When xAI's auth backend fails to redirect (e.g. the German "We couldn't reach
your app" fallback shown in #27385), users sometimes navigate manually to the
bare loopback callback URL — `http://127.0.0.1:<port>/callback` with no query
string. The handler used to return 200 "xAI authorization received" for any
GET that hit the expected path, because `parse_qs("")` yields no `code` and no
`error`, leaving `result` untouched while the success page was still served.
The CLI's wait loop, of course, still saw no code and timed out with
`AuthError: xAI authorization timed out waiting for the local callback.`
The user is left looking at a browser tab that claims success and a terminal
that says failure — exactly the contradiction in #27385.
This change makes the empty-callback case return 400 with an explicit
"not received" page and a hint to retry `hermes auth add xai-oauth`. The
wait-loop semantics are unchanged: `result["code"]` and `result["error"]`
both stay None, so the CLI still raises a real timeout rather than treating
the bare hit as a successful callback.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When xAI returns a subscription/entitlement error through an SSE
``type=error`` frame, ``_StreamErrorEvent`` is raised with
``status_code=None``. This caused ``_classify_by_status`` (step 2 of
``classify_api_error``) to be skipped entirely, and the Grok-specific
phrases ("do not have an active Grok subscription", "out of available
resources") appeared in none of the message-pattern lists. The error
fell through to ``FailoverReason.unknown (retryable=True)``, burning
``max_retries`` on every affected X Premium+ / SuperGrok user before
the agent stopped — and ``_is_entitlement_failure`` was never called
because it only fires under ``FailoverReason.auth``.
The HTTP 403 path already handled this correctly (``_classify_by_status``
returns ``auth/non-retryable`` for 403). Add an explicit pattern block
at step 1 (highest priority, before the ``status_code`` guard) so both
code paths route to ``FailoverReason.auth, retryable=False,
should_fallback=True`` — matching the 403 path exactly.
Add three regression tests in ``Fix D`` section of
``test_codex_xai_oauth_recovery.py``:
- primary "do not have an active Grok subscription" phrase
- "out of available resources" + "grok" variant
- unrelated ``_StreamErrorEvent`` must not be reclassified
xAI is a first-class provider in hermes-agent with its own credential
pool entry (XAI_API_KEY / xai-oauth). API keys follow the format
xai-<60+ alphanumeric chars> and were absent from _PREFIX_PATTERNS in
agent/redact.py.
When a key appears raw in log output, tool results, or error messages,
it passed through completely unmasked. The ENV-assignment and Bearer
header patterns catch the most common cases, but a raw token in a
stack trace or debug print had no protection.
Verified before fix:
redact_sensitive_text("using key xai-ABCD...rstu to call xAI", force=True)
# "using key xai-ABCD...rstu to call xAI" <- exposed
After fix:
# "using key xai-AB...rstu to call xAI" <- masked
Five unit tests added to TestXaiToken covering bare token masking,
env assignment, short-prefix false positive, company name false
positive, and visible prefix in masked output.
Tirith flags .app domains with a lookalike_tld finding because the TLD
"can be confused with file extensions". This is a false positive for
legitimate production APIs (e.g. api.example.app, lark.app).
Add _is_app_tld_finding() and a post-parse suppression block in
check_command_security(): if the only finding(s) on a warn verdict are
lookalike_tld entries for .app, downgrade the action to allow.
Mixed findings (e.g. .app + shortened_url) and block verdicts are
unaffected. Non-.app lookalike_tld findings (.zip, .exe, etc.) are
preserved.
Add 15 regression tests covering: .app-only suppression, mixed-finding
preservation, non-.app TLD preservation, block-verdict invariance, and
the helper's field-name and case-insensitivity behaviour.
Closes#24461
When auxiliary compression's summary generation returns None (aux model
errored, returned non-JSON, timed out, etc.) the compressor previously
still dropped every middle message between compress_start..compress_end
and replaced them with a static 'Summary generation was unavailable'
placeholder. The session kept going but the user silently lost N turns
of context for nothing.
New behavior: on summary failure, compress() aborts entirely — returns
the input messages unchanged and sets _last_compress_aborted=True. The
existing _summary_failure_cooldown_until gate (30-60s) keeps the aux
model from being burned on every turn. Auto-compress callers detect
the no-op (len(after) == len(before)) and stop looping. The chat is
'frozen' at its current size until the next /compress or /new.
Manual /compress (CLI + gateway) now passes force=True which clears
the cooldown so users can retry immediately after an auto-abort. If
the manual retry also fails, the user gets a visible warning telling
them nothing was dropped and how to retry.
- agent/context_compressor.py: compress() gains force= kwarg; failure
branch sets _last_compress_aborted and returns messages unchanged
instead of inserting placeholder.
- run_agent.py: _compress_context() detects abort, surfaces warning,
skips session-rotation entirely, returns messages unchanged.
- cli.py + gateway/run.py: manual /compress paths pass force=True.
- gateway/run.py: hygiene + /compress handlers detect _last_compress_aborted
and emit the new 'Compression aborted' warning (gateway.compress.aborted)
instead of the old 'N historical messages were removed' message.
- locales/*.yaml: new gateway.compress.aborted key in all 16 locales.
- tests: updated to assert the abort contract (messages preserved,
compression_count not incremented, abort flag set, no placeholder
leaked). New test_force_true_bypasses_failure_cooldown covers the
manual-retry path.
uv.lock drifted from pyproject.toml after the CVE bumps (#26830) and
the 0.14.0 release. The installer's hash-verified tier was failing
`uv pip sync --locked` and falling back to unlocked PyPI resolve,
producing two warnings on every fresh install.
Regen aligns the lockfile:
- aiohttp 3.13.4 -> 3.13.3 (matches messaging/slack/homeassistant/sms pin)
- anthropic 0.87.0 -> 0.86.0 (matches anthropic extra pin)
- hermes-agent 0.13.0 -> 0.14.0 (matches project version)
No behavioral changes. `uv lock --check` now passes.
xAI's /responses endpoint rejects tool schemas that contain pattern or
format JSON Schema keywords with HTTP 400. chat_completion_helpers.py
already strips these for the main-agent xAI/xai-oauth path (lines
294-302), but _CodexCompletionsAdapter.create() — used for every xAI
OAuth auxiliary call (kanban decomposer, profile describer, etc.) —
passed raw tool schemas without sanitization.
MCP tools that carry pattern/format keywords (common for string fields)
silently caused every auxiliary call over xAI OAuth to fail with an
HTTP 400, while the main agent worked fine. Parity fix: call
strip_pattern_and_format() on the tool list before converting to
Responses API format, matching the main-agent guarantee.
decompose_triage_task inlines SQL INSERTs for atomicity and intentionally
bypasses link_tasks() — which calls _would_cycle() per edge. If the LLM
emits a cyclic parent graph (e.g. A.parents=[1], B.parents=[0]) the DB
write succeeds but every involved child deadlocks in 'todo' forever:
recompute_ready() requires all parents to be done, which is impossible
when A waits for B and B waits for A.
Add a Kahn topological sort over the sibling parent indices in the
pre-validation block, before any DB writes. Mirrors the cycle-safety
guarantee that link_tasks() provides for manually linked tasks.
The dashboard SDK's <Select> is a shadcn-style popup that fires
onValueChange(value), not native onChange({target:{value}}). The file
even has a selectChangeHandler() helper at L213 documenting this:
"Older plugin code calls onChange({target:{value}}) which silently
never fires."
#24547 already fixed the bulk-reassign, workspace-kind, and new-task
parent selects. This patch covers the two OrchestrationPanel selects
introduced later in #27572 that regressed onto the same broken pattern:
- OrchestrationPanel orchestrator_profile picker
- OrchestrationPanel default_assignee picker
Users opened the popup, picked an option, and the popup closed without
firing a PUT to /orchestration — so the orchestrator profile and
default assignee dropdowns appeared totally inert.
Uses the same selectChangeHandler helper as the other working Selects
in the file for consistency.
Reported by Exaario.
Cherry-pick of @sharziki's #27022 routed Azure Foundry through
_requires_bearer_auth, which also triggered the MiniMax-specific
beta-strip in _common_betas_for_base_url — dropping the 1M-context
beta from Azure even though Azure needs it for 1M context.
Split the strip predicate: introduce _is_minimax_anthropic_endpoint
so the fine-grained-tool-streaming and context-1m strips only fire
for MiniMax hosts, leaving Azure's bearer-auth header swap intact
without losing 1M context.
Also add a regression test that asserts Azure gets Bearer auth,
the api-version query param, and the context-1m-2025-08-07 beta.
Azure AI Foundry's Anthropic-style endpoint requires
`Authorization: Bearer` instead of `x-api-key`. Add `azure.com` to
`_requires_bearer_auth()` so the existing Bearer path at line 586 fires
before the generic third-party branch sets `api_key` (x-api-key).
Fixes#26970
SDK Select fires onValueChange(value) not onChange({target:{value}}), so
all three bare onChange handlers silently received undefined from e.target.
Replace raw onChange with selectChangeHandler() — the existing helper that
wires both onValueChange and a guarded onChange — so selections register
regardless of which event the SDK Select dispatches.
Closes#24520
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The header theme picker (`ThemeSwitcher`) renders a `role="listbox"` popup
with no `max-height` or overflow. With 20+ community themes installed under
`~/.hermes/dashboard-themes/`, the list extends past the viewport and themes
at the top or bottom are unreachable — the user reports only 15 of 26 themes
visible, with no scrollbar to access the rest.
Sibling switchers (`LanguageSwitcher`, `SlashPopover`) already cap their
listboxes (`max-h-80 overflow-y-auto` / `max-h-64 overflow-y-auto`); this
just brings the theme picker into line. Scoped to the component instead of
a global `div[role="listbox"]` CSS rule so other dropdowns aren't affected.
`70dvh` matches the user's tested workaround and the `dvh` unit handles
mobile browser UI chrome correctly (unlike `vh`).
Fixes#25213.
Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor(bootstrap): consolidate ACP browser bootstrap into install.{sh,ps1}
Delete 687 lines of duplicated browser bootstrap code from
acp_adapter/bootstrap/. All browser installation now routes through
dep_ensure -> install.{sh,ps1} --ensure, using agent-browser install
for Chromium. install.sh gains ensure_browser() with macOS app-bundle
detection and per-distro guidance.
Tracking: #27826
* fix(install.sh): add --ignore-scripts to npm install for camofox
@askjo/camofox-browser has a dependency (impit) whose postinstall
script runs `npx only-allow pnpm`, which fails under npm. Adding
--ignore-scripts avoids the spurious failure without affecting
functionality.
Tracking: #27826
* fix: add explicit return in ensure_browser, narrow exception in entry.py
ensure_browser() now returns 0 explicitly on all success paths.
_run_setup_browser() catches OSError instead of broad Exception,
letting ImportError propagate as a real packaging bug.
* feat(dep_ensure): complete Windows bootstrap — dep_ensure + install.ps1 + detection
dep_ensure.py gains Windows awareness: PowerShell invocation, platform-
specific browser detection, (path, shell) tuple returns.
install.ps1 gains -Ensure/-PostInstall modes using npm -g --prefix
(aligned with install.sh) and agent-browser install for Chromium.
browser_tool.py gains node/ in candidate dirs for Windows .cmd shims.
Both install scripts bundled in pip wheel.
Tracking: #27826
* fix(install.ps1): add --ignore-scripts to npm install for camofox
@askjo/camofox-browser has a dependency (impit) whose postinstall
script runs `npx only-allow pnpm`, which fails under npm. Adding
--ignore-scripts avoids the spurious failure without affecting
functionality.
Tracking: #27826
* fix: remove duplicate install scripts from git
CI already copies scripts/install.{sh,ps1} into hermes_cli/scripts/
during wheel build. No need to commit copies — .gitignore keeps them
out, _find_install_script() falls back to scripts/ for git-clone users.
Tracking: #27826
* fix: address review — remove env_extra, fix ps1 error handling
- Remove unused env_extra parameter from ensure_dependency()
- Invoke-EnsureMode node case now uses Test-Node consistently
- Install-AgentBrowser uses throw instead of exit 1
* feat(config): add install-method stamping + Docker detection
Dockerfile stamps "docker", install.sh stamps "git", and cmd_postinstall
stamps "pip" into ~/.hermes/.install_method. detect_install_method() reads
the stamp first, then falls back to managed-system / container / .git
heuristics. Adds Docker upgrade guidance.
Tracking: #27826
* fix(stamp): move Docker stamp to entrypoint, install.sh stamp after print_success
The Dockerfile stamp was overwritten by the VOLUME overlay at container
start. Moving it to entrypoint.sh ensures it persists. The install.sh
stamp now writes after print_success so it only lands on full success.
The agent can now produce a chart, PDF, spreadsheet, or any other supported
file type and have it land in Slack / Discord / Telegram / WhatsApp / etc.
as a native attachment, just by mentioning the absolute path in its
response. Same primitive works for kanban-worker completions: workers
attach artifacts via kanban_complete(artifacts=[...]) and the gateway
notifier uploads them alongside the completion message.
Changes:
- gateway/platforms/base.py: extract_local_files now covers PDFs, docx,
spreadsheets (xlsx/csv/json/yaml), presentations (pptx), archives
(zip/tar/gz), audio (mp3/wav/...), and html — not just images and video.
Image/video extensions still embed inline; everything else routes to
send_document via the existing dispatch partition in gateway/run.py.
- tools/kanban_tools.py + hermes_cli/kanban_db.py: kanban_complete gains
an explicit ``artifacts`` parameter. The handler stashes it in
metadata.artifacts (for downstream workers) and the kernel promotes
it onto the completed-event payload so the notifier can find it
without a second SQL round-trip.
- gateway/run.py: _kanban_notifier_watcher now calls a new helper
_deliver_kanban_artifacts after sending the completion text. The
helper reads payload.artifacts (preferred), falls back to scanning
the payload summary and task.result with extract_local_files, then
partitions images / videos / documents and uploads each via
send_multiple_images / send_video / send_document.
- website/docs/user-guide/features/deliverable-mode.md + sidebars.ts:
user-facing docs page covering the extension list, the kanban
artifacts pattern, and the MCP-for-connector-breadth recommendation.
Tests:
- tests/gateway/test_extract_local_files.py: 7 new test cases
(documents, spreadsheets, presentations, audio, archives, html,
chart-pdf canonical case). 44 passing, 0 regressions.
- tests/tools/test_kanban_tools.py: 4 new cases covering the artifacts
arg shape (list / string / merge with existing metadata / type
rejection). 17 passing.
- tests/hermes_cli/test_kanban_notify.py: 2 new cases covering full
notifier → artifact-upload path and missing-file silent-skip. 12
passing.
- E2E (real files, real kanban kernel, real BasePlatformAdapter):
worker calls kanban_complete(artifacts=[png,pdf,csv]) → metadata +
event payload land → notifier helper partitions correctly →
send_multiple_images called once with the PNG, send_document called
twice with PDF + CSV.
What's NOT in this PR (deferred to follow-ups):
- Ad-hoc "research this for two hours, ping the thread when done"
slash command — covered today by kanban subscriptions; a dedicated
slash command can ride a follow-up PR if needed.
- Setup-wizard prompt for recommended MCP servers (Notion, GitHub,
Linear, etc.) — docs page lists them; UI is a separate change.
Plan and rationale captured in ~/.hermes/docs/perplexity-computer-parity.pdf
(local doc, not shipped).
Adds a 'triage_aux_unavailable' diagnostic for tasks stuck in triage when
neither the active aux helper slot nor the main-model auto fallback is usable.
Auto-decompose aware:
- kanban.auto_decompose=True (default): primary is auxiliary.kanban_decomposer,
triage_specifier is the fanout=false fallback.
- kanban.auto_decompose=False: primary is auxiliary.triage_specifier (manual
'hermes kanban specify' path).
Default aux slots use 'provider: auto' which falls back to the main model, so
this rule only fires when both the explicit slot config AND the main-model
auto fallback are absent. Quiet by default; informative when there is a real
config gap.
Also adds kd.config_from_runtime_config() that carries kanban + auxiliary +
model keys through to diagnostics, and updates CLI/dashboard call sites to
use it. config_from_kanban_config() is preserved for back-compat.
Reworks the original PR #25640 idea (@qWaitCrypto) to align with the new
auto-decompose dispatcher path landed in #27572. The original PR pointed only
at auxiliary.triage_specifier, which is now the fallback rather than the
primary helper.
Co-authored-by: qWaitCrypto <axmaiqiu@gmail.com>
Yuanbao's QuoteContextMiddleware has a transcript-lookup fallback for
when quote.desc is empty: it scans the session transcript for the quoted
message_id and pulls ybres anchors out of its content. That fallback
works for observed (silent) group messages because the platform writer
attaches message_id (yuanbao.py:2091).
It silently fails for @bot agent-processed messages because gateway/run.py
wrote them as {role:user, content, timestamp} with no message_id, so
quoting an earlier @bot turn that contained an image/file couldn't be
resolved.
Fix: attach event.message_id to the user transcript entry at all three
write sites in gateway/run.py — the agent_failed_early branch, the
no-new-messages edge case, and the normal agent path (first user-role
entry in new_messages).
Surfaces gap reported in #27425 (loongfay) using the existing fallback
already on main; no new caches needed.
Co-authored-by: loongfay <loongfay@users.noreply.github.com>
`hermes_cli/doctor.py` had two recurring patterns:
1. **15 section headers** of the form `print() ; print(color("◆ Name", Colors.CYAN, Colors.BOLD))`
bracketed by 3-line `# =====` / `# Check: X` / `# =====` comment banners.
2. **Paired `check_fail(...) ; issues.append(...)`** for every diagnostic that emits both a
user-visible failure and an auto-fix instruction.
Add two helpers and collapse the patterns:
def _section(title):
print()
print(color(f"◆ {title}", Colors.CYAN, Colors.BOLD))
def _fail_and_issue(text, detail, fix, issues):
check_fail(text, detail)
issues.append(fix)
Replacements:
- 15 `# =====/# X/# =====` banner triples + section header pairs compressed to `_section(...)`
- All 18 `check_fail + issues.append` pairs collapsed to `_fail_and_issue(...)` (single-line
where the call fits under 120 chars, multi-line where it doesn't)
- Net -5 LOC (`+128 / -133`)
The LOC delta is modest after wrapping long calls onto multi-line form for readability — the
real win is uniform call shape and removal of two parallel-pattern footguns. There is now
exactly one way to emit a diagnostic that pairs a user-visible failure with a fix instruction.
Behavior is byte-identical. `_section` produces the same blank line + bold-cyan output the
inline two prints did, and `_fail_and_issue` does the same `check_fail + issues.append`
sequence in the same order. Verified empirically by diffing live `run_doctor()` stdout from
this branch against `origin/main` — `diff -q` reports zero differences.
Test plan:
- All 69 tests across test_doctor.py, test_doctor_command_install.py, and
test_doctor_dedicated_provider_skip.py pass
- `ruff check hermes_cli/doctor.py` clean
- Live `run_doctor()` output byte-identical to origin/main
Refs #23972 (Phase 2 tracker — dedup-only refactor in line with the "net-LOC-negative"
discipline).
Companion PR to #27590. Sweeps remaining stale references to the
LLM-summary path that landed in main with #27590 but weren't fully
caught in the followup cleanup commit.
Real rewrites:
- user-guide/sessions.md: 'Session Search Tool' section rewritten to
describe the three calling shapes (discovery / scroll / browse) with
worked examples. Adds the 'Optional parameters' subsection covering
sort and role_filter.
- user-guide/features/memory.md: 'Session Search' overview rewritten,
comparison table updated (speed: ms instead of LLM summarization,
added explicit free-cost row, link to sessions.md for details).
Stale-claim sweeps:
- user-guide/configuring-models.md: drop the 'Session Search' row from
the aux-model override table (no aux model anymore), drop session
search from the auxiliary-models list.
- user-guide/features/codex-app-server-runtime.md: drop session_search
from the ChatGPT-subscription cost note, drop the session_search
block from the per-task override config example.
- developer-guide/provider-runtime.md: drop 'session search
summarization' from the auxiliary tasks list.
- developer-guide/agent-loop.md: drop session search from the
auxiliary fallback chain list.
- user-guide/skills/.../autonomous-ai-agents-hermes-agent.md: drop
session_search from the 'auxiliary models not working' debug step.
Untouched (still accurate as tool-name mentions, not behavioral claims):
- features/tools.md, features/honcho.md, features/acp.md
- cli.md, sessions.md (other sections)
- developer-guide/tools-runtime.md, agent-loop.md (line 157)
- acp-internals.md, adding-tools.md, prompt-assembly.md
- reference/toolsets-reference.md, reference/tools-reference.md
* feat(session_search): single-shape tool with discovery, scroll, browse — no LLM
Replaces the LLM-summarized session_search with a single-shape tool that
returns actual messages from the DB. Three calling shapes inferred from
args (no mode parameter):
1. Discovery — pass query. FTS5 + anchored ±5 window + bookends per hit,
all in one call. ~20ms on a real DB instead of ~90s for the previous
three aux-LLM calls.
2. Scroll — pass session_id + around_message_id. Returns a window
centered on the anchor. To paginate, re-anchor on the first/last id
of the returned window. Boundary message appears in both windows
as the orientation marker. ~1ms per scroll call.
3. Browse — no args. Recent sessions chronologically.
Bookend_start (first 3 user+assistant msgs) and bookend_end (last 3) give
the agent goal + resolution on every discovery hit, so a single tool call
reconstructs a long session's arc without loading the whole transcript.
The aux-LLM summary path is gone: it cost ~$0.30/call, took ~30s, and
laundered FTS5 hits through a model that could confabulate when the right
session wasn't in the hit list. The merged shape returns byte-for-byte
content from SQLite.
History:
- PR #20238 (JabberELF) seeded the fast/summary dual-mode split.
- PR #26419 (yoniebans) expanded to fast/guided/summary with bookends,
multi-anchor drill-down, default-mode config, and a teaching skill.
This PR collapses that toolkit into one shape with explicit scroll
support, drops the summary path, drops the mode parameter, drops the
config knob, drops the skill. JabberELF's seed work is acknowledged via
the AUTHOR_MAP entry.
Validation:
- 38/38 tool tests pass (tests/tools/test_session_search.py)
- 12/12 get_messages_around tests pass (tests/hermes_state/)
- 11/11 get_anchored_view tests pass (tests/hermes_state/)
- Full tests/tools/ run: 5168 passing, 2 failures pre-exist on main
(test ordering in test_delegate.py, unrelated)
- E2E against live state DB: discovery 20ms, scroll 1ms, browse 280ms;
pagination forward+backward works with boundary-message orientation;
error paths return clean tool_error responses
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
* chore(session_search): prune dead LLM-summary config and docs
Companion to the single-shape rewrite. The auxiliary.session_search config
block, max_concurrency / extra_body tunables, and matching docs sections
all referenced the removed LLM summarization path. Removing them so users
don't try to tune knobs that nothing reads.
- hermes_cli/config.py: drop dead auxiliary.session_search block from
DEFAULT_CONFIG. Leftover keys in user config.yaml are harmless and
ignored.
- hermes_cli/tips.py: drop two tips referencing the removed
max_concurrency / extra_body knobs.
- website/docs/user-guide/configuration.md: drop 'Session Search Tuning'
section and the auxiliary.session_search block from the example.
- website/docs/user-guide/features/fallback-providers.md: drop session_search
rows from the auxiliary-tasks tables and the dedicated tuning subsection.
- website/docs/reference/tools-reference.md: rewrite the session_search
entry to describe the new three-shape behaviour.
- CONTRIBUTING.md: update the file-tree description.
- tests/tools/test_llm_content_none_guard.py: remove TestSessionSearchContentNone
class and test_session_search_tool_guarded — both guard against an
unguarded .content.strip() call site in _summarize_session() that no
longer exists.
Validation: 97/97 targeted tests still pass (hermes_state + session_search +
llm_content_none_guard). Config tests 55/55.
---------
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
The system prompt's 'Conversation started:' line carried minute precision
(%I:%M %p), making it byte-unstable across every rebuild path. Within a
CLI session the in-memory cache held, but on the gateway path (fresh
AIAgent per turn → restore from session DB), any silent failure in the
read or write path dropped the cache stem and forced a full re-prefill
on every subsequent turn. Local prefix-caching backends (llama.cpp /
vLLM) saw this as KV-cache invalidation; remote prefix-caching providers
saw it as an Anthropic-style cache miss.
Three changes:
1. Date-only timestamp ('Sunday, May 17, 2026' instead of '... 03:42 PM').
System prompt now byte-stable for the full day. The model can still
query exact time via tools when it actually needs it. Credit:
@iamfoz (PR #20451).
2. Loud logging on session DB write failures. The update_system_prompt
call used to log at DEBUG, hiding disk-full / locked-database / schema
drift behind a silent fall-through that forced fresh rebuilds on
every subsequent turn. Now WARN with the session id and exception so
persistent issues show up in agent.log without verbose mode.
3. Three-way stored-state distinction on read. The previous
'session_row.get("system_prompt") or None' collapsed three states
into one (missing row / null column / empty string). Now we tell them
apart and WARN when a continuing session lands on null/empty (which
means the previous turn's write never persisted — every subsequent
turn rebuilds and the prefix cache misses every time).
The restore block is extracted into _restore_or_build_system_prompt()
so the prefix-cache path can be unit-tested in isolation.
E2E proof: fresh AIAgent constructed for turn 2 across a minute-boundary
sleep restores byte-identical bytes from the session DB. NULL stored
prompt fires the new warning. Date-only timestamp survives the rebuild
path. All on real SessionDB, no mocks.
Tests:
- tests/agent/test_system_prompt_restore.py (10 new tests)
- tests/run_agent/test_run_agent.py::TestBuildSystemPrompt::
test_datetime_is_date_only_not_minute_precision
Closes#20451 (date-only), #18547 (prefix stabilization),
#8689 (stabilize timestamp across compression), #15866 (timestamp
caching question), #8687 (compression timestamp), #27339
(claim #3: live timestamp in cached system prompt).
Co-authored-by: Martyn Forryan <9133432+iamfoz@users.noreply.github.com>
Grok models hit the same failure modes that OPENAI_MODEL_EXECUTION_GUIDANCE
addresses for GPT/Codex: claiming completion without tool calls
('to be honest, I didn't create the file yet'), suggesting workarounds
instead of using existing tools (proposing a folder-based memory system
when the memory tool exists), replying with plans instead of executing.
TOOL_USE_ENFORCEMENT_GUIDANCE was already injected for any model whose
name contains 'grok' (TOOL_USE_ENFORCEMENT_MODELS). This extends the
follow-on family-specific block — OPENAI_MODEL_EXECUTION_GUIDANCE
(tool_persistence / mandatory_tool_use / act_dont_ask / prerequisite_checks
/ verification / missing_context) — to grok-named models too.
The OPENAI_ prefix is retained for backwards compat with imports/tests;
docstring + inline comment now note that the body is family-agnostic and
the prefix reflects origin, not exclusivity.
Tests cover the OpenRouter slug (x-ai/grok-4.3) and the xai-oauth bare
name (grok-4.3), plus a negative control on claude.
E2E verified against a real AIAgent build of the system prompt for both
xai-oauth and openrouter grok models.
Adds a new 'Auxiliary Capacity-Error Fallback' section to
website/docs/user-guide/features/fallback-providers.md covering:
- The 4-step ladder (primary → fallback_chain → main agent → warn)
- Which errors trigger fallback (402, 429 quota, connection) vs
which respect explicit provider choice (transient 429 rate limits)
- Optional fallback_chain config schema with vision + compression examples
- Recognized quota-error phrases (Bedrock, Vertex AI, generic)
Updates the bottom summary table — every auxiliary task now shows
'Layered (see above)' instead of 'Auto-detection chain' since
explicit-provider users also get the main-agent safety net.
7 new tests:
TestAuxiliaryFallbackLayering (3):
- configured_chain succeeds → main agent fallback NOT consulted
- chain returns nothing → main agent fallback runs and succeeds
- both exhausted → user-visible 'all fallbacks exhausted' warning
fires before the original error is re-raised
TestTryMainAgentModelFallback (4):
- returns (None, None, "") when main provider is 'auto'
- returns (None, None, "") when failed provider == main provider
(no point retrying the same backend)
- resolves the main provider's client when configured correctly
- skips when main provider is marked unhealthy
Layered fallback for auxiliary tasks (compression, vision, tts, web_extract,
session_search, etc.):
1. Primary aux provider (existing)
2. User-configured auxiliary.<task>.fallback_chain (new)
3. Main agent provider + model (new — last-resort safety net)
4. Warn user + re-raise original error (new)
For users on 'auto' (no explicit aux provider), the existing
_try_payment_fallback auto-detection chain runs instead — its Step 1
already IS the main agent model, so they get the same behaviour without
configuration.
The configured fallback_chain config schema comes from #26882 / @zccyman;
the main-agent safety net + exhaustion warning were added on top.
Closes#26882. Builds on the capacity-error gate fix in the previous
commit (#26803 / @Bartok9).
The two TestAuxiliaryClientPoisonedCacheEviction tests were written
when explicit-provider users got no fallback at all on connection
errors — they asserted ConnectionError propagated after eviction
because the fallback gate blocked the auto chain.
After the #26803 fix in the previous commit, capacity errors
(payment/quota/connection) now DO trigger fallback even on explicit
providers. The tests still verify cache eviction (their actual
contract) but now stub _try_payment_fallback so the fallback
machinery does not attempt a real network call.
Closes#26803
Root causes:
1. _is_payment_error() checked for billing keywords (credits, insufficient
funds, billing, payment required) but missed daily token quota exhaustion
phrases used by Bedrock, Vertex AI, and LiteLLM proxies — e.g.
'Too many tokens per day', 'quota exceeded', 'resource exhausted',
'daily limit'. These are functionally identical to credit exhaustion
(provider cannot serve the request) but don't trigger fallback.
2. The call_llm() fallback chain was gated on resolved_provider == 'auto'.
When a task resolves to a specific provider (e.g. 'custom' for a LiteLLM
proxy, or 'openrouter'), capacity failures (payment/quota/connection)
silently raise instead of trying alternatives. This is overly conservative:
capacity errors mean the provider *cannot* serve the request regardless of
user intent, so alternatives should always be tried.
Fixes:
- Add quota-related keywords to _is_payment_error(): quota_exceeded,
too many tokens per day, daily limit, tokens per day, daily quota,
resource exhausted (Vertex AI gRPC code).
- Allow fallback for capacity errors (payment + connection) even when
resolved_provider is not 'auto'. Rate-limit fallback stays gated on
is_auto to honour explicit provider constraints for transient limits.
- Apply both fixes to sync call_llm() and async acall_llm() paths.
- Add 6 targeted tests for the new quota-error detection cases.
