@fangliquanflq); #100883
(@Sahilvishnaliya) diagnosed the missing recovery in the 0.21.0 read pool.
Fixes#100871.
Co-authored-by: fangliquanflq <fangliquan@qq.com>
Co-authored-by: Sahilvishnaliya <222165401+Sahilvishnaliya@users.noreply.github.com>
apply_wal_with_fallback() reports "wal" in two indeterminate cases -- the vulnerable-
SQLite gate (_apply_delete_for_wal_reset_bug) and the non-vulnerable probe-unknown path
(a7f2a593d1) -- meaning "touched nothing, the connection inherits the header's mode".
SessionDB turned that assumption into `_wal_active=True`, which enables the mode=ro read
pool that skips `self._lock`. On a file that is really in rollback-journal mode those
readers race the writer with a 5s busy timeout and no retry: random SQLITE_BUSY read
failures for the instance's lifetime (#86515).
Confirm the header on the freshly opened connection before enabling the pool. When the
probe is still blocked, reads queue on the writer connection under the lock -- slower,
never wrong. Every other apply_wal_with_fallback caller ignores the return value, so the
consumer is the right place to gate; changing the return contract to Optional across
15 call sites (#87044's shape) is not needed.
Live repro: DELETE-mode file, sibling holding BEGIN EXCLUSIVE during open ->
before: _wal_active=True and _checkout_read_conn() hands out a pooled mode=ro conn;
after: _wal_active=False, reads take the locked writer path.
Fixes#86515. Based on the analysis in #87044.
Co-authored-by: QDung210 <dqdung205@gmail.com>
_send_session_db_warning_notifications() broadcast the error recorded at startup
without asking whether it was still true. A startup `database is locked` routinely
clears while the adapters are still connecting (another profile's open, a `hermes
sessions` one-shot, a slow SMB lock release), so the home channels were told the
store was unavailable when it had already healed — and a warning that is wrong once
is ignored the next time it is right.
The RecoverableHandleCache opener already clears `_session_db_init_error` on
recovery; the broadcast now drives one open attempt through it first and only warns
when the error is still standing. A store that is genuinely still down warns exactly
as before.
Fixes#108031.
main replaced the file-local _make_db/_require_wal/_unlink_sidecars helpers with
tests/hermes_state/_wal_generation_harness (make_db/require_wal/lose_sidecars) after
PR #107411 branched; the cherry-picked tests referenced the old names and failed at
collection with NameError. Fixture-only change; the assertions are unchanged.
Classify deleted WAL generations separately from main-file replacement and point operators at the captured-generation manifest and mode-aware recovery path.
Co-authored-by: crazyief <8566250+crazyief@users.noreply.github.com>
st_nlink == 0 alone cannot distinguish a genuine orphan from one that
still has a surviving hard link (e.g. a backup) after the watched
sidecar path itself was removed or replaced — that left st_nlink >= 1
on a truly orphaned generation, letting a new opener through while a
live writer still owned the old one. Compare (st_dev, st_ino) between
the fd and the current watched sidecar path instead: only an exact
match means they're the same live file, so any mismatch or unstattable
watched path still fails closed.
iter_deleted_sqlite_sidecar_holders() and SessionDB._wal_generation_was_lost()
both treated a `` (deleted)`` suffix on a /proc/<pid>/fd/* target as proof that
state.db-wal or state.db-shm was unlinked. On OpenZFS that suffix is not proof:
a live, still-linked file whose dentry was unhashed is reported the same way,
with st_nlink still 1 and the same (dev, ino) as the path. The guard then fires
permanently and the gateway falls back to JSONL forever, because the WAL was
never actually deleted.
Add _fd_is_truly_unlinked(), which confirms via os.stat(fd_path).st_nlink == 0
before a target counts as an orphaned generation. An unstattable descriptor
still counts as deleted, so the guard keeps failing closed. _iter_proc_fd_targets()
and _proc_fd_targets() now also yield the /proc fd path itself so both call
sites (open-path and the sticky write-path probe) can run the check.
Keep the two invariant tests from #105428: a genuine second instance
whose argv is scoped to another HERMES_HOME is not a holder of our
state.db; argv that names our state.db stays flagged. The helper-shape
tests were change-detectors on `_argv_scoped_to_other_home` internals.
The salvaged commit is re-authored to TaoMasterCoder's GitHub noreply
identity: the original `devops@77hub.com` is a shared org address
(misconfigured local git, not malice).
Refs #107440
Field evidence (2026-09-07, production host): the host runs two independent
Hermes instances - a main gateway (user ubuntu, HERMES_HOME=/home/ubuntu/.hermes)
and a demo gateway (user demo, HERMES_HOME=/home/demo/.hermes). Because the
demo process is owned by another user, its /proc/<pid>/fd table is unreadable
and foreign_state_db_holders() falls back to cmdline + _looks_like_hermes().
The demo argv matches Hermes patterns exactly, so it was flagged as an
uninspectable holder of the MAIN instance's state.db even though lsof proved
0 open handles on it. Result: _recover_stale_fts was deferred 42 times across
6 gateway restarts, the fts_stale breadcrumb never cleared, and FTS
self-repair stayed permanently disabled.
#92419 removed substring false positives (journalctl/grep mentioning hermes);
a genuine second instance with a DIFFERENT HERMES_HOME was still misjudged.
Add _argv_scoped_to_other_home(): when the argv of an uninspectable Hermes
process proves it lives under a different /.hermes home (or a state.db
sidecar under a different parent) AND no token references our state.db,
sidecars, or home, do not count it as our holder. Applied to all three
uninspectable branches (holder + two descriptor paths). Ambiguous argv
without absolute-path tokens remains fail-closed, preserving the
conservative intent.
References #92401
Invariant test for the #103489 salvage: a profile gateway and the root
gateway resolve the same hosted-room coordination file at the install
root, and that file is never the root SessionDB (`state.db`). Every
profile gateway starts the hosted-room worker unconditionally, so the
old mapping made each profile process a long-lived writer on the master
session store — the simultaneous-restart corruption in #102120 and the
main offender in the #103339 / #103490 fleet reports.
Also: WAL-fallback labels say `shared-state.db`, and test fakes take the
store path from `default_db_path()` instead of hardcoding `state.db`.
Reported-by: #102120#103339 (@RChina) #103490
Refs #102120#103339#103490
`hermes profile delete` leaves `profiles/.deleted/<name>` behind.
`HostedRoomService.local_profiles()` fed every subdirectory name to the
roster, so `.deleted` failed `validate_roster`'s identifier check and
`plan_next_task` raised on every cycle for every room until the
directory was removed by hand (#106847, bug 2). Skip dot-dirs and
tombstoned profiles, using the same `named_profile_is_deleted` predicate
`hermes_cli.profiles` uses to list live profiles.
Refs #106847
The dashboard's `_eager_reconcile_own_session_db` did an unconditional
writable `acquire()` at every startup. When the gateway shares that
state.db the dashboard became a second long-lived writable SessionDB
owner: a close-time WAL checkpoint plus a possible FTS rebuild in
`_init_fts`, the two-writer vector behind the corruption reports in
#107688 and #100896 ("5 live SessionDB handles" precursor, gateway +
dashboard both holding the WAL).
Route the startup reconcile through `_open_session_db_at_path(...,
read_only=True)`, which already bootstraps a missing store and heals a
stale/malformed schema through exactly ONE writable open before
reopening read-only. A healthy store now gets zero writable opens from
the dashboard while the #79531/#80037 "bring schema current before the
first poll" contract is kept (existing heal test unchanged).
Live repro (healthy store, count writable SessionDB.__init__ calls from
the startup worker): before=1 after=0.
Reported-by: #107688, #100896 (@kokhlo diagnosis)
Refs #107688#100896
doctor --fix ran a raw sqlite3.connect + wal_checkpoint(PASSIVE) with no
holder guard. Under a running gateway that second connection joins the
live WAL and its close-time handling is the second-writer corruption
class #103339 tracks. Route the checkpoint through live_writer_holds_db
and skip with an actionable finding when the database is held.
[Salvage note: the original PR also flipped the repair probe's
DatabaseError branch to fail closed; that hunk is dropped here because
it refuses every header-destroyed DB (the exact class repair exists
for) — the probe's own connect raises before the EXCLUSIVE/BEGIN
statements ever run.]
DEFERRED_INDEX_SQL unconditionally DROPs and re-CREATEs the four display
triggers on every open so a changed trigger body rolls out; DROP TRIGGER IF
EXISTS on an existing trigger takes the write lock, so a settled database
still blocked behind a sibling's transaction after the three statement
gates. Compare each trigger's stored sql against the desired CREATE text and
run the pair only when they differ. CREATE ... IF NOT EXISTS forms are
lock-free on an existing object and run as written. The no-writes test now
also traces DROP TRIGGER / ALTER.
Every read-write SessionDB open issued three writes that usually change
nothing, and a write statement takes the database write lock even when it
matches no rows:
- _ensure_db_file_generation's INSERT OR IGNORE into state_meta. The stamp
is minted once per FILE, so every open after the first inserted nothing.
- the NULL-`active` heal, UPDATE messages SET active = 1 WHERE active IS
NULL, which matches nothing on a healthy database.
- the fts_storage_version stamp, which re-wrote the same value on every
open of an already-optimized database.
The connection is opened with timeout=1.0, so each blocked write costs a
full busy timeout while a sibling process holds the write lock, and the
open path's patience loop can ultimately give up and raise.
Gate all three on a read. Measured on a real 99 MB state.db (239
sessions, 6470 messages) with a sibling holding the write lock: 2117-2136
ms -> 3.6-7.1 ms. On an already-optimized database the unpatched open does
not merely stall, it raises `database is locked`; patched it completes in
3.7-6.8 ms. With a sibling running 200 ms write transactions in a loop
(n=20 opens): p50 894.6 -> 9.6 ms, p90 1094.7 -> 13.9 ms. A settled
database now issues zero main-database write statements to open.
The reads cost nothing measurable: the state_meta probe is a primary-key
seek (2.0 us), the messages probe is 1.7 us on the modern NOT NULL column
(unsatisfiable constraint, short-circuited) and 0.4-0.6 us at 300k rows on
a legacy default-less column via the partial index that already exists for
exactly this predicate. An uncontended open is unchanged.
Semantics are preserved. INSERT OR IGNORE still resolves the first-opener
race inside SQLite and racers still converge on the winner's token via the
re-read; the application_id gate and the PASSIVE-only checkpoint are
untouched; the heal is still considered on every startup, as #60108
deliberately made it, with only the write now conditional on a read
proving there is something to repair.
Read-first also fixes a correctness bug. Under contention the generation
block was abandoned by its `except sqlite3.Error` handler, so a process
ended up with no generation token at all even though the value was already
on disk and a plain read would have returned it -- and that token feeds
the deleted-WAL and replaced-file guards added by #101221. The heal's
`except OperationalError: pass` likewise skipped the repair silently, so
the unconditional form did not even deliver the unconditional repair it
advertised whenever it mattered most.
The probe deliberately does not use INDEXED BY: that hint raises
OperationalError("no query solution") against the modern NOT NULL column,
and the existing handler would swallow it, disabling the repair forever.
Since 338bf9ea9a _check_via_local_git reads _github_branch_tip directly; patching _upstream_main_sha intercepted nothing, so on the CI runner the check made a live GitHub call and behind stayed None. From #107835 (banner half; the anon_auth half landed via #107822).
Under gateway.multiplex_profiles, os.environ holds the DEFAULT profile's .env. Several
adapter-owned authorization gates still read GATEWAY_ALLOW_ALL_USERS, GATEWAY_ALLOWED_USERS
or their platform allowlist/allow-all raw from os.environ, so the default profile opting
into open access opened every secondary email/QQ/WhatsApp/Matrix/Teams/Slack/LINE/DingTalk
bot to any sender (email additionally skipped From: authentication), the default's Matrix
allowlist decided who may approve tool calls on a secondary bot, and a secondary that
opted in only in its own .env was silently deny-all.
Every such read now goes through the adapter's existing module-local scoped reader
(gateway.platforms._shared.get_scoped_secret / matrix _startup_env_secret): profile
scope first, scoped miss = default, never os.environ; the unscoped default-profile and
single-profile paths keep the environ read, where it IS the profile's own value.
Sites: email _allow_all_senders/_allowlist_in_effect; qqbot _open_dm_opted_in;
whatsapp_common _open_dm_opted_in/_live_dm_allow_from; teams _card_action_denied;
matrix _is_authorized_user, MATRIX_ALLOWED_USERS, MATRIX_IGNORE_USER_PATTERNS,
_extra_csv_set (allowed/free-response rooms); slack _slack_allow_bots/_slack_api_human_users;
line _truthy_env/allowlist (allow-all, user/group/room allowlists); dingtalk _extra_get
(allowed_users/chats, free-response chats, require_mention).
Live repro (temp HERMES_HOME, multiplex on, default env GATEWAY_ALLOW_ALL_USERS=true,
secondary scope without opt-in): EmailAdapter._allow_all_senders() True -> False,
QQAdapter._open_dm_opted_in() True -> False, Matrix _is_authorized_user('@stranger')
True -> False, Teams card action allowed -> denied.
Co-authored-by: Drexuxux <drexux0@gmail.com>
Co-authored-by: MoonsvnLyn <FirmamentalSpring@users.noreply.github.com>
Co-authored-by: svector-anu <anuoluwakolapo94@gmail.com>
Co-authored-by: babatorik <durgun.ismail@gmail.com>
Co-authored-by: salch-cred <salch-cred@users.noreply.github.com>
A bare `astra: 0.85` in compression.model_thresholds was written for the Codex
OAuth route, where Astra is capped at 272K and 50% would compact at ~136K. The
key is substring-matched on the model name alone, so it also fired on
openai/gpt-6-astra via OpenRouter and Nous, where the window is 1.1M: the user's
0.5 global threshold was silently replaced by 0.85 and the session sat at 620K
(~59%) without compacting.
Keys may now carry a provider prefix: `"openai-codex:astra": 0.85` applies only
when the session's provider is openai-codex; bare keys keep their route-agnostic
behaviour. Ranking is by model-substring length with scope as the tie-break, so
`astra-900k` still outranks `openai-codex:astra` for the 900K picker. The
provider flows through ContextCompressor (ctor + update_model), the ContextEngine
base class and the TUI hot-reload path, so a /model switch between routes
re-scopes the override.
- _git_run(network=True) now carries a 300s timeout; a dead-stalled fetch
(HTTP/2 to GitHub on some networks, black-holed proxy) becomes a failed run
whose stderr names the stall instead of an update pinned on
'Fetching updates...' forever (#93759, #95777). Local git stays unbounded.
- The apply path prunes stale .git/shallow grafts alongside its existing
lock/tmp_pack cleanup, so installs that already accumulated grafts from
past depth-1 checks (#105951: 57 entries) heal on their next update, not
only on --check.
Every 'git fetch --depth 1' in 'hermes update --check' (and the past
banner passive checks, before #107648 moved them to the GitHub API)
appends the fetched tip to .git/shallow as a new graft and git never
removes the previous one, so a long-lived shallow installer checkout
accumulates one graft per check (57 observed). The stale grafts break
merge-base and push 'hermes update' into the orphan-divergence reset
path with a rescue ref on every run.
prune_stale_shallow_grafts() now runs after each successful depth-1
fetch in 'hermes update --check' and clears the grafts already
accumulated by past checks: it keeps only the boundaries still
protecting referenced tips (HEAD, FETCH_HEAD, every ref tip) and
atomically rewrites .git/shallow, restoring the original file if the
trimmed set breaks history walking. The dropped commits are already
unreachable; their objects are left for git gc.
Rebased onto main after #107648: the banner.py hook is dropped (the
passive check no longer git-fetches); the update --check prune and the
cleanup of already-accumulated grafts are kept.
(cherry picked from commit 6174837fc5b9f4cc3d4d46dc1b2d9a2f6b83c120)
* feat(wisdom): add trusted publish and install foundation
* feat(wisdom): add private contribution loop
* feat(wisdom): add managed consumption workflows
* fix(wisdom): close cross-repository safety gaps
* fix(wisdom): align local package and lifecycle policy
* fix(wisdom): require explicit profile setup
* docs(wisdom): repin reconciled gateway head
* fix(wisdom): fence content downloads and approval receipts
* docs(wisdom): record generation-fenced downloads
* docs(wisdom): record unified delivery PR
* fix(ci): stop passing invalid classifier inputs
* docs(wisdom): remove internal requirements ledger
* feat(wisdom): localize dashboard and desktop copy
* feat(wisdom): complete local contribution and consumption UX
* style(wisdom): satisfy desktop lint
* chore(wisdom): refresh requirements pin
* test(dashboard): allow formatted profile copy
* test(wisdom): stabilize desktop interaction coverage
* fix(wisdom): surface dashboard action failures
* fix(wisdom): add repeatable Portal demo login
* feat(wisdom): add actionable skill notifications
* feat(wisdom): add notification install and update actions
* fix(wisdom): make Telegram skill alerts actionable
* fix(wisdom): always refresh demo Agent login
* feat(wisdom): embed Telegram notification actions
* fix(wisdom): preserve Telegram notifications after actions
* fix(wisdom): keep Telegram notification cards readable
* feat(wisdom): add Telegram candidate approval flow
* feat(wisdom): explain Telegram qualification reasons
* fix(wisdom): reconcile cross-surface candidate actions
* feat(telegram): add Collective Wisdom management command
* chore(wisdom): refresh Gateway contract pin
* chore(wisdom): advance Gateway contract pin
* feat(wisdom): align command UX across clients
* feat(slack): add Collective Wisdom management parity
* feat(wisdom): add security and professionalism reviews
* feat(wisdom): add first-time qualification guidance
* feat(wisdom): simplify qualification sharing choices
* feat(skills): add optional editorial metadata
* feat(wisdom): enrich legacy skill presentation
* fix(wisdom): harden review and update boundaries
* fix(wisdom): emit canonical review timestamps
* fix(wisdom): align with merged gateway and main
* wisdom: add agent-led sharing core (policy, evidence, schemas, templates, delivery, weekly job, share/install flows)
- hermes_wisdom/agent_led/: policy resolution (server > local > defaults),
7-day evidence builder that excludes bundled/hub/managed skills and
dismissed/handled/recently-suggested content hashes, strict pydantic
schemas for agent output with repair-or-reject, fixed copy templates
(Share / Teammate / Published / Update / Mute), idempotent retried
delivery ledger with stale-action resolution, weekly review job,
resumable Share and Install flows.
- prompts/: candidate review, recipient recommendation, share packaging.
- tests/wisdom/test_agent_led.py: 30 tests.
* wisdom: agent-led renderers and button action dispatcher
- render.py: Telegram HTML, Slack blocks, Desktop payload; editorial name
is the emphasized line, product label stays separate.
- actions.py: resolve opaque wa:<action>:<dedup> targets via the delivery
ledger; Not now -> dismissal, Mute -> fixed options, Share -> resumable
packaging flow, Install/Update -> plan command. Never publishes/installs.
* wisdom: CLI verbs, agent_led config default, conversational catalog skill
- hermes wisdom browse/review-week/act/share/dismiss/mute (all --json).
- wisdom.agent_led config block, default enabled.
- SKILL.md rewritten so natural-language catalog questions map to the CLI
verbs, share/install flows and fixed notification templates.
* wisdom: wire agent-led weekly review into gateway tick and Telegram buttons
- gateway housekeeping tick calls maybe_run_weekly_review with a home
channel sender when a Telegram adapter is available.
- Telegram: wa: callbacks resolved through the ledger (stale-safe), mute
duration keyboard, send_wisdom_agent_recommendation rich card + fallback.
* fix(wisdom): integrate local mediation and harden model and setup boundaries
* fix(wisdom): honor authoritative recommendation policy and defer on failure
* fix(wisdom): synchronize opaque suppression and recheck delivery preferences
* feat(wisdom): route weekly selection through the session-owned assessment queue
* fix(wisdom): prepare and submit the reviewed generated share package
* feat(wisdom): separate native Share preparation from publication consent
* feat(wisdom): sync native mute choices through a leased preference outbox
* feat(wisdom): bind native mute controls to durable preference choices
* feat(wisdom): add scoped desktop and dashboard notification settings
* fix(wisdom): revalidate feed recommendations before assessment and delivery
* fix(wisdom): persist validated delivery receipts before completing notices
* feat(wisdom): add private notification claim and receipt client
* Persist Wisdom send reservations and recover delivery acknowledgements
* Route legacy Wisdom controls through current native review
* Add typed private Wisdom operation outcome client
* fix(wisdom): make agent-led advice usable in the local demo
* fix(wisdom): keep requested consent outside proactive limits
* fix(wisdom): distinguish unavailable assessments and preserve digest text
* fix(wisdom): assess ongoing usefulness beyond the current task
* fix(wisdom): restore immediate qualification sharing controls
* fix(wisdom): separate qualification review from installation advice
* fix(wisdom): collapse review checklists and simplify sharing copy
* fix(wisdom): show compact sharing progress and publication receipts
* fix(wisdom): require credential prefixes rather than matching skill names
* fix(wisdom): finish package checks before presenting sharing consent
* fix(wisdom): scan local skills before qualification cards
* fix(wisdom): update moderation results on existing sharing cards
* fix(wisdom): keep sharing review accessible from receipt cards
* fix(wisdom): align mediated review cards and collapsible checks
* fix(wisdom): clarify clean security summary wording
* fix(wisdom): normalize consent plans and add explicit recheck
* fix(wisdom): keep install and update receipts concise
* fix(wisdom): collapse assessments and deduplicate operation cards
* fix(wisdom): restore private Portal review from native cards
* fix(wisdom): sync Portal publication to original consent card
* fix(wisdom): show local skill version on sharing cards
* fix(wisdom): skip agent recommendations for self-published versions
* fix(wisdom): simplify candidate notices and local-edit recovery copy
* feat(wisdom): submit locally reviewed packages with one confirmation
* feat(wisdom): expose safe receipt and outcome sync recovery
* wisdom: onboarding notice says detect and share, names the user's own skill
Copy review from the product owner on the first and returning
qualification notices (fixed delivery mode):
- the feature blurb now says the org enabled detection *and sharing*
- both notices say the detected skill is one the user created
- both close with an exclamation mark
Applied identically to hermes_wisdom.notice, the desktop and web i18n
strings, and the tests that assert the sentences.
* wisdom: one opener, no approval line, ask to share after the skill is shown
Product owner review of the candidate card.
- The Hermes written card now opens with the same sentence as the fixed card
("Your organisation has enabled Collective Wisdom, a feature designed to
automatically detect and share useful skills across all team members.")
instead of its own blurb, so there is one first time message.
- "Nothing is shared without your approval." removed from Telegram, Slack
and Desktop. The buttons already make the permission explicit.
- "Would you like to share?" no longer appears before the skill is named.
It is now the last line, after the skill name, description, why suggested
and the checks, and reads "Would you like to share it?" (matching the
agent led template wording).
Tests updated for the new order; proposalNotice removed from all desktop locales.
* wisdom: American spelling, organization
Product owner decision: user facing copy uses American spelling.
Changes "Your organisation" to "Your organization" in the chat notice,
the Hermes written card opener, the desktop and web strings, and the
tests that assert them. Identifiers such as nas_organisation:* and the
German and French locales are untouched.
* wisdom: candidate card copy round 4 (owner review)
Apply the product owner's round 4 copy decisions to the Hermes Collective
Wisdom candidate card on Telegram, Slack, Desktop and the shared views:
1. Hermes-written cards are titled "Hermes Collective Wisdom" instead of
the bare "Collective Wisdom".
2. The "Reusable skill ready to review" line is gone from the candidate
card (Telegram rich card and plain fallback, legacy agent-led share
template).
3. The skill name and description are labelled: "Skill name: <name>" and
"What it does: <description>" (Telegram, Slack, Desktop).
4. "Why suggested:" is now "Why others might benefit:".
5. A passing professionalism review reads "Safe to share at work ✓ (no
inappropriate content found)" with no per-check bullets and no "Pass";
a failed review reads "Needs a look before sharing at work (possible
inappropriate content)" and lists only the checks that flagged
something. Pending/unavailable wording is unchanged.
6. Telegram button toasts: "Will ask later...", "Preparing more
details...", "Sharing...".
7. Qualification reasons: "You used this skill consistently across many
days." and "You've really refined this skill."
8. prompts/wisdom_candidate_review.md asks for a compelling
editorial_name, a simple one_line_description and a compelling
why_coworkers_benefit under 300 characters; "Be concise and
convincing." becomes "Be concise and compelling: the goal is that the
user wants to share it."
Tests updated for the new strings; review_text() gains direct coverage.
* wisdom: re-apply owner copy after rebase
- Native share cards (advice_view/interaction_view): drop the approval line, ask "Would you like to share it?" as the last line after the checks
- Hermes-written completion card titled "Hermes Collective Wisdom"
- Qualification reasons use the owner wording (consistently across many days / really refined)
- American spelling (organization) in remaining English copy
- Desktop test asserts the current Share button; web test matches the returning notice
* fix(wisdom): pin reconciled Gateway and verify Unicode hash vectors
Pin Gateway 60cd2d6b613ae3cd4a6e65155d1142006d907e78 and byte-identical producer artifacts. Verify every content-order case and package-manifest binding. Validation: 186 focused Python tests, Ruff and contract verifier.
* fix(wisdom): reconcile optional SDK tests and frontend lint
* fix(wisdom): default to agent-written notification summaries
* fix(wisdom): restore deferred install review and browse controls
* feat(wisdom): inspect installed setup with exact package provenance
* feat(wisdom): run native-approved installed setup steps with durable evidence
* fix(wisdom): recover interrupted setup with explicit native consent
* feat(wisdom): hand native installs into guided setup review
* fix(wisdom): continue requested setup with fixed notification copy
* fix(wisdom): preserve setup while waiting for a session model
* fix(wisdom): expose canonical setup review controls on desktop
* fix(wisdom): resume setup after recorded automatic updates
* fix(wisdom): make missing setup prerequisites recheckable
* chore(wisdom): align Agent with verified Gateway contract
* fix(wisdom): stop guessing team slugs in portal links
* fix(wisdom): retire pending advice on account sign-out
* fix(wisdom): cancel advice after terminal account revocation
* fix(wisdom): fence feed responses across account sign-out
* fix(wisdom): checkpoint signed-out feed before reactivation
* fix(wisdom): link proactive advice to scoped notification settings
* fix(wisdom): coalesce queued publication recommendations by version
* fix(wisdom): keep package review navigation local and deferable
* fix(wisdom): reflect installed state in discovery controls
* fix(wisdom): show exact checks before command confirmation
* chore(wisdom): pin bounded analytics privacy contract
* chore(wisdom): pin retired legacy notification contract
* feat(wisdom): review publisher usage with exact sharing copy
* fix(wisdom): align discovery and review check summaries
* fix(wisdom): show expired consent before confirmation
* fix(wisdom): require fresh review for legacy install controls
* fix(wisdom): preserve review expiry across check toggles
* fix(wisdom): retain update policy in native install reviews
* fix(wisdom): surface failed native card edits
* fix(wisdom): persist local command approval reviews
* fix(wisdom): use saved approvals for messaging commands
* test(wisdom): provide scan result in setup handoff fixture
* test(wisdom): exercise Telegram approvals with saved review state
* fix(wisdom): retain suppression policy for offline deferral
* fix(wisdom): reconsider candidates after deferred suppression expires
* fix(wisdom): bind review checks and report verified readiness separately
* fix(wisdom): persist accepted publication intent and recover exact outcomes
* fix(sync): pin UTF-8 tree ordering across writers
* chore(wisdom): pin organisation-scoped Gateway authorization
* fix(wisdom): restrict consent delivery to user-facing sessions
* chore(wisdom): refresh reviewed Gateway contract pin
* fix(wisdom): preserve kept tools in Blank Slate exclusions
* test(auth): reset anonymous fixture with a profile-scoped cache
* fix(wisdom): gate local surfaces and work on current profile entitlement
* fix(wisdom): invalidate quiet tool cache on entitlement changes
* test(wisdom): authorize local consent gateway fixtures
* fix(wisdom): keep entitlement decoding free of native crypto imports
* test(wisdom): provide local entitlement to demo CLI subprocess
* ci: leave upstream workflow unchanged in Wisdom PR
* fix(wisdom): ship package and contracts in Nix wheels
---------
Co-authored-by: hbizi <36184542+hbizi@users.noreply.github.com>
bedrock.guardrail was only attached on the Converse route (guardrailConfig in the
body). Claude on Bedrock goes through the AnthropicBedrock SDK, i.e. InvokeModel,
whose body has no guardrailConfig, so the default Claude route ran with no guardrail
at all (#52179; live-verified by JiaDe-Wu: the blocked word came back through Hermes).
Bedrock reads the guardrail for InvokeModel from X-Amzn-Bedrock-GuardrailIdentifier /
-GuardrailVersion / -Trace headers. Attach them as default_headers in
build_anthropic_bedrock_client so every AnthropicBedrock client Hermes builds
(primary init, /model switch, fallback, per-request rebuild, auxiliary) enforces the
same guardrail, with prompt caching / thinking / 1M context kept (the reason Claude is
not routed through Converse).
InvokeModel blocks do NOT change stop_reason (stays end_turn) and return the guardrail's
canned text as an ordinary assistant reply, flagged only by
amazon-bedrock-guardrailAction=INTERVENED in the body (SDK: response.model_extra).
AnthropicTransport.response_finish_reason maps that to content_filter so the loop runs
its refusal handling instead of reasoning over the canned text; _derive_finish_reason
uses it for the anthropic_messages branch.
Mantle (openai.gpt-5.x) is documented by AWS as not supporting Guardrails on the
Responses endpoint; the docs now say so instead of promising "all model invocations".
Header mechanism proposed in #52312 by @JoaoMarcos44 (stale base, 7-file conflict,
detection keyed on a Converse-only stopReason); reimplemented on current main.
Live probe (local sink, SigV4 fake creds): before, no X-Amzn-Bedrock-* header on the
InvokeModel request; after, headers present, SigV4 intact, INTERVENED → content_filter.
A custom HERMES_HOME (outside the profiles tree) reported `profile: null`,
so the tail entry landed under profile '' while the session's owner hint —
built from list rows that _serving_profile() stamps "default" — looked up
'default'. Two identities for one backend; the exact-key lookup missed and
"Show earlier" stayed hidden for the Desktop's own sandboxed and
HERMES_HOME-overridden installs (electron/main.ts resolveHermesHome).
The messages endpoint now returns the same _serving_profile() stamp the
list rows carry, so the Desktop keys a page under the owner it already
routes the session by; the inline resolver and its function-body import go
away. On the renderer, the ambient profile used for backends that predate
the field is captured at request time alongside the connection, so a
profile switch mid-read cannot re-key the page.
The SDK-private _build_headers probe was spelled three times across two files; the api-key shard also re-asserted the bearer invariant the portal test owns. dict(headers or {}) → dict(headers): every caller passes _beta_header's dict.
The bearer guard is now an Omit() default header (copy-safe), so the SDK
attribute may still hold the env key while nothing reaches the wire. Assert
on _build_headers for the client and a with_options() copy instead.
The api-key branch now uses an Omit() default header because an attribute
clear does not survive with_options(); the mirror bearer branch still relied
on `client.api_key = None`. Probe on anthropic 0.87.0: a with_options() copy
of a bearer client re-read ANTHROPIC_API_KEY and sent x-api-key alongside
the Bearer (#26970's dual-auth leak, on copies). Both branches now set one
Omit() header, built once from the beta headers. Wire test asserts the
Authorization header is absent outright, not merely sentinel-free.
The pinned anthropic==0.87.0 exports `Omit` at package level, so the
import-probe plus httpx header-stripping fallback added for "SDK too old"
never runs; drop both and set the default header directly. Tests trimmed
to two invariants: the header-builder contract on the client and a
with_options() copy, and the wire-level end-to-end through
build_anthropic_client. The bearer-style mirror case stays covered.
The auth-boundary group (env bearer isolation, fail-closed Omit
fallback, wire-level header captures) moves to
test_anthropic_client_auth.py: the main adapter suite was pushed past
the 2,000-line ceiling by the group, and the shard keeps every test —
including both local HTTP round-trips — with explicit imports and a
shared capturing-server fixture. Both suites run together; coverage
is unchanged.
The api-key credential-isolation guard in this PR only removes the
env-derived Bearer when `anthropic._types.Omit` can be imported. When the
sentinel is unavailable (older/exotic SDK layout), `_new_sdk_client` fell
through to a bare api-key client whose SDK env fallback re-reads
ANTHROPIC_AUTH_TOKEN and ships `Authorization: Bearer ***` to third-party
endpoints — the compatibility path failed open (P2, reported by @egilewski).
Fail closed instead: when Omit is unavailable, build the client with a
copy-safe httpx request hook that strips Authorization on every request.
`http_client` propagates through `with_options()`/`copy()`, so the original
client and every copy are covered without depending on the SDK's
header-omission internals — the same custom-client shape already used by
`_build_anthropic_client_with_bearer_hook`.
Adds a real-loopback e2e test that simulates Omit unavailable and asserts
no Bearer leak on the original client and on a `with_options()` copy, while
x-api-key and request success are preserved.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Anthropic SDK fills an unset auth_token from ANTHROPIC_AUTH_TOKEN and sends
it as a Bearer credential alongside x-api-key to third-party
Anthropic-compatible endpoints. Mirror the existing bearer-side guard in
_new_sdk_client so api-key-style construction clears auth_token after
construction, and cover it with regression tests (client attributes, header
shape, and an end-to-end local-server capture).
The inner ProcessLookupError handler around the marker probe made the outer one reachable only through an injected pid_exists that raises (gateway.status._pid_exists never does). Keep the single mapping; the degrade-to-liveness fixture no longer models a stderr the probe now classifies as a missing process.
The stderr sniff also matched "not found", which BSD ps prints for an
unsupported column ("ps: lstart: keyword not found", rc=1, verified on
macOS). That would have classified a healthy parent as dead and os._exit'd
the backend — the fail-unsafe direction the watchdog must never take. Keep
the explicit missing-process message only; the macos_only test now pins the
"keyword not found" case as a plain OSError. The standalone
ProcessLookupError test (already green on main) folds into the degrade test.
