Commit Graph

194 Commits

Author SHA1 Message Date
kshitijk4poor 170a73637d fix(openai): drop prompt_cache_options from Astra requests — not an SDK kwarg, 30m is the server default
Every direct-API (api.openai.com) Astra request raised
``TypeError: Responses.create() got an unexpected keyword argument 'prompt_cache_options'``
before reaching the network: openai 2.24.0's Responses.create has no such parameter and no
**kwargs, and neither send path relocates it into extra_body. The PR's tests stopped at
build_kwargs/preflight so the SDK boundary was never crossed.

OpenAI's prompt-caching guide states ``prompt_cache_options.ttl`` accepts only ``30m`` and that
``30m`` is the default, so the field carried no information: sending nothing yields the same
cache lifetime. The sanitizer now only removes what the API rejects (none/minimal effort,
sampling/logprob knobs, the pre-5.6 ``prompt_cache_retention``) and never adds a field, which
also keeps the request body byte-stable for the cache prefix.

Also: none/minimal→low no longer needs a bespoke {"", "none", "disabled", "off"} set —
``clamp_effort`` against CODEX_ASTRA_EFFORTS already resolves to the floor (``low``); and the
auxiliary adapter derives ``is_codex_backend`` from ``classify_responses_route`` (the declared
single owner of that predicate) instead of re-implementing the host test inline.

Tests reshaped to contracts: the two proxy/subdomain cases collapse into one parametrised
"exact host only" test asserting effort and temperature pass through untouched.
2026-09-07 21:43:54 +05:30
Eva 299d86851c fix(openai): keep Astra 900K alias gated and wire-compatible
(cherry picked from commit c7cd27d7f050598b9dc052c73fa1dc78c045d3c6)
2026-09-07 21:43:54 +05:30
Eva 850680fcdf fix(openai): require canonical host for Astra cache
(cherry picked from commit 6e73cc5cc66e4003276c4472e6ce2d77e602f130)
2026-09-07 21:43:54 +05:30
Eva 5a82258626 fix(openai): keep Astra rules on eligible routes
(cherry picked from commit f92fb9d9964e6e8ea118035c548aae812054f504)
2026-09-07 21:43:54 +05:30
Eva c990017482 test(openai): close Astra baseline review gaps
(cherry picked from commit 8c27b7c9316ba675e4d9ebcc7a659754f37f18ef)
2026-09-07 21:43:54 +05:30
Eva 2c315ff59b feat(openai): add GPT-6 Astra baseline support
(cherry picked from commit a8c53d20c6b16cc35745e364e16bb7259166a1d3)
2026-09-07 21:43:54 +05:30
Teknium a9ef4a7625 fix(codex): keep transport echoes out of durable user history
Port the exact submitted-wire-text ownership boundary from #93546 onto
current topical runtime code. Do not add the candidate's mocked-result
fallback or storage-level content deduplication. Preserve later distinct
and identical user events, separate identical accepted turns, and keyless
inputs. Add two regression invariants and offline subprocess-wire A/B.

Local wire A/B: 4/8 control matrix passing on base, 8/8 after.
Broader tests queued behind campaign lock; not ready for merge.

Refs #104653
Original diagnosis: @gitszabolcs (#38254)
Original implementation: #43127, submitted by @vashkartik
Focused salvage and wire-text correction: @fancyboi999 (#93546)
Current-main carry-forward considered: #104698

Co-authored-by: Xinmin Zeng <135568692+fancyboi999@users.noreply.github.com>
Co-authored-by: VECTOR <vector.hq@outlook.com>
2026-09-07 08:09:57 -07:00
Teknium b578261584 fix: keep Kanban worker scope out of descendant processes
Carry the existing write fence across Hermes-owned spawn boundaries without
dropping board routing or changing credential policy. Grant dispatcher and
managed tool runtimes explicit task scope; align CLI task mutations with tools.

Verify real shell/CLI descendants, dispatcher startup, and supervised stdio
transport against isolated SQLite boards. This is cooperative runtime scoping,
not OS confinement.

Refs #103974, #104058, #104904
2026-09-07 07:10:28 -07:00
Teknium fd3565deec fix: remove dedicated user-facing output cap controls 2026-09-07 06:15:43 -07:00
sylvainCDA 693641aa8b fix(chat-completions): strip name from tool-result messages for strict providers
The Chat Completions schema has no `name` field on `role: tool` (only on
the long-removed `role: function`), but Hermes carries the tool name over
onto the result message. Permissive providers ignore it; strict ones
(aki.io) reject the whole payload with `contains item with unknown key
name`, which breaks every tool call in the session.

Follow-up to the review on #51365:

- The strip now goes through the copy-on-write `mutable_msg()` path in
  `convert_messages()`, preserving the identity/copy-on-write contract
  instead of mutating `msg` in place.
- `handle_max_iterations()` hand-builds its summary payload and calls
  `chat.completions.create()` directly, bypassing the transport, so it
  leaked `name` even with the transport fixed. It now mirrors the same
  role-qualified removal, next to the existing tool_name/codex_*/timestamp
  strips.

The removal is role-qualified: `name` stays on user/assistant messages,
where it is schema-valid.

Regression coverage on both paths; both tests fail without the fix.
2026-09-07 02:50:45 +05:30
tylman b0adce1cbf feat(models): add gemini-3.7-flash and gemini-3.8-flash support
- Generalize Gemini 3 thinking config model prefix match to gemini-3*
- Add pricing snapshot entries for gemini-3.7-flash and gemini-3.8-flash
- Add model identifiers to Google, OpenRouter, and Vertex CLI lists
- Add test coverage for gemini-3.8-flash thinkingLevel configuration
2026-09-06 05:42:22 -07:00
Teknium 2776813df3 compat(plugins): temporary import-path shims for external plugins — ONE commit, revert on schedule
The Sep 2026 decomposition (PR #102117) makes internal import paths a non-API: names now live in
the focused modules that define them. This commit is the ONLY thing keeping the old paths alive,
so external plugins have time to update. It is deliberately a single, unsquashed commit:

    git revert <this sha>

removes every shim, stub and manifest at once on the announced date. Nothing in-tree may depend on
these pointers: scripts/check_compat_pointers.py (wired into lint.yml) fails CI if it does.

What it adds (see COMPAT_MANIFEST.md, compat_manifest.json):
- 332 facade modules get one delimited `PLUGIN-COMPAT` block appended at the end of the file
- 1,172 moved names resolved lazily via a module `__getattr__` (PEP 562) — never a top-level import,
  so no import cycles; facades that already had `__getattr__` get a chained one
- 592 third-party/stdlib names the old modules used to expose, with their original import statements
- 266 public definitions that had been deleted as unused, restored byte-for-byte from the pre-decomposition
  tree (+40 private helpers and 16 imports pulled in only because a restored definition needs them)
- 3 deleted modules recreated as re-export stubs (gateway/startup_watchdog, hermes_cli/observability/
  relay_runtime, tools/environments/modal_utils)
- private names (`_x`) get no pointer: they were never API (3,792 skipped)

Verified: all 335 touched modules import under a fresh HERMES_HOME and every manifest name resolves;
the lint reports zero in-tree uses; ruff clean; targeted suites unchanged.
2026-09-03 17:13:22 -07:00
Teknium 2a95791992 simplify(compat): run_agent/model_tools/toolsets/acp/providers — drop 42 re-exports/aliases, repoint 15 callers + 99 test files
run_agent.py: delete the `# noqa: F401` re-export block (agent.process_bootstrap
OpenAI/_SafeWriter/_get_proxy_*, model_tools get_tool_definitions/
handle_function_call/check_toolset_requirements, FailoverReason,
_qwen_portal_headers/_routermint_headers, session_persistence names,
estimate_request_tokens_rough, ContextCompressor + friends, jittered_backoff,
prompt_builder names, message_sanitization names, tool_dispatch_helpers
names) — 41 names run_agent never used itself — and the `_STREAM_DIAG_HEADERS`
back-compat class alias (no in-tree reader). run_agent now imports only what
it uses (get_toolset_for_tool, is_local_endpoint, coalesce/uniquify tool-call
ids, cleanup_vm/get_active_env from terminal_tool_lifecycle).

agent/*: `_ra().X` late-binds that only reached a re-export now import the
defining module directly (agent_runtime_helpers -> process_bootstrap.OpenAI,
model_tools.handle_function_call, session_persistence._safe_session_filename_component;
agent_init -> model_tools.get_tool_definitions/check_toolset_requirements,
_lazy_headers("agent.client_lifecycle", ...) for qwen/routermint;
system_prompt -> agent.prompt_builder / model_tools directly, dropping its
own _ra() shim and the `_r` parameter threading). `_ra()` stays for
run_agent-resident names (logger, AIAgent, _hermes_home, _set_interrupt, ...).

toolsets.py: remove resolve_multiple_toolsets (shim-only, restored by
34abf954bd); tests/test_toolsets.py pins the same union behavior via
resolve_toolset over each name.

providers/__init__.py: drop the OMIT_TEMPERATURE re-export (no callers via the
package); ProviderProfile stays because __init__ uses it for annotations —
2 tests repointed to providers.base.

agent/iteration_budget.py: drop the "run_agent re-exports the class"
docstring pointer; 4 tests import IterationBudget from its home.

model_tools.py (arg_coercion names), agent/tool_executor.py, and
hermes_cli/cli_session_mixin.py repoints landed via a sibling commit on this
shared worktree.

Callers repointed: gateway/run.py, hermes_cli/cli_chat_turn_mixin.py,
hermes_cli/cli_tui_mixin.py, tui_gateway/session_workdir.py,
agent/transports/codex.py (one-line imports) + comment pointers in
tools/file_state.py, tools/schema_sanitizer.py, scripts/tool_search_livetest.py.
Tests: patch("run_agent.X") / monkeypatch.setattr(run_agent, "X") /
`from run_agent import X` -> defining module across 99 test files.
2026-09-03 13:28:22 -07:00
Teknium d179f28307 simplify(compat): anthropic_adapter — drop 30 re-exports + 1 alias, repoint 22 caller files (32 sites), 38 test files (~125 sites) 2026-09-03 13:16:47 -07:00
Teknium e83816a4d1 review-fix(comments): restore lost #NNNN rationale comments across non-test source (mechanical sweep, condensed, code unchanged)
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
2026-09-03 09:44:26 -07:00
Teknium 5a0efda992 review-fix(comments): restore reviewer-named rationale blocks (#4926, #81335, #54220/#56747, #100436, #5057/#6252/#10370/#4665) 2026-09-03 09:32:25 -07:00
Teknium 2198087049 Merge branch 'simp/r3-07-C2' into simp/integration3 2026-09-02 22:41:56 -07:00
Teknium 9b669ca507 refactor(agent/relay): _ManagedAttempt error-recording ctx manager; managed_callback_guard as contextmanager; plugin cleanup steps table; close_session via _operation; anthropic normalize predicates collapsed 2026-09-02 22:35:41 -07:00
Teknium b5ad36ac81 Merge branch 'simp/r3-08' into simp/integration3 2026-09-02 21:57:13 -07:00
Teknium 5adb74fd24 refactor(agent/relay_runtime,transports): inline single-use _push_session_scope; get_transport rediscovery predicate 2026-09-02 20:23:21 -07:00
Teknium c83de74cb7 refactor(agent/relay): pack call/signature spans to 120 cols 2026-09-02 19:55:45 -07:00
Teknium ff4d896e50 refactor(agent/relay,transports): fold docstring whitespace (text unchanged) 2026-09-02 19:49:06 -07:00
Teknium 46f696c48b refactor(agent/relay,transports): anthropic build_kwargs default table + thinking-type set; compact accumulator/logical-scope plumbing 2026-09-02 19:43:35 -07:00
Teknium e58175139d refactor(agent/relay): drop _safe in favour of _warn_on_error/suppress; pack spans to 110 cols; strip intra-function separator blanks 2026-09-02 19:24:48 -07:00
Teknium 706a507806 refactor(agent/transports): lift _pareto_score, fold reasoning on/off ladder in legacy chat_completions path 2026-09-02 19:10:10 -07:00
Teknium 0d04e1b5c7 refactor(agent/transports): lift codex _reasoning_fields, cc _normalize_tool_call/_attr_or_model_extra, unify approval routing; trim module docstrings 2026-09-02 19:07:07 -07:00
Teknium b6f60bf123 refactor(agent/transports): merge token-usage/compaction accounting into one handler, contextlib.suppress for pass-except blocks, lift extra_content dump 2026-09-02 18:54:23 -07:00
Teknium be3a659b14 refactor(agent/relay): compact relay/transport docstrings and comments (keep every invariant); reflow boolean spans; drop no-op helpers 2026-09-02 18:53:45 -07:00
Teknium 18e73f891e refactor(agent/transports): trim narrative docstrings/comments in codex, chat_completions, app-server session (WHYs kept) 2026-09-02 18:49:33 -07:00
Teknium a560fd840c refactor(agent/relay): fold execute/execute_async invoke into _ManagedAttempt; stream() = ManagedLlmStream; codec tool normalizer table; plugin acquire preflight/activate split; pack call/signature spans 2026-09-02 18:35:48 -07:00
Teknium 8dad1f6de5 refactor(agent/transports): split run_turn into _run_started_turn, single-predicate scope check, tighten apply_patch/compaction helpers 2026-09-02 18:30:59 -07:00
Teknium a0cc8cdb25 refactor(agent/transports): drop _Pending/_take_id and __enter__/__exit__ shims, lift file-change summary + scope-id helpers, tighten projector/bedrock/types/vertex 2026-09-02 18:26:51 -07:00
Teknium 0e66a40d09 refactor(agent/transports): collapse chat_completions sanitize/base-kwargs helpers and codex build_kwargs plumbing; wire output fuzz-identical 2026-09-02 18:21:51 -07:00
Teknium c94ced6225 refactor(agent/turn): AST-neutral bracket/signature packing across r3-08 slice 2026-09-02 18:01:27 -07:00
Teknium d2b3e545cb refactor(agent/transports): shared codex turn driver, build_kwargs phase helpers, dispatch tables in projector/accumulator, base finish-reason mapping 2026-09-02 13:29:48 -07:00
Teknium 2a0605a807 fix(agent): reasoning-off continuation reaches the wire on the legacy chat path; reset one-shot flag per turn
Follow-up to the #99622 salvage:
- agent/transports/chat_completions.py: the legacy (no provider profile)
  chat_completions path always re-emitted extra_body.reasoning with
  enabled=True, so both reasoning_effort: none and the one-shot
  length-continuation override went out as {enabled: true, effort: none}.
  Honor enabled=False / effort=none the way the profile path does.
- agent/conversation_loop.py: reset agent._ephemeral_reasoning_off at
  turn start so a flag armed by an interrupted/errored turn can never
  strip thinking from the next turn's first request.
- User-facing hints now name the real slash command (/reasoning); the
  /thinkon//thinkoff commands do not exist.
- tests: wire-level regression (continuation request carries
  reasoning.enabled=false) and a stale-flag turn-scope test.
2026-09-02 00:55:42 -07:00
Lakshya Agarwal 428e084dcd feat(web): add Tavily web search and extract provider
This commit re-introduces the Tavily provider, which supports both search and content extraction capabilities, which was removed in #99199.
2026-09-01 10:56:49 -07:00
CoolStar aaca343110 fix(agent): preserve Bedrock redacted reasoning replay 2026-09-01 08:30:26 -07:00
joaomarcos 9d3f1de994 fix(anthropic): alias session_search/memory OAuth billing-classifier triggers
Anthropic subscription OAuth (claude_code credential) misroutes Hermes
sessions carrying the session_search or memory toolset into the
extra-usage lane, surfacing as HTTP 400 "You're out of extra usage" on
a valid subscription. Live-verified via the
anthropic-ratelimit-unified-representative-claim response header
(deterministic lane oracle, no dependency on the laggy usage counter):
tool schemas are innocent, the trigger is three specific system-prompt
sentences (session_search recall + two skill_manage sentences),
required jointly — breaking any one clears the classifier.

Two independent layers:
1. OAuth wire alias (anthropic_adapter.py, transports/anthropic.py):
   session_search -> chat_history_lookup, memory -> context_notes in
   tool name, description, and (session_search only) system-prompt
   prose, with wire-collision guarding and a normalize_response
   reverse-map that keeps GH-25255 registered-tool precedence. Also
   routes named tool_choice through the same normalizer, closing a gap
   where a forced tool_choice would leak the raw trigger string and
   stop matching tools[].
2. Prompt-preserving reword (prompt_builder.py): rewords the two
   triggering SKILLS_GUIDANCE sentences while keeping the same
   meaning, still naming skill_manage, and leaving the Skill Safety
   Rule section untouched. Applies to all auth paths since it's a
   prompt-copy change, not a wire-level transform.

Two layers rather than one because the three-sentence AND-condition
means a classifier tightening could start firing on either remaining
leg alone.

Fixes #65365
2026-09-01 16:27:20 +05:30
Teknium 7beb0de676 fix: follow-up for salvaged PR #71904 — source raw inbound id, strip persistence key from the wire
- Thread event.message_id (raw inbound id) as TurnContext.inbound_message_id
  instead of reusing event_message_id, which is the reply/thread anchor and
  can be the replied-to message on Slack/Mattermost/Buzz or None for
  Telegram topics.
- Add platform_message_id to the schema-foreign strip sets in
  ChatCompletionsTransport.convert_messages and the summary path so strict
  providers never see the persistence-only key.
2026-08-31 12:46:32 -07:00
Teknium b7ebe6456f fix(xai): request-local alias provenance + collision-safe wire aliasing
Hardens the two #95003 alias carriers per review feedback on #95019/#95011:

- _alias_reserved_tools / _rename_tool_search_bridge_for_xai now return the
  alias map THIS request emitted; the transport stashes it
  (_last_wire_aliases) and normalize_response reverses ONLY those aliases.
  A real user/plugin/MCP tool named hermes_tool_search is never silently
  dispatched as tool_search when no alias was sent.
- Collision safety: if a real tool already occupies the alias name, the
  bridge takes hermes_tool_search_2/_3 — no duplicate wire declarations.
- Legacy static reverse map retained only for normalize-only call sites
  that never built a request on the transport instance.
- chat_completion_helpers resets provenance per request so stale maps from
  a prior request can't leak into the next response's dispatch.

Refs #95003
2026-08-31 10:09:04 -07:00
liuhao1024 5e2f8b9865 fix(xai): alias the reserved tool_search bridge name on chat completions
xAI's chat-completions API reserves the function name tool_search for
its native server-side tool and rejects the whole request when the
client Tool Search bridge declares it (HTTP 400 'The function name
tool_search is reserved for the tool_search tool', #95003) — Grok
providers were unusable whenever the bridge assembled into the payload
(default tools.tool_search: auto). Mirror the web_search treatment in
transports/codex.py: rename the bridge's wire declaration to
hermes_tool_search for xAI targets (deep-copied first, #27907 lesson)
and map the alias back to tool_search in normalize_response so dispatch
is unchanged. Alias matches the Codex-side fix for the same class
(#83122).
2026-08-31 10:09:04 -07:00
David Zhang de123be524 fix(xai): alias the reserved tool_search bridge on the wire (#95003)
xAI reserves the function name `tool_search` for Grok's native
server-side Tool Search and rejects the client declaration outright:

    HTTP 400 {"code":"invalid-argument","error":"The function name
    tool_search is reserved for the tool_search tool"}

Hermes's progressive-disclosure bridge registers exactly that literal
(`TOOL_SEARCH_NAME` in tools/tool_search.py) and assembly is not
provider gated, so with the default `tools.tool_search.enabled: auto`
every grok turn fails the moment the catalog crosses the threshold —
mid-session, which reads to the user as a session reset.

Same treatment as the two collisions already handled on this
transport (xAI `web_search` #48108, OpenCode reserved names #85589):
alias to `hermes_tool_search` on the wire in build_kwargs, map back in
normalize_response so Hermes dispatch and the bridge contract are
untouched. `tool_describe` / `tool_call` are not reserved by xAI and
are left alone.

Folds the per-provider rename helpers into one `_alias_reserved_tools`
owner parameterized by the reserved-name tuple, and extends the
existing `_RESERVED_ALIAS_TO_NAME` reverse map so the dispatch-side
un-aliasing needs no new branch.

Scope note: this covers the Responses transport, which is where every
api.x.ai route lands by default (`_fallback_api_mode` maps api.x.ai →
codex_responses, and the xai provider profile declares it). An xAI
model forced onto `api_mode: chat_completions` would still hit the
400; that path has no provider-specific tool rewriting today and would
need the symmetric hook in agent/transports/chat_completions.py. Happy
to add it here if you'd rather have both in one change.

Tests: new TestXaiReservedToolSearchAlias covering the wire alias,
non-xAI backends keeping the canonical name, composition with the
native web_search swap, and the normalize_response round trip.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012vLaAmnsdii3Gm9jMDs5gw
2026-08-31 10:09:04 -07:00
Teknium d6773cf26f refactor: remove the Tavily web backend; keyless ring is exa/parallel/firecrawl/keenable
- Tavily plugin deleted (plugins/web/tavily), keyless endpoints and
  ring entry removed from keyless_mcp, legacy backend set / credential
  ladder / preference walks / rescue key map scrubbed.
- TAVILY_API_KEY deregistered across config, setup, status, dump, and
  nous_subscription surfaces. The tvly- redaction pattern stays --
  legacy keys in user envs still deserve masking.
- Sibling test pins migrated (keenable/exa stand in where tavily was
  the fixture vendor); tavily test suite deleted.
- Docs updated: web-search, configuration, integrations,
  environment-variables, tools-reference, web-dashboard, provider
  plugin dev guide.

Live-verified from an isolated HERMES_HOME with all web creds blanked:
zero-config resolution lands in the 4-vendor ring, live keyless ring
search succeeds, no tavily anywhere in resolution order.
2026-08-31 00:56:41 -07:00
kshitijk4poor 1c5ee5815f fix(router): pytest guard on caps warmer + debug log in fail-open efforts lookup
Review findings on salvaged #93548: _warm_efforts_async now returns
early under PYTEST_CURRENT_TEST (matching the canonical OpenRouter caps
warmer) so a test that forgets to monkeypatch it can't fire live HTTP
when RAMP_ROUTER_API_KEY is set; the codex transport's fail-open
except in _profile_declared_efforts logs at debug instead of silently
swallowing profile-hook bugs.
2026-08-29 20:29:04 +05:30
Neel Patel eeb7916000 review: host-resolved efforts, ladder-validated ingest, deduped catalog
Addresses the automated review on this PR:

- _profile_declared_efforts falls back from provider name to the
  endpoint's host (via model_metadata's URL->provider map), so a named
  custom provider pointed at api.router.com — which the host mandate
  already routes onto this transport — gets the catalog clamp instead
  of the default vocabulary and a Router 400.
- _parse_efforts validates catalog levels against EFFORT_LADDER at
  ingest, logging and dropping unrecognized tiers; a model whose whole
  vocabulary is unrecognized stays out of the map (transport defaults)
  instead of passing the requested effort through unclamped.
- fetch_models dedupes ids while preserving Router's deliberate listing
  order.
- plugin.yaml credits the human contributor per repo convention.
2026-08-29 20:29:04 +05:30
Neel Patel 804f8b4732 feat(providers): add Ramp Router (router.com) provider plugin
Ramp Router is an OpenAI Responses-compatible LLM gateway at
https://api.router.com/v1 that routes each request across upstream
providers (OpenAI, Anthropic, xAI, Fireworks, ...) with server-side
fallbacks and spend controls. Nous asked for a PR adding it as a
provider, so:

- plugins/model-providers/router/: RouterProfile plugin —
  api_mode=codex_responses, RAMP_ROUTER_API_KEY auth,
  RAMP_ROUTER_BASE_URL override, live account-scoped catalog via
  GET /v1/models (no hardcoded fallback_models: IDs are key-scoped and
  Router's docs mandate runtime catalog reads).
- hermes_cli/providers.host_mandated_api_mode +
  runtime_provider._detect_api_mode_for_url: api.router.com ->
  codex_responses. The host is Responses-only — POST /v1/chat/completions
  does not exist and 404s — so this is a genuine host mandate (exact
  hostname match per #32243, mirroring the api.meta.ai precedent).
- providers/base.py: new overrideable supported_reasoning_efforts(model)
  hook (tri-state: None=defer, ()=model takes no reasoning params,
  tuple=clamp set). Router validates reasoning.effort per model and
  returns HTTP 400 invalid-argument on levels outside the model's
  published vocabulary, and 400 unsupported_parameter when a
  non-reasoning model receives any reasoning field (both verified live).
  The profile answers from a cached copy of the catalog's
  router.capabilities.reasoning block: cache-only on the hot path,
  seeded for free by fetch_models(), disk-mirrored across processes
  (/cache/router_catalog.json), background-warmed when cold
  — same design as the OpenRouter reasoning-caps clamp on the chat path.
- agent/transports/codex.py: consult the profile-declared vocabulary in
  the generic effort-clamp branch (xai/actual/github branches untouched;
  profiles that do not override the hook see no behavior change).
- cli-config.yaml.example + adding-providers.md + providers/README.md:
  document the provider, the host mandate, and the new hook.
- tests: behavior contracts for the host mandate/URL detection/spoof
  rejection, profile registration + auth auto-registry wiring, catalog
  parsing, and transport clamp/suppression/fallback paths.

Verified live against api.router.com (Aug 2026): one-shot chat,
streaming SSE, tool calls + parallel_tool_calls, encrypted-reasoning
replay on OpenAI-served models, function_call_output follow-up turns on
OpenAI- and Fireworks-served models; store:false / prompt_cache_key /
include:[reasoning.encrypted_content] / reasoning.summary accepted
across backends; effort clamp confirmed to convert a would-be 400
(xhigh on o3) into a successful request via the disk mirror.
2026-08-29 20:29:04 +05:30
Teknium 3951ead838 fix(cache): over-length caller prompt_cache_key no longer 400s Chat Completions requests
Port from anomalyco/opencode#44571: OpenAI caps prompt_cache_key at 64
chars (DeepSeek and Zai inherit the same limit via their OpenAI-compatible
APIs) and rejects longer values with HTTP 400. The Responses transport
already bounds keys via _bounded_prompt_cache_key, but the Chat
Completions transport passed caller-supplied keys (request_overrides,
top-level or extra_body) through unmodified on both the profile and
legacy kwargs paths.

Bound caller keys with the same pck_<sha256[:24]> hash shape codex.py
uses so both transports behave identically; blank keys are dropped
instead of sent empty. Hermes-generated keys were already safe
(content-addressed pck_ hashes).
2026-08-29 11:33:05 +05:30
kshitijk4poor 5885289c47 refactor(codex): route transports _pair_ids through shared fc_ canonicalization
The reuse reviewer found a third copy of the fc_->call_ synthesis in
agent/transports/codex.py _pair_ids (item_id[3:] spelling, which is why
the len('fc_') grep missed it). All three sites now share
_canonical_call_id_from_fc(), keeping the pairing invariant in one place.
2026-08-26 12:58:35 +05:30
Teknium 63a9c26fbe feat(model): Codex GPT slugs default back to 272K; explicit -900k picker variants opt into the verified large window
The Aug 16 change that auto-raised gpt-5.4/5.6 Codex OAuth context to the
live-verified 900K burned through subscription usage for users who never
asked for the larger window (bigger window = more input tokens per request).

- Base Codex slugs (gpt-5.6-sol/terra/luna, gpt-5.4) now resolve to the
  advertised 272K again — the cheaper limit is the default.
- The model picker synthesizes explicit <slug>-900k variants (e.g.
  gpt-5.6-sol-900k) for every live-verified slug; selecting one opts into
  the 900K window. Slugs that genuinely enforce 272K (gpt-5.5,
  gpt-5.4-mini) get no variant.
- The -900k suffix is Hermes-side only: stripped before the model id hits
  the wire (main transport + auxiliary Responses adapter), and pricing
  aliases the variants onto the base entries.
- Docs: new opt-in section in context-compression-and-caching.md.
2026-08-23 02:14:35 -07:00