The preflight-compression gate only ran the (expensive) token estimate when
the message COUNT exceeded protect_first_n + protect_last_n + 1. A session
with a handful of very large messages never tripped the count condition, so
compression was never attempted and the turn eventually hit a hard
context-overflow error.
Add _should_run_preflight_estimate() with OR semantics: run the estimate when
either the message count exceeds the protected ranges (the historical gate)
OR a cheap char-based estimate already crosses the configured threshold. The
downstream estimate_request_tokens_rough() stays authoritative — this is only
a hint that decides whether to pay for the full estimate.
Salvaged from #27435 by @texhy (authorship preserved). Re-applied on current
main: the preflight gate moved from conversation_loop.py to turn_context.py
since the PR was opened, so the helper + gate are placed there; the test
imports the real MINIMUM_CONTEXT_LENGTH instead of a hardcoded literal.
Closes#27405.
When context compaction's summary generation fails, the compressor's default
path (abort_on_summary_failure=False) drops the middle window and inserts a
static 'summary unavailable' marker — destroying the compacted turns. #29559
reported the field impact: a Connection error at the compaction moment dropped
124->15 messages (110 lost) for a long browser-automation task; #25585 is the
same failure mode (failed summary commits a destructive compaction anyway).
compress() already has an EXCEPTION to the historical drop default: auth
failures (401/403) ALWAYS abort and preserve the session, because rotating into
a placeholder-summary child on a broken credential strands the user. A transient
network/connection error is the same situation in reverse: it WILL recover, and
retrying then is strictly better than discarding context for a momentary blip.
Extend the always-abort carve-out to terminal connection/network failures:
- new _last_summary_network_failure flag, set in _generate_summary's terminal
failure branch when _is_connection_error(e) (reached only after any main-model
fallback is exhausted), reset alongside the auth flag;
- compress() aborts when it's set (returns messages unchanged,
_last_compress_aborted=True), independent of abort_on_summary_failure;
- a network-specific operator warning (distinct from the auth + config-flag
messages).
Scoped to connection errors only: a generic 500/400 still takes the historical
fallback-drop path (test_non_auth_failure_still_uses_fallback_path stays green).
Tests: network-failure detection + abort-despite-flag-false, both mutation-checked
(removing the flag-set fails detection; removing the carve-out fails the abort).
Anthropic migrated the OAuth token endpoint from
console.anthropic.com/v1/oauth/token (now returns HTTP 404) to
platform.claude.com/v1/oauth/token. The token *refresh* path already
iterated both hosts, but the two initial code-exchange call sites were
hardcoded to the dead console host, so every new Claude OAuth login
failed with 'Token exchange failed: HTTP Error 404: Not Found' and saved
no credentials.
Fix the whole bug class:
- Add _OAUTH_TOKEN_URLS [platform.claude.com, console.anthropic.com] in
agent/anthropic_adapter.py; _OAUTH_TOKEN_URL now points at the live
host for backward-compat with existing imports.
- run_hermes_oauth_login_pure() (CLI flow) iterates the list, first
success wins, mirroring the refresh path.
- hermes_cli/web_server.py (desktop dashboard flow) imports the list and
iterates it too, so the GUI login path is fixed identically.
Probe: console.anthropic.com/v1/oauth/token -> HTTP 404 (gone),
platform.claude.com/v1/oauth/token -> HTTP 400 (alive). Verified a real
Claude MAX OAuth login now succeeds end-to-end.
deliver=origin (or omitted) from a TUI or classic-CLI session produces a
job with origin=null, because those sessions never populate the
HERMES_SESSION_PLATFORM/CHAT_ID context vars that _origin_from_env reads.
The scheduler then resolves no delivery target and skips delivery — the
job runs and saves output to last_output, but nothing reaches the user
and they only find out by polling cronjob(action='list') (#51568).
This is by design (local sessions have no live-delivery channel), so the
fix surfaces it instead of silently dropping the intent:
- cronjob create now appends an informational notice to its result when
a created job resolves to zero delivery targets and the user did not
explicitly ask for deliver='local'. The check uses the scheduler's own
_resolve_delivery_targets so it accounts for origin, home channels,
'all', and explicit platform targets — no false positives.
- PLATFORM_HINTS gains a 'tui' entry (the TUI had none) and the 'cli'
hint now states that cron jobs from these sessions are local-only and
that deliver must target a gateway-connected platform to notify the
user. This stops the agent promising a delivery that never happens.
No scheduler/delivery behavior change; no new env var; cron isolation
invariant untouched.
install_pet now refuses spritesheet/pet.json URLs that aren't on a petdex
host (matching thumbnail_png's existing _is_petdex_host guard), so a
spoofed manifest can't redirect a download at an arbitrary host. Slugs
are normalized to a single path segment before indexing into pets_dir(),
closing a path-traversal vector in load_pet/remove_pet/install_pet.
Open-ended skill learning across every surface. /learn <free text> takes a
description of any source — a directory, a URL, the workflow you just walked
the agent through, or pasted notes — and the live agent gathers it with the
tools it already has (read_file/search_files, web_extract, the conversation,
the pasted text), then authors a SKILL.md via skill_manage following the
house authoring standards (<=60-char description, the standard section order,
Hermes-tool framing, no invented commands).
No engine, no model-tool footprint, works on any terminal backend (local,
Docker, remote): /learn builds a standards-guided prompt and hands it to the
agent as a normal turn.
- agent/learn_prompt.py: shared standards-guided prompt builder
- /learn registry entry (both surfaces) + CLI handler (inject onto input
queue) + gateway handler (rewrite turn, fall through, /blueprint pattern)
- tui_gateway command.dispatch returns a send directive -> TUI + dashboard chat
- dashboard Skills page 'Learn a skill' panel (dir + URL + open-ended text)
composes a /learn request and runs it in chat
- docs (slash-commands ref + skills feature page), 11 targeted tests
Inspired by OpenAI Codex's Record & Replay and the /learn concept from #47234
(dir-distillation engine); reworked to be open-ended and engine-free per
review.
A "one-shot" is a single stateless model call that runs OUTSIDE any conversation:
it never touches session history, never breaks prompt caching, and returns plain
text. UI surfaces need this for small generative chores — a commit message from a
diff, a rename suggestion, a summary — where an agent turn would pollute the
thread and hand-rolling an LLM call at every call site would be worse.
- `agent/oneshot.py`: `run_oneshot(...)` over the existing auxiliary-client
plumbing (same path as title generation). Two call shapes: explicit
instructions/input, or a registered `template` + `variables` (templates own the
prompt engineering so it stays consistent across CLI/TUI/desktop). Ships a
`commit_message` template. Model selection inherits the live session via
`main_runtime`, else the configured aux `task` backend.
- `tui_gateway/server.py`: `llm.oneshot` RPC (long-handler) inheriting the
session's model when `session_id` resolves.
Stateless by construction — no session mutation, cache untouched.
Follow-up to the coding-context posture (#43316): that PR detects each repo's
verify loop (manifests, package manager, exact test/lint/build commands, context
files) and bakes it into the system-prompt snapshot — but only as a string, for
the model. Non-prompt consumers (the desktop verify UI) had no way to read it
without re-sniffing and drifting from the prompt.
Split detection from rendering, keeping one source of truth:
- `detect_project_facts(root) -> ProjectFacts` (frozen) holds the structured
facts; `_project_facts()` now renders it into the same snapshot lines, so the
prompt block stays byte-identical (cache-safe).
- `project_facts_for(cwd)` resolves the workspace root (git, else marker) and
returns the structured facts, or None outside a workspace.
- `project.facts` gateway RPC surfaces it to any client (desktop/TUI/ACP).
Tests assert the structured output and that the UI-facing commands never drift
from what the prompt block renders (one detector feeds both).
Adds auxiliary.background_review.{provider,model} (default auto = main chat
model — unchanged). Set it to a different, cheaper model and the post-turn
self-improvement review runs there for ~3-5x lower cost.
Cache-aware by design: the main chat is warm in the prompt cache, so the
default full-history replay on the main model is cheap cache reads — left
exactly as-is. A different model can't reuse that cache (different key), so
when (and only when) routed to a different model the fork replays a compact
digest instead of the full transcript, minimising what it cold-writes on the
aux model. Same model -> full replay; different model -> digest.
Quality holds in benchmarks: memory capture identical, skill near-identical.
Nothing changes unless you opt in by naming a different model.
Co-authored-by: Hermes Agent <noreply@nousresearch.com>
The success/staged gating and op-expansion for mirroring built-in memory
writes to external providers lived in a standalone agent/memory_write_bridge.py
helper called inline from two core call sites (tool_executor.py,
agent_runtime_helpers.py). That left the mirror decision-making in the agent
loop, outside the memory-provider interface.
Fold it into a new MemoryManager.notify_memory_tool_write() entry point: the
loop now hands over the raw tool result + args and a metadata callback, and the
manager decides whether/what to mirror. Both core call sites collapse to a
single call; the orphan module is removed. No MemoryProvider ABC change.
Tests rewritten as behavior tests against the manager method.
Mirror built-in memory writes to external providers only after the native memory tool succeeds and is not staged for approval. Keep OpenViking's built-in memory mirroring add-only, since Hermes native memory entries do not yet have stable OpenViking file URIs for replace/remove.
Add a narrow viking_forget tool for exact user memory file deletion and document the current OpenViking write/delete behavior.
Make the computer_use toolset platform-agnostic by driving cua-driver on
macOS, Windows, and Linux. Consumes the 8 cua-driver decoupling surfaces
(capability discovery, structuredContent AX tree, opaque element_token,
click button enum, explicit mimeType, machine-readable manifest,
structured list_windows, structured health_report), each degrading
gracefully on older drivers.
Adds `hermes computer-use doctor` (drives cua-driver health_report with a
per-OS check matrix and an exit 0/1/2 ok/degraded/blocked contract), full
typed wrappers for the previously-uncovered cua-driver tools plus a generic
call_tool escape hatch, per-session agent-cursor lifecycle, platform-aware
system-prompt guidance (host-deterministic, cache-safe), and honors
HERMES_CUA_DRIVER_CMD end-to-end.
Replaces the macOS-only skills/apple/macos-computer-use skill with a
cross-platform skills/computer-use skill, and refreshes the EN + zh-Hans
docs.
Supersedes #44221 (Windows-enablement salvage of #30660).
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
The compaction trigger compared estimated input against context_length *
threshold, but the provider reserves max_tokens of OUTPUT out of the same
window. With a large max_tokens (e.g. 65536 on a custom provider) the usable
input budget is materially smaller than the raw window, so sessions hit a
provider 400 before compaction ever fired.
_compute_threshold_tokens now subtracts the output reservation
(context_length - max_tokens) before applying the percentage and the
small-window 85% guard. max_tokens is stored on the compressor (threaded from
agent.max_tokens at construction) and reused across update_model() switches;
None = provider default = no reservation (full-window behavior, unchanged).
Reimplemented on the current _compute_threshold_tokens surface (the inline
threshold calc the original PR targeted was since refactored for the
small-window #14690 fix); composes with that 85% guard on the effective budget.
Credit: @kyssta-exe (#43651) — original design for the output-token
reservation in the compaction threshold.
Closes#43547.
After a compaction, the post-compression path parks last_prompt_tokens=-1 and
sets awaiting_real_usage_after_compression=True, but last_real_prompt_tokens
still holds the stale pre-compression value (above threshold). should_defer_
preflight_to_real_usage() hit the 'last_real_prompt_tokens >= threshold => False'
short-circuit and let preflight fire a SECOND compaction before the provider
reported real post-compaction usage. Add an early-return on the awaiting flag so
deferral holds for exactly one turn; update_from_response() clears it.
The flag-setting half (#36718) already landed on main via the in-place
compaction path (conversation_compression.py); this adds the missing
should_defer guard that consumes it.
Credit:
- @ashishpatel26 (#38133) — diagnosis + the should_defer early-return design
- @Tranquil-Flow (#36769) — same #36718 fix, identical guard placement
Closes#36718.
The tail-protection budget walks estimated an assistant message's tokens from content + function.arguments only, dropping each tool_call's id, type and function.name (plus JSON structure). Assistant turns that fan out into parallel tool calls were undercounted by 2-15x (a 4-tool-call turn measures ~73 vs ~1,090 real tokens), so the protected tail overshot tail_token_budget and compression ran far below its intended ratio — context kept growing.
Consolidate the three duplicated budget walks (_prune_old_tool_results and the two passes in _find_tail_cut_by_tokens) into a single _estimate_msg_budget_tokens() helper that counts the full tool_call envelope via len(str(tc)), consistent with how _estimate_message_chars estimates message size elsewhere.
Tested on Windows: new tests/agent/test_compressor_tool_call_budget.py plus the existing compression suite (test_context_compressor, compressor_image_tokens, cross_session_guard, infinite_compaction_loop) — 209 passed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Follow-up to the salvaged preflight token-progress fix: require a material
(>5%) token reduction to count as progress, matching the overflow-handler
retry path (conversation_loop.py, #39550), so a sub-5% wobble can't keep the
3-pass preflight loop spinning. Adds boundary + zero-token regression tests.
/simplify-code QUALITY finding: the `if callable(_available_entries): ... else:
pool.select()` ladder was dead for the real CredentialPool type (`_available_entries`
is always a bound method) AND the select() fallback violated the helper's read-only
contract — select() -> _select_unlocked() runs _available_entries(clear_expired=True,
refresh=True), which persists to auth.json and triggers a network refresh. Call
_available_entries(clear_expired=False, refresh=False) directly inside the existing
try/except instead.
Also drops the now-dead `select=` stubs from the 6 pool tests (they only existed to
satisfy the removed fallback branch). Behavior unchanged; 6 pool tests pass and the
read-only / null-token contract tests were mutation-checked (flipping the flags /
removing the None-guard fails the respective test).
Rebased onto god-file Phase 1 refactor — preflight compression has moved
from agent/conversation_loop.py to agent/turn_context.py (no semantic
change in the refactor itself; the bug below was carried over verbatim).
The preflight compression loop in ``turn_context.py`` uses
``len(messages) >= _orig_len`` to decide whether a compression pass has
made progress. That conflates two different conditions: a true no-op
(transcript materially unchanged) and effective token compression that
summarises message contents but keeps the same number of rows. The
second case is misread as "Cannot compress further" — the session then
surfaces ``Context length exceeded`` and auto-resets even when the
post-compression estimate is far below the model context window.
Observed example from #39548: a Telegram session on GPT-5.5 with a 1M
context dropped from ~288k → ~183k tokens (a 36% reduction) while
preserving 220 messages. The loop treats that as exhaustion and the
gateway auto-resets the session.
Fix
---
Add ``_compression_made_progress(orig_len, new_len, orig_tokens, new_tokens)``
and call it after the post-pass ``estimate_request_tokens_rough`` (which
is moved up to run *before* the progress check instead of after it).
Either a row-count reduction OR a token-count reduction now counts as
progress; only when neither moves do we break out as "stuck".
Fixes#39548
Compression can materially reduce request size (tool-result pruning,
in-place summarization) without reducing message count. The two
compression-success checks in conversation_loop.py (413 handler and
context-overflow handler) only compared len(messages) to detect
success, missing token-only compression.
Now re-estimates tokens after compress_context() returns and treats
any >=5% reduction as a successful compression pass. Error logs
also use the post-compression token count instead of the stale
pre-compression estimate.
Fixes: #39550
* feat(providers): remove google-gemini-cli + google-antigravity OAuth providers
Google now actively bans accounts for third-party tools that piggyback on
Gemini CLI / Antigravity / Code Assist OAuth, and because abuse prevention
sits at a backend layer the ban can extend to the entire Google account
(Gmail/Drive), with a second violation being permanent.
Ref: https://github.com/google-gemini/gemini-cli/discussions/20632
Removes both OAuth inference providers entirely (modules, provider profiles,
auth/runtime/config/models wiring, the /gquota Code Assist quota command,
the antigravity-cli optional skill, desktop + docs surface in en + zh-Hans).
The API-key 'gemini' provider (GOOGLE_API_KEY/GEMINI_API_KEY against
generativelanguage.googleapis.com) is unaffected and stays fully supported.
* fix(skills): keep the antigravity-cli skill — only the OAuth provider is removed
The antigravity-cli optional skill orchestrates the external `agy` binary as
a coding-agent tool via the terminal tool — it does NOT wrap Hermes inference
through the banned google-antigravity OAuth provider, so it carries none of
the account-ban risk that motivated removing that provider. Restore the skill,
its docs page, the sidebar entry, and the optional-skills catalog row. The
google-antigravity / google-gemini-cli inference providers stay fully removed.
* fix(agent): strip stale reasoning_content when falling back to a strict provider
A reasoning primary (DeepSeek/Kimi/MiMo thinking mode) pins reasoning_content
on every assistant tool-call turn (a single space " " pad). api_messages is
built once under the primary; on a mid-session fallback to a strict
OpenAI-compatible provider (Mistral, Cerebras, Groq, SambaNova), those stale
pads were replayed verbatim and rejected with HTTP 400/422:
body.messages.2.assistant.reasoning_content: Extra inputs are not
permitted (input: ' ')
reapply_reasoning_echo_for_provider() only ever ADDED pads, so it never
reconciled history built under a reasoning primary against a strict fallback.
copy_reasoning_content_for_api() also leaked empty-string and 'reasoning'-only
shapes to non-pad providers.
Fix both sites: when the active provider does not enforce echo-back, strip
reasoning_content (empty, space-pad, or non-empty) entirely. Re-padding when
switching TO a reasoning provider is preserved. Covers the Cerebras 400 from
#45655 and the DeepSeek->Mistral 422 fallback report.
Refs #45655.
* test: update reasoning-replay tests for strict-provider stripping
test_explicit_reasoning_content_beats_normalized_reasoning_on_replay was
implicitly running on the OpenRouter fixture (non-pad); pin it to a reasoning
provider so the precedence it checks is observable. Add a positive
strict-provider test asserting reasoning_content is stripped on replay.
The kanban-worker and kanban-orchestrator bundled skills existed only to
be force-loaded into dispatcher-spawned workers, gated by
environments:[kanban] so they wouldn't leak into normal CLI listings.
That gating was fragile (the leak that #50443 patched) and the
--skills auto-load was already best-effort — most workers ran without it
because the bundled skill isn't present in profile-scoped skills dirs.
Remove the skills entirely and promote their load-bearing content
(workspace kinds, deliverable artifacts, created-card integrity, profile
discovery) into KANBAN_GUIDANCE, which is already injected into every
kanban worker's system prompt. Net result: every worker reliably gets
the guidance, nothing can leak into a CLI/blank-slate session, and the
gating machinery is gone.
- agent/prompt_builder.py: promote the 4 load-bearing rules into KANBAN_GUIDANCE
- hermes_cli/kanban_db.py: drop --skills kanban-worker auto-injection + _kanban_worker_skill_available probe
- hermes_cli/kanban_swarm.py: drop skills=[kanban-orchestrator] on the root card
- hermes_cli/kanban.py: drop kanban-init skill seeding; fix help text
- delete skills/devops/kanban-{worker,orchestrator}
- docs: delete the two skill pages (EN+zh), fix sidebars/catalog/kanban.md/kanban-worker-lanes.md and the video-orchestrator + codex-lane references
- tests: update spawn-argv expectations; re-bound the guidance-size guard
Supersedes the skill-leak half of #50443 (credit @helix4u for flagging the area).
Salvage follow-up on top of @pmos69's #29474. The PR resolved the
Antigravity OAuth client purely by discovering it from an installed `agy`
binary or HERMES_ANTIGRAVITY_CLIENT_ID/SECRET env vars, so users without
agy installed hit a hard 'client ID not available' error.
Antigravity's desktop OAuth client is a public, non-confidential installed-app
client (PKCE provides the security), baked into every copy of the Antigravity
CLI — same posture as the gemini-cli credentials Hermes already ships in
google_oauth.py. Bake it in as the final fallback (env -> discovery -> public
default) and add the public default Code Assist project as the discovery
fallback, matching the reference Antigravity flow. Now consumers can
authenticate directly without agy installed.
Secret redaction only matched `Authorization: Bearer <token>`. Other auth
headers passed through verbatim into logs, tool output, and transcripts:
- `Authorization: Basic <base64>` — leaks base64(user:password)
- `Authorization: token <pat>` / any non-Bearer scheme
- `Proxy-Authorization: ...`
- `x-api-key: <key>` (Anthropic and many providers) and `api-key`,
`x-goog-api-key`, `x-auth-token`, `x-access-token`, ... — opaque values with
no known vendor prefix were caught by nothing
A logged request or an echoed `curl -H "x-api-key: ..."` command therefore
leaked live credentials.
Generalize the Authorization rule to mask the credential for any scheme (and
Proxy-Authorization) while preserving the header name and scheme word for
debuggability, and add an api-key header rule for the single-opaque-value
headers. Bearer behavior is unchanged; plain prose containing the word
"authorization" (no colon-delimited value) is left untouched.
Adds regression tests for Basic/token/Proxy auth and the x-api-key/api-key
headers, including inside a curl command.
hermes backup only walks HERMES_HOME, so memory providers that keep
config/credentials in home-anchored dotdirs (honcho -> ~/.honcho,
hindsight -> ~/.hindsight, openviking -> ~/.openviking) lost that data
across a backup/import cycle — the peer IDs, session pairings, and API
keys never made it into the archive.
Add an optional MemoryProvider.backup_paths() hook (default []). The
active provider declares its external paths; backup resolves them from
config only (no init, no network), archives the ones under the home dir
into a reserved _external/ subtree encoded relative to home, and import
restores them to their original location with a home-anchored traversal
guard and 0600 on credential-shaped files. Paths outside home are
skipped as non-portable.
honcho, hindsight, and openviking override the hook. E2E-validated full
backup->import cycle plus 7 new tests.
Bedrock Claude routes through the AnthropicBedrock SDK and injects
cache_control, so cached tokens are always reported — but the pricing
table had no cache cost fields for any Bedrock model, so /usage showed
"cost unknown" on every cached session. Also, cross-region inference
profiles (us./global./eu. prefixes) never matched the bare pricing keys.
- Add cache_read/cache_write rates to the four Bedrock Claude rows
(read 0.1x input, write 1.25x input per the Bedrock pricing page).
- Normalize the cross-region prefix in the Bedrock pricing lookup,
mirroring is_anthropic_bedrock_model's prefix list.
Closes#50295.
The background-review fork (fires ~every 10 turns) pins
review_agent.session_id = agent.session_id — the parent's LIVE id — for
prefix-cache parity, then calls close(). With session finalization now in
close(), that would end the still-active parent session mid-conversation.
Set _end_session_on_close = False on the fork so the real owner (CLI close /
gateway reset / cron) finalizes the session instead.
Follow-up to the #12029 fix.
Funnel session finalization through AIAgent.close() — the single terminal
path every agent (CLI, gateway, subagent, cron) funnels through — so finished
agents stop leaving rows with ended_at IS NULL. The biggest leak source was
delegate_task subagent + background-review forks whose close() never ended
their row.
end_session() is first-reason-wins and no-ops on an already-ended row, so a
'compression'/'cron_complete'/'cli_close' reason set by an earlier terminal
path is never clobbered. /resume already calls reopen_session(), so
finalizing-on-close does not break resumability.
Temporary helper agents that rotate/share the session forward (manual
compression, gateway session-hygiene) opt out via _end_session_on_close=False.
Also stop the long-running gateway heartbeat once the executor is done or the
session slot is rebound to a different agent, preventing a stale
'running: delegate_task' bubble from outliving its run.
Closes#12029.
The 'Session compressed N times — accuracy may degrade' warning went
through _vprint (CLI stdout only), so the Ink TUI / Telegram / Discord
never saw it — unlike the two other compression warnings in the same
module, which route through _emit_status (and store _compression_warning
for late-bound gateway status_callback replay).
Set agent._compression_warning + call agent._emit_status() for this
warning too, matching the sibling pattern. _emit_status still _vprints
for the CLI, so CLI output is unchanged; TUI / gateway surfaces now
receive it via status_callback (and replay_compression_warning can
re-deliver it once a late-bound gateway callback is wired).
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
When an OpenAI-compatible proxy (e.g. cmkey.cn, one-api Anthropic channels)
returns a well-formed HTTP 200 whose summary content is null or empty/
whitespace-only, _generate_summary coerced it to "" and stored a prefix-only
summary — silently replacing the compacted turns with nothing. The model then
lost all in-progress context after compression (#11978, #11914).
_validate_llm_response already guards None / empty-choices, so those never
reach the compressor; the gap was a well-formed response with empty *content*.
Now treat empty content as a summary failure: raise so it routes through the
existing main-model fallback then transient cooldown, dropping the turns
without a summary rather than wiping context with an empty one.
Also narrow the bare 'except RuntimeError' so only genuine 'No LLM provider
configured' errors take the 600s no-provider cooldown; empty/invalid-response
RuntimeErrors from a configured provider now correctly get the main-model
fallback instead of being misrouted into the long no-provider cooldown.
Reported by @Hung2124; area identified by @annguyenNous in #39590.
When the main provider is the Codex app-server runtime (api_mode
codex_app_server), the gateway showed no verbose 'running X' tool-progress
breadcrumbs on Telegram while every other provider did. The app-server
session processes item/started notifications (command execution, file
changes, MCP/dynamic tool calls) but never surfaced them as Hermes
tool-progress events — the session was constructed without an on_event
hook, so the agent's tool_progress_callback was never invoked on this
route.
Add _codex_note_to_tool_progress() mapping item/started → (tool_name,
preview, args) for commandExecution / fileChange / mcpToolCall /
dynamicToolCall, and wire an on_event hook into CodexAppServerSession that
forwards mapped events to agent.tool_progress_callback('tool.started',
...) — the same signature the chat_completions path uses (tool_executor.py).
Non-tool items (agentMessage/reasoning) and non-item/started methods map
to None and are ignored.
Co-authored-by: jplew <462836+jplew@users.noreply.github.com>
load_pool() is meant to be a read, but it persistently pruned env-seeded
pool entries whenever the calling process's os.environ lacked the seeding
var. A process without MINIMAX_API_KEY would delete the persisted
env:MINIMAX_API_KEY entry from auth.json for every other process, causing
auth.json to oscillate and auxiliary auto-detect to fall through to the
wrong provider.
env:* entries are persisted references re-hydrated from the environment on
each load — a missing var means "cannot re-seed right now", not "source is
gone forever". _prune_stale_seeded_entries now gates env-source removal
behind prune_env_sources (default True for explicit cleanup paths);
load_pool() passes prune_env_sources=False. File-backed singletons
(device-code OAuth, hermes_pkce) still prune when their backing file is
gone, and explicit removal via `hermes auth remove` (source suppression)
is unaffected.
Fixes#9331.
Co-authored-by: houko <suzukaze.haduki@gmail.com>
The compaction threshold is max(context_length * threshold_percent,
MINIMUM_CONTEXT_LENGTH=64000). The floor prevents premature compression on
large models, but degenerates at small windows: a model at exactly 64000
ctx gets max(32000, 64000) = 64000 — a threshold equal to the ENTIRE
window. should_compress() can then never fire, because the provider
rejects the request before usage reaches 100%. Auto-compression silently
never triggers for any model whose context_length <= MINIMUM /
threshold_percent (e.g. 64K-per-slot local models).
Centralize the calc in _compute_threshold_tokens(). When the floor would
meet or exceed the context window, trigger at 85% of the window
(_MIN_CTX_TRIGGER_RATIO) — high enough that a minimum-context model uses
most of its budget before compacting (compacting at the 50% percentage
would waste half the small window), but below 100% so compaction actually
fires before the provider rejects the request. This mirrors the existing
gpt-5.5/Codex 85% autoraise rationale. Large-context behavior (floor at
64000) is unchanged; both call sites (__init__ and update_model) use the
shared helper.
Co-authored-by: soynchux <soynchuux@gmail.com>
Co-authored-by: LeonSGP43 <154585401+LeonSGP43@users.noreply.github.com>
Co-authored-by: Tranquil-Flow <tranquil_flow@protonmail.com>
