Aggregators republish first-party models under a namespaced id and varying
case, so the shared-model check could not group novita/moonshotai/kimi-k3 with
moonshot/kimi-k3. Matching now ignores one leading namespace segment and case,
which catches that whole class automatically instead of needing an
upstreamModel marker per row.
Declares the tier on the 18 rows this surfaces across baseten, deepinfra, gmi,
novita, nvidia, and together. All are "capable", matching what the runtime
already applied for an absent flag, so behavior is unchanged.
* feat(plugins): catch code-mode drift between catalogs sharing one model
Adds a contract test that groups bundled catalog rows by shared upstream
model and requires every row in a group to declare compat.codeMode once any
sibling does. Rows sharing a model id group automatically; rows under
different ids opt in with the new manifest-only `upstreamModel` marker.
Moves the kimi catalog into its manifest so the scan can see it, and records
the tier reseller catalogs were silently missing as explicit "capable".
* docs: regenerate docs map for the shared-model code-mode section
The moonshot provider already declares compat.codeMode: "preferred" for the
same model (kimi-k3), so tools.codeMode: "auto" engaged code mode on the API
surface but silently skipped the Kimi Code subscription surface (kimi/k3,
kimi/k3-256k). Live proof on kimi/k3: "auto" reported codeModeEngaged=false
while true reported codeModeEngaged=true with "code-mode: cataloged 50 tools
behind exec/wait" and 2 bridge tool calls.
K2.7 (kimi-for-coding*) stays unflagged, matching moonshot's kimi-k2.7-code.
* feat(agents): add per-run stats to embedded agent run meta
Adds codeModeEngaged, assistantTurns, bridgeCalls, and costUsd to
EmbeddedAgentRunMeta.agentMeta and mirrors them on the agent exec --json
envelope. Code-mode engagement is stamped from the tool-surface truth,
round trips accumulate across attempts beside usage, bridge counts come
from the run's tool-search catalog counters, and cost reuses the shared
model pricing helpers (cache tiers included, omitted without cost data).
* fix(agents): accumulate bridge call counts across run attempts
Attempt cleanup clears the per-attempt tool-search catalog, so retries and
fallbacks discarded earlier bridge counts. Fold each attempt's bridgeCalls
into the run accumulator beside assistantTurns and stamp the cumulative
totals into agentMeta, matching the documented per-run contract.
* feat(tools): per-model code-mode capability flags and auto master-switch tier
* feat(anthropic): flag claude-sonnet-4-6 as code-mode preferred
* revert(anthropic): drop claude-sonnet-4-6 from the code-mode preferred set
* test(anthropic): type the manifest compat field in the catalog contract test
* fix(anthropic): carry catalog compat onto hand-built forward-compat model rows
Reject recognizable POSIX and Windows shell source before QuickJS execution while preserving valid JavaScript, TypeScript, syntax errors, standard globals, and real hoisted bindings. Add real-worker regression coverage and adversarial cross-platform stress proof. Fixes#113069.
* feat: normalize web search output contract
* refactor(agents): promote web_search contract from a dedicated output module
* fix(agents): wrap unwrapped web_search text and pass unknown provider payloads through as raw
* fix(agents): gate web_search results branch on conforming rows and cover metadata fields
* fix(agents): gate every provider text path at the web_search boundary
* test(agents): align web_search fixtures with boundary-owned wrapping
* fix(agents): make the web_search boundary own the untrusted-content envelope
* fix(agents): report declared web_search errors first and align the documented contract
* fix(agents): bind envelope stripping to real markers and densify result rows
* fix(agents): emit canonical urls and a closed error code from web_search
* fix(agents): keep structured provider error diagnostics in the wrapped message
* fix(agents): satisfy production export and lint gates for the web_search contract
