* fix(security): deny generated-image access when ownership verification fails
The except Exception block in serve_generated_image catches all
exceptions during ownership verification and falls through to serve
the file anyway. If the database is down or corrupted, the ownership
check is bypassed entirely — any authenticated user can download any
generated image by guessing the content-hash filename.
Raise HTTP 503 (Service Unavailable) instead of falling through,
so the endpoint fails closed when verification is impossible. This
matches the defense-in-depth principle: deny access on verification
errors rather than granting it.
* fix(security): enforce fail-closed ownership and secure caching for generated images
- Fail closed on missing gallery records, null/empty owners, and DB errors
- Support both cookie session and bearer API token owners via effective_user
- Add in-memory registry for freshly generated images to preserve access
- Eliminate file existence oracle by verifying ownership before disk probing
- Update Cache-Control to private, no-cache, must-revalidate
- Pass owner attribution through tool execution and image MCP server
- Add comprehensive hermetic regression tests for ownership gates and caching
* fix(security): sanitize tool owner arguments and drop unneeded MCP env fallback
- Remove redundant and unsafe ODYSSEUS_MCP_IMAGE_OWNER fallback in image_gen_server.py to fix 4 tests in test_env_reference.py.
- Sanitize caller-supplied tool arguments across all MCP and email tool dispatch paths in src/tool_execution.py: strip untrusted _odysseus_* keys from arguments.
- Only inject _odysseus_owner when verified trusted server context is present, preventing untrusted/anonymous users from spoofing ownership claims.
- Sanitize empty/whitespace owner strings in image_gen_server.py to None.
- Add comprehensive regression tests in test_generated_image_ownership.py for argument sanitization, owner injection, fallback propagation, and server sanitization.
---------
Co-authored-by: isharak7m <192635824+isharak7m@users.noreply.github.com>
Co-authored-by: PR #6166 Reviewer <reviewer@odysseus-review.local>
Skills tagged remote-only in frontmatter are excluded from the injected
skill index when the active model's endpoint is local (loopback/private/
tailscale per is_local_endpoint). Big on-demand reference lookups
overwhelm small local contexts; local models never see the skill, while
remote models and API/UI listings are unaffected.
- SkillsManager.index_for gains optional keyword-only local_model flag
(None = don't gate, same contract as active_toolsets=None)
- _build_system_prompt/_build_base_prompt thread endpoint_url from
_build_route_request_state; unknown endpoint fails open
- tests: cover hidden-on-local, visible-on-remote/unknown, untagged
skills never gated
Refs: discussed for the local-model overwhelm problem
Co-authored-by: Alexandre Teixeira <111787685+alteixeira20@users.noreply.github.com>
With Auto-approve OFF the agent loop asked get_relevant_skills for
min_confidence=2.0, meant as 'published only'. The gate applies the
confidence check to published skills too, and confidence is 0-1, so no
user skill was ever injected, published or not. The explicit-activation
path already treats OFF as status == published.
Add a published_only flag to get_relevant_skills and pass it from both
callers that used the sentinel (relevance injection and the skill
preflight). Auto-approve ON is unchanged: a skill still needs a passing
audit and the confidence threshold.
Fixes#6634
* feat(settings): opt-in reasoning effort for utility model calls
Add utility_reasoning_effort (empty = provider default) and let utility
calls inherit a chat session's effort only on that session's matching
endpoint+model route. Explicit caller effort wins; otherwise the utility
setting wins over session inheritance on utility-chain routes. Resolve
the chain and setting per user and validate levels against model evidence.
No-session work uses the setting only, with no chat-effort crossover.
- src/utility_effort.py owns effort_for_call and candidate_effort_factory
- remove global effort fill from llm_call/llm_call_async; utility call
sites pass effort explicitly, so unrelated calls on the same route do
not pick it up
- wire auto-title, memory/persona/skill extraction, memory suggest/import/
audit, compaction, auto-sort, and per-owner background task candidates
- wire no-session email writing-style, summary, and translation calls,
plus skills evaluation, necessity/retrieval audits, and improvement
- deliberately exclude email replies because thinking_mode='off'
- add the optional candidate_request_factory to llm_call_async_with_fallback
- add sync llm_call reasoning_effort and include it in the cache key
- show the Utility Model effort selector only for advertised levels
Fixes#6569
* fix(utility): exclude email replies and support inherited effort in settings
Pass reasoning_effort='' to task_llm_call_async for scheduled reply drafting to honor the email reply exclusion. In AI settings, resolve the effective Default Chat endpoint and model when Utility is set to 'Same as chat' so supported reasoning effort levels can be selected.
* feat(utility): support same-as-chat effort and session model fallback in compaction
In AI settings, show 'Same as chat' as the default effort option when Utility Model is inherited, and support an explicit 'Provider default' (off) override. Pass the active session fallback in context compaction callers so compaction shares the live chat session's model and reasoning effort for maximum prompt/KV cache affinity.
* fix(settings): clarify chat effort inheritance and keep option visible
Label inherited effort as 'Same as chat (when supported)' and mention
cache affinity and latency speedups in the help text. Ensure the effort
control remains visible when the utility model is set to 'Same as chat'
even if the default chat model lacks advertised reasoning levels, and
populate candidate levels across configured endpoints so the user can
configure effort or keep provider default.
* feat(settings): per-fallback reasoning effort for utility model
Each utility fallback row gets an Effort select, shown only when the
selected model advertises reasoning levels. The choice is stored as
reasoning_effort on the utility_model_fallbacks entry and sent only to
that candidate; an empty value means provider default.
* fix(utility): transmit reasoning effort in non-streaming calls
---------
Co-authored-by: Alexandre Teixeira <111787685+alteixeira20@users.noreply.github.com>
ToolApprovalStore.create() sealed a process identity only from the request
authority's launch scopes, which exist only for granted bash/python. For an
ungranted call the sealing failed silently, so the approval was created
without a process identity and the executor always refused it ("Approved
action has no sealed process/job identity"). When the authority is not
inherited and has no launch scope for the backend, seal one in the
request's single workspace root at approval time, as filesystem approvals
already do. Inherited authorities still cannot widen.
The skill test run and audit arm left their `async for` over
stream_agent_loop early when an approval was needed, without closing the
generator. asyncio closed it later from another task, so its ContextVar
resets raised "Token ... was created in a different Context". Close the
stream with aclosing, like the scheduler and teacher escalation do.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: add Notes and Todos as agent chat context
- Send selected Note/Todo IDs from the Notes UI
- Load selected notes with owner scoping in chat routes
- Format note content and checklist items for the model
- Inject selected notes as untrusted chat context
- Add a selected-context indicator beside Shell Access
- Keep selected context associated with the active chat session
* Improved selected notes context handling and discouragin redundant note lookup and permission requests
* Fix selected notes UI when switching chats
* fix(notes): harden selected context lifecycle and validation
---------
Co-authored-by: Alexandre Teixeira <111787685+alteixeira20@users.noreply.github.com>
The #6503 merge added _control_plane_path() to _is_denied_tool_path(),
which grep, glob and ls call per enumerated entry. Without a snapshot
argument every call rebuilt _control_plane_snapshot() and stat'ed every
protected state file again. A 5,000-file grep went from 0.75 s to ~7 s,
and around 20k files it hits the grep timeout.
Thread an optional snapshot through _is_denied_tool_path() and
_can_traverse_tool_path(), and build it once per scan, the way
process_resources already does for its launch-boundary walk. Root
resolution and bound-resource resolution still observe fresh state.
The compact preview reduces every pre-execution tool error to a fixed
allowlist so exception text cannot reach the client. Messages our own
validators build per call are not on that list, so the model got "The
tool call could not be validated..." instead of the pdf_extract path
hint, the email uid provenance error, the artifact-Python target
message, or which schema argument was wrong. That is the default path
for the tool-profile models, Qwen3.5-9B included.
Each validator site now records its message in a per-call
validator_error before raising, and only that text is returned
verbatim. A schema failure gets a hint rebuilt from the offered schema
and the call's own arguments (missing property, expected type, allowed
values), never from the caught ValidationError. Everything else,
including all execution failures, still goes through
_public_preview_tool_error.
Request authority admits whole tool families from the user's request, so a
request to read email also admits send_email, delete_email and bulk_email,
and agent processes inherit the host network. With the gate defaulting to
off, an instruction injected through an email or a fetched page reaches those
tools with no other check; dev refuses them today.
Default the gate on, keep ODYSSEUS_TOOL_APPROVAL_GATE=0 as the opt-out, and
pin the production default with a test that imports the module in a fresh
interpreter. Four routing tests written for the opt-out posture now set it
explicitly.
Require caller-supplied model endpoints to resolve through enabled owner-visible registrations, harden session path encoding, and remove the SVG title HTML parsing sink.
Integrates the merged and frozen Wave 3 lab commit
b1666951faf8285054e1ca90f11533b0fb53fb57 with a normal merge, preserving
every Wave 4 commit unchanged.
Conflict: src/agent_runtime/resources.py. Wave 3's _control_plane_snapshot()
/ _control_plane_path(path, *, snapshot=None) split is kept. The snapshot adds
the effect-store directories to its prefix set after the recursive job-dir
inventory and no longer references path (the auto-merged prefix check would
have raised NameError there). _control_plane_path calls _aliases_effect_store
after its os.stat, only for multiply linked files, so single-link files never
list the store.
Semantic reconciliation (no textual conflict): bg_monitor keeps launch
settlement right after the first successful validate_job and before the
authority check, with Wave 3's post-drain revalidation intact. The
deleted-session branch, terminal before linkage validation, now settles a
validated launch too: that job is later pruned and its publication retired,
which would otherwise leave its effect RUNNING. Regression tests cover the
snapshot form of the effect-store check and both deleted-session linkage
outcomes.
A hardlink into the effect store was protected only by the log's own nlink
refusal, which an agent could undo by removing the alias after writing
through it. Adding the store to the recursive control-plane inventory would
make every path check cost grow with accumulated runs. _aliases_effect_store
instead uses the store's invariants: logs and launch indexes refuse
st_nlink != 1 and the store is flat, so only a multiply linked regular file
on the store's device is compared by inode against one non-recursive listing.
Single-link files cost nothing and the store is never rglob-inventoried. The
helper takes a stat result so it plugs into Wave 3's scan-local snapshot after
the rebase.
Effect obligations were consulted only for declared artifacts, and reported
external success could be presented as done. Now, regardless of declared
artifacts:
- the latest effect on any changed file contradicted by a fresh readback
fails the run (a superseded earlier effect is history, not a contradiction);
- a passing verifier followed by an effect that may have changed state
without settled evidence is stale (BLOCKED);
- executed external effects that are not VERIFIED cap the decision at
UNVERIFIED, and the answer always carries server-authored facts for them
("reported success; any external change it made was not independently
verified", "reported failure", "unknown outcome").
The disclosure is structural and does not depend on recognizing the model's
wording. When it is the only change, the model's answer events are released
unchanged and the disclosure follows as one delta (and in round_texts).
Prose filtering is also tightened (remote verbs are mutation claims, an
unnamed "I updated it" cannot borrow the single required artifact, bare
"Done." is a terminal claim beside unverified external effects). A passing
verifier still supports test claims; it never speaks for the external effect.
Replaces the uncommitted attempt that blocked every run with any RUNNING
effect: a background launch with no declared obligations completes
UNVERIFIED.
Result-dictionary keys could set lifecycle state for any producer: a dynamic
or registry tool returning bg_job_id/detached became RUNNING, teardown became
verified cleanup, and timed_out/failure_kind/mutation_attempted/containment
were copied from untrusted results. Facts are now scoped to the producer the
dispatcher actually bound. An unbound tool contributes its exit status alone.
RUNNING requires a bound process producer (and an exact launch reservation
for bg_job_id), cleanup is attested only by a bound process producer, and job
observations and launch settlement only by a bound manage_bg_jobs operation
on exactly one Wave 3-validated job. External/remote-acknowledged facts come
from the captured ExternalResource, not from the result.
Sequence positions were allocated from each EffectLog object's in-memory
counter, so two objects, threads or processes could reuse a position or
settle one effect twice; replay then failed closed for the whole log. Every
append now takes an exclusive flock, merges the durable records other writers
appended (truncating a torn tail a crashed writer left), allocates from that
merged tail, rejects records the merged history makes invalid (a second
settlement, recovery of a claim another writer settled or marked running),
then appends, fsyncs and releases. history() merges others' records under a
shared lock. An incremental consistency index keeps appends O(1).
The first append of each log object fsyncs the log's directory, and every
directory created for it is fsynced in its parent, all under the lock before
the claim returns. A failed write or directory fsync truncates the record
back, so dispatch is refused and nothing unacknowledged is later merged. The
launch index writes and fsyncs a temp file, replaces it, then fsyncs the
directory. flock and directory fsync are POSIX-only and not claimed
elsewhere.
edit_file and apply_patch update claims asserted only existence (or, in the
uncommitted corrective attempt, any content change), so an unrelated write
could verify them. Each filesystem postcondition is now the exact content the
producer's own transformation writes from the identity-checked pre-state:
edit_file through the extracted pure _edit_file_text (no newline
translation), apply_patch updates through _apply_patch_hunks on the
universal-newline pre-state. An oversized, replaced or undecodable pre-state,
a non-matching hunk, or an underivable write_file body leaves the whole claim
without postconditions (UNVERIFIED) instead of letting derivable targets
verify the operation or falling back to existence.
Only the native detached launch (bg_job_id) or a bridge's explicit detachment
marks an operation's own work as RUNNING. A listing that reports some other
download/model/job as running settled normally; treating it as running left
the claim pending forever and could block required artifacts.
EffectHistory now indexes outcomes per effect once, removing a cubic scan in
assessment over long run lineages.
Adds adversarial coverage: browser page operations stay fail-closed through
the real dispatcher with effects enabled (no claim, never dispatched),
scheduler task triggers stay unverified admission, and assessment scales.
The background monitor already validates the exact Wave 3 job linkage
(job_from_record + validate_job) before continuing a session. At that point it
now records the job's settlement against the durable launch claim through the
launch-generation index, using typed lifecycle facts from the server-owned
record. Settlement is idempotent across deferred retries, is execution
evidence only, and never reads the delivered output: the injected report stays
attributed content. Failure to record leaves the claim running/unknown and
never blocks the follow-up.
Dispatcher seam: mark_dispatch, which runs inside the live Wave 3 binding
scope immediately before backend invocation, now durably claims a possible
effect before execution_id is assigned. If the claim cannot be persisted the
action stays undispatched and the dispatcher returns BLOCKED; dispatched()
closes the never-awaited coroutine. record_action appends the outcome
(including cancellation/interruption) and admitted-read observations before
the receipt reduction drops producer facts.
Adapters consume only the bound operations the dispatcher admitted:
filesystem bindings give exact scope and predicates (write_file content digest
after fence unwrapping, apply_patch add/delete, edit existence); bash/python
launches have unknown scope with the launch generation as lineage; job kills
scope the exact job and its processes; owned operations scope their exact
revisioned records; external backends are claimed as external and never
verified by acknowledgement; browser session_info yields session lifecycle
observations only, and a page binding is never effect scope. Complete
read_file re-reads the exact bound source to digest it; offset/limit,
truncation, extraction and listings are partial. Background launches stay
RUNNING until an admitted read of the exact job generation (via a durable
launch index, across continuation runs) reports settlement.
Producer seams: typed job lifecycle facts on manage_bg_jobs reads/kills, a
structured timed_out flag on containment timeouts, and mutation_attempted on
in-place write_file/edit_file failures after truncation.
Completion: the existing EvidenceLedger consumes effect assessments through a
single helper used for the decision, ask_user and prose filtering. A required
artifact is unsettled by a later unresolved effect that may have touched it,
a fresh contradicting readback fails the decision, and partial reads no longer
count as artifact validation. Ordinary conversation and read-only turns are
unchanged; no second completion policy is introduced.
Claims are fsynced to a per-lineage JSONL log before a caller may invoke a
backend; a persistence failure raises EffectPersistenceError (a
ResourceIdentityError) so dispatch fails closed. Outcomes and observations are
appended; nothing is rewritten. Reload validates every record strictly, ignores
only a torn final write, and fails closed on corruption, forgery or hardlink
aliasing. recover_interrupted appends INTERRUPTED/possible-impact outcomes for
claims that never settled and leaves RUNNING background effects alone.
The effect store is added to Wave 3 control-plane paths (prefix check only;
the log itself refuses aliased files), so filesystem tools cannot forge it.
Tests redirect the store to a session tmp directory.
Recreate (rather than cherry-pick 9012e208) the effect/provenance foundation.
The historical types used opaque string resource keys, a may_have_changed flag
defaulting to no impact, and a single status mixing execution and verification.
Claims, outcomes and observations now reference only typed Wave 3 identities
(filesystem root/inode/ancestor chain, process PID+start token, job generation,
owned revision, external incarnation, browser session incarnation). Browser
page resources are refused. Known no-op is limited to refusal before
invocation; unknown scope stays conservative; verification is derived from
fresh, complete, post-settlement readback checked against an explicit
predicate, and unknown execution with matching state is reported as observed
state without causation. Cleanup is recorded separately from effect outcome.
Replace unscrubbed os.environ inheritance with an explicit allowlist
(_SAFE_SUBPROCESS_VARS) containing only variables necessary for bash/python
execution (PATH, locale, terminal, Python virtualenv/site-packages, Windows
essentials) and regex-based credential scrubbing (_SENSITIVE_PATTERN) to
prevent provider tokens, database URLs, and API keys from leaking into child
processes.
Shutdown cleanup must not depend on active record.session capability,
which is cleared on cancellation. Guard cleanup by socket directory
presence so all owned daemons are terminated.
