Gate C11 r4 quality: the `flags &= {True, False}` set filter let YAML
`1` count as an opt-in because 1 == True in a set. Keep only bool values
so a stray 1/0 never promotes private reasoning. New parametrize row
(acme-int, value 1) is red without this.
Gate C11 r4 2c: startup, gateway and TUI build the agent with
provider="custom" and the named identity in requested_provider; only a
/model switch sets provider to the custom:<slug>. Matching entries against
agent.provider alone left the live-entry set empty at startup, so an
unflagged sibling on a shared endpoint still inherited the opt-in and a
sibling's false cancelled the provider that opted in. Collect the
custom:<slug> identity from both fields. The acme-plain parametrize row now
uses the startup shape (red before this change) and one opted-in row pins
the positive startup path.
Gate finding (C11 r3 quality, Low): 5769ff4aa9 removed the only writer of
runtime_capabilities["answer_in_reasoning"] (the agent_init seed); every
remaining writer stores resolve_native_compaction_capabilities(), which
yields only native_compaction. The reader was an unconfigurable second
trust source that could override the live config read, reachable only
from a test seam. The test now opts in the way users do, through a
custom_providers capabilities block on its base_url.
Also import _entries_for_route from hermes_cli.config like its neighbour.
Gate finding (C11 r3, Low): the provider-level loop returned the first
entry on the base_url carrying an answer_in_reasoning bool, whatever
provider was live. Two providers: entries on one endpoint (LiteLLM/vLLM
router) leaked one's opt-in to the other, and an earlier sibling's true
overrode the live entry's explicit false (probe: vllm-nemo true + vllm-ds
false on one URL, live custom:vllm-ds -> True).
Match the live custom:<slug> via custom_provider_slug, the helper that
derives that identity from an entry. With no slug match (bare 'custom'),
trust only when every flagged sibling on the endpoint opts in.
The provider-level `capabilities:` block is no longer handed to the agent
by the gateway; the promotion gate re-reads it on the live route in CLI,
TUI and gateway alike. Say so, and that it survives /model on the same
provider but is not inherited by fallback or other providers (OpenRouter
never trusted) (fold2 finding 1).
52e8ecd495 merged the constructor `capabilities=` answer_in_reasoning bool
into runtime_capabilities at startup so a provider-level opt-in reached
the promotion gate. The gate now re-reads the provider-level
`capabilities:` block on the live route (previous commit), which covers
CLI/TUI and /model switches the seed never did, so the seed is redundant.
Forward removal, not a revert: 52e8ecd495's test coverage stays, but the
fixture now opts in through the custom_providers entry-level
`capabilities` block instead of the constructor (fold2 finding 1).
The provider-level `capabilities: {answer_in_reasoning: true}` block only
reached the promotion gate through the constructor `capabilities=` arg,
which only the gateway passes. CLI and TUI never pass it, and every
/model switch rebuilds runtime_capabilities without it, so the documented
provider-level opt-in was silently ignored on CLI/TUI and lost after
/model in the gateway (fold2 finding 1, 2c review).
Read the entry-level block live, like the per-model key: when no
per-model capability is set, scan the custom_providers entries serving
the live base_url. It now holds on any model of that provider, is never
inherited by a fallback on another base_url, and OpenRouter stays
untrusted. The trusted-route test opts in through the entry-level block
with no constructor capabilities and gains /model-switch and fallback
rows (the first two are red without this change).
Reasoning-only clean stops are now promoted to the reply only on trusted
routes, so a local parser that puts the answer in `reasoning` needs an
explicit opt-in. Document the per-model key and the provider-level
`capabilities:` block next to prompt_caching, plus the route scoping
(no fallback inheritance, OpenRouter never trusted). Finding from the 2c review.
The exhaustion test pins an OpenRouter route, where the promotion gate
returns False before it reads runtime_capabilities, so setting
answer_in_reasoning=False there changed nothing (quality review). Also
collapse the leftover 3-5 blank-line runs to two.
The live-trust refactor dropped the writer of
runtime_capabilities["answer_in_reasoning"] but kept its reader, so an
explicit opt-in passed as AIAgent(capabilities={"answer_in_reasoning": True})
(what _lift_model_capabilities builds from a provider-level `capabilities:`
block and gateway/run.py passes through) never reached the gate and private
reasoning-only stops on that route were retried instead of promoted.
Seed it into runtime_capabilities at startup, merged into the existing
expression so agent_init.py does not grow past its size cap. The opt-in is
scoped to the primary route: a fallback rebuild drops it and the primary
restore brings it back from the snapshot. The fixture now opts in through
the constructor and the trusted-route test gains a constructor-opt-in row
(red without this change).
The code-health ratchet blocks growth of agent_runtime_helpers.py
(3909), agent_init.py (2527), chat_completion_helpers.py (4122) and
finish_text_response (309 lines); the gate added 60+ lines to those
facades.
Move answer_in_reasoning_capability into a topical sibling and evaluate
it from the agent's live route at the promotion site instead of caching
the decision in runtime_capabilities. That removes the plumbing at
startup, primary snapshot/restore, switch_model and fallback activation:
a live check cannot go stale across a route change, so the whole
sibling-site class is covered by construction. The unused constructor
`capabilities={"answer_in_reasoning": ...}` hook goes too (no caller
sets it); an explicit runtime_capabilities bool and the
custom_providers per-model opt-in still work.
Keep two behavioural invariants for the route gate: an untrusted
OpenRouter/DeepSeek route retries past private reasoning to the visible
answer while the local Nemotron parser route still promotes in one call
(one parametrized test), and exhausted recovery never echoes private
reasoning. The capability-helper, constructor-plumbing and fallback-
restore unit tests duplicate what those end-to-end paths already cover.
get_custom_provider_model_capability already returns None when the
config cannot be read, so the try/except around it in
answer_in_reasoning_capability only hid real bugs.
_terminal_empty no longer returns site_copy("reasoning_only") with a
reasoning preview, and nothing else references that entry, so remove it
instead of leaving dead copy behind.
A clean-stop response with empty content and a reasoning payload was
promoted to the visible answer on every route. A field name is not
provenance: OpenRouter, DeepSeek and other adapters put private
chain-of-thought in `reasoning`, so users saw the model's private
thoughts as the reply (#111761, #114082). Exhausted recovery also echoed
a 500-char reasoning preview.
Promotion now requires a trusted route: an explicit
`answer_in_reasoning` runtime capability, a custom_providers per-model
opt-in, or the local Nemotron-3.5-Lightning parser route from #109205.
The decision lives in runtime_capabilities and is re-derived at startup,
fallback activation, primary restore and model switch. Exhausted
recovery returns the empty sentinel without a reasoning preview.
Rebuilt by hand on current main (keeps the Anthropic signed-thinking
skip and the _refund_api_call import added since the PR's base).
Salvaged from #112833 (a339569d77, 15a19b2fc0, 1d240e7b24).
Review on #132378 (@andrexibiza) showed the regression oracle was the net pack
count: with foreground auto-GC (gc.auto=1, autoPackLimit=1, autoDetach=false)
a guard with the override removed still made two lazy fetches and left the
count at 2 -> 2. The test now captures Trace2 around the assessment and
requires zero fetch child starts, pins global/system git config, and runs
plain and foreground-GC variants; removing the override fails both.
The cherry child's environment now comes from noninteractive_git_env() like
the other no-lazy-fetch callers, instead of a raw os.environ copy that the
spawn-env guard rejects.
`_assess_parked_branch_switch` still ran `git cherry origin/<target>` whenever the
commit-graph count found parked-only commits. On a tree:0 partial clone that
patch-id walk lazy-fetches a tree batch per upstream commit, and nothing bounded
it: the #131444 trace identifies exactly this child (`git cherry origin/main`,
6 h 45 m, 332 packs / 180 GiB) as the writer behind the silent disk runaway.
Run the refinement with GIT_NO_LAZY_FETCH=1 (the NO_LAZY_FETCH_ENV every other
read-only updater probe already uses). A missing object now fails `git cherry`
fast and the conservative rev-list count stands in, so the guard can never turn
into a fetch loop; full clones keep the patch-equivalence refinement.
Test: a reachable promisor remote, a parked branch one commit ahead — the guard
must not add a single pack. Red on origin/main and on #124777 alone (4 packs
after vs 2 before), green here.
Refs #131444. Supersedes the bound/offline variants in #125529, #126693, #128335.
git cherry's patch-id walk needs upstream-side trees, which a tree:0
partial clone lazy-fetches in many promisor batches; one failed batch
made the guard call a clean checkout unverifiable and skip the update
(#124767). Count parked-only commits with rev-list (commit graph only)
first, keep cherry as a refinement, and degrade a cherry failure to the
conservative commit count instead of unverifiable.
Adopts plastic-labs/honcho#1203: the plugin sends X-Honcho-Host and
X-Honcho-Plugin on its Honcho client. No capability changes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Normalizes 'Disclosure:' to 'Disclosure —' and appends the reviewed note on the system-prompt section, tool count and remote MCP behaviour (salvage of #133564).
Prepends 45 verified first-person stories of Hermes Agent used at work
(companies, agencies, practices, shops and solo operators) to
userStories.json. Every quote is verbatim from the linked public source.
No existing entries are changed or removed.
Co-authored-by: witcheer <208820874+notwitcheer@users.noreply.github.com>
The module docstring still said only explicit per-provider config sits
above the platform store; platform_ssl_context() now honours an exported
SSL_CERT_FILE bundle in addition to it.
Fold3 finding 3 (quality Low).
