## Why
The model provider does not reliably identify which curated plugin catalog is
available. ChatGPT authentication can be used with a custom provider, while an
unauthenticated session should use the API-compatible catalog regardless of its
provider.
## What changed
- Select the ChatGPT curated catalog only for authentication modes that use the
Codex backend; use the API curated catalog for API-key and unauthenticated
sessions.
- Initialize standalone plugin managers with the current authentication mode
across CLI, app-server, MCP, and external-agent migration paths.
- Preserve authentication mode while detecting and importing migrated plugins.
## Testing
- Cover catalog and skill routing across ChatGPT, API-key, unauthenticated,
Bedrock, and custom-provider configurations.
- Verify authenticated plugin migration uses the ChatGPT curated marketplace.
GitOrigin-RevId: 660a339ee8891c33aad961078d3a979242a6a166
## Why
Transient executor disconnects could leave capability discovery and skill catalogs
stuck on a cached failure for the rest of a thread, even after the executor
reconnected.
## What changed
- Replay capability discovery after executor recovery and retry transient failures
on later requests while continuing to cache permanent failures.
- Avoid caching skill catalogs produced from failed discovery so a later step can
load the recovered catalog.
- Mark the MCP runtime dirty when recovered manifests change the projected MCP
servers, and allow discovery to be cancelled with the turn.
## Testing
- Cover same-request recovery after a disconnect and recovery on a later request.
- Cover retry classification through connection-attempt errors and skill catalog
caching after discovery recovers.
GitOrigin-RevId: a57f90844351e73ea831931f72a9ddc4e4f3335c
## What changed
Clarify that commits created through a GitHub app or plugin must include the
Codex co-author trailer in the tool's `message` argument. This covers commits
that create, update, or delete files.
GitOrigin-RevId: 58be9302da9f8d4f11aa100c32f779fac9cc05e9
## What changed
- Add a configurable renderer that converts conversation messages, agent
messages, tool calls and outputs, and reasoning into a numbered plaintext
transcript.
- Keep only relevant readable content, including manual-approval developer
messages, while omitting media payloads, encrypted content, and unsupported
response items.
- Limit transcripts to the most recent 320 KiB without splitting UTF-8
characters.
## Testing
- Cover source selection, content filtering, tool-name correlation, and bounded
UTF-8 truncation with unit tests.
GitOrigin-RevId: e2c6535f4a895862ca744258399fb36fc92e42c6
## What changed
- Register a tool lifecycle contributor when Guardian V2 is installed.
- On tool start, asynchronously ask the existing Luna sampler for a low-effort
`action_risk` score constrained to the range from `0.0` to `1.0`.
- Bound the tool metadata supplied to the classifier and treat it as untrusted
input.
- Emit an extension warning if classification sampling fails.
## Testing
Add an integration test that verifies the contributor reuses the configured
Luna pool and sends the expected model, attribution metadata, reasoning effort,
strict output schema, and tool-call context.
GitOrigin-RevId: 6b69fcc0443086544086849c38bcdd90560a291f
## What changed
- Prewarm two Responses WebSocket connections and grow the pool on demand, up to eight connections, so overlapping samples can run concurrently.
- Lease each connection to a single sample and return healthy connections to the idle pool after completion.
- Replace closed or 55-minute-old connections and retry a sample once after a retryable or stream error.
- Keep the sampler available when the second prewarm connection cannot be opened.
## Testing
- Cover connection reuse, partial prewarm success, concurrent pool growth, and retrying an expired connection on another warm connection.
GitOrigin-RevId: 3ee7b05adc00a2135ba7cb35f6e4455199bf3784
## What changed
- Add a shared, read-only `ConversationHistorySnapshot` capability to the extension API.
- Include the snapshot in `ToolStartInput`, preserving conversation order while excluding contextual user messages.
- Avoid acquiring a history snapshot when no tool lifecycle contributors are registered.
## Testing
- Verify snapshots share existing response items, remain stable as history changes, and filter contextual user messages.
- Verify tool-start callbacks receive the history available for successive tool calls.
GitOrigin-RevId: 822cae33781dd876ea628f104be08d8a449a4900
## Why
Structured output can be complete before the Responses stream emits its terminal
events. Waiting for those events unnecessarily delays the sampler and can leave it
waiting after usable output has arrived.
## What changed
- Return a Luna sample as soon as accumulated text deltas parse as a complete JSON
object.
- Continue draining the remaining response events in the background so the
authenticated WebSocket stays reusable for subsequent samples.
- Enforce the output-size limit while accumulating deltas on the early-return path.
## Testing
- Cover returning complete JSON without terminal response events.
- Verify that early return still allows the authenticated WebSocket to be reused.
GitOrigin-RevId: 80c9963f1540f7862356aaad3503e3071a8fb92a
## What changed
- Add a `LunaSampler` that opens an authenticated Responses WebSocket and reuses it for structured, tool-free `gpt-5.6-luna` requests.
- Carry the host's provider, authentication, proxy, attribution, and service-tier configuration into the connection and requests.
- Require strict JSON schemas, preserve per-request reasoning effort and turn metadata, and reject missing or oversized output.
## Testing
- Add a WebSocket test covering authentication and attribution headers, connection reuse, structured request fields, per-turn metadata, reasoning effort, and returned output.
GitOrigin-RevId: aef85fd8ddcfcb7c76a9ede0d3191e3a0321656b
## What changed
- Add a `SecurityRiskScore` rollout item containing a category and numeric score.
- Persist the item in both thread history modes while excluding it from model context, user-visible thread history, search text, forks, and reconstructed conversation history.
- Re-export the score type from the extension API.
## Testing
- Cover serialization, persistence and loading, thread history projection, session reconstruction, append planning, and memory filtering.
GitOrigin-RevId: 1926fe366aeaa75052708a6da589f45a38eefb52
## What changed
- Add dedicated coverage for explicitly starting a queued item that a prompt hook rejects.
- Verify the rejected item is consumed and no model request is sent.
- Keep the automatic queue dispatch test focused on consuming a rejected item while allowing later queued input to proceed.
GitOrigin-RevId: e01cefb9d8581b0d4be05d4595f279d61e628e83
## What changed
- Add the `codex-guardian-v2` crate with an extension install entry point that does not register contributors yet.
- Register the crate in the Cargo workspace and add its Bazel target.
GitOrigin-RevId: 7c0c9479c6722d65f0f0dad9b0fd4a756e4649b3
## What changed
- Add `TurnInputRequest` and typed submission results for atomically starting a turn, steering the active turn, or declining input with a specific reason.
- Expose `start_or_steer_turn`, `start_turn_if_idle`, and `steer_turn` on `CodexThread`, and migrate Core consumers to these APIs.
- Make app-server `turn/start` steer an active regular turn and return that turn's ID. Reject incompatible output schemas and non-steerable turns without applying settings or enqueueing input.
## Testing
- Cover concurrent start-or-steer submissions, accepted and rejected settings updates, output-schema compatibility, idle-start rejection, and app-server steering.
GitOrigin-RevId: dd9b5528d76ec650c019e97af420bc13190ea86a
## Why
Executor-backed skills can include bundled scripts, so skill readers need the
skill directory in the executor filesystem to locate them.
## What changed
- Add `skill_root` to `skills.read` responses for executor-backed skills.
- Derive the root from the parent directory of the skill's main resource and
omit the field for other skill authorities.
## Testing
- Verify executor skill reads return the expected root for both `SKILL.md` and
a referenced resource.
GitOrigin-RevId: b7035c7e2e62155890795fb508fefe3a1c17805b
## Why
Skill catalogs can present shortened package locators, but callers previously had
to expand those aliases before reading a skill.
## What changed
- Resolve catalog aliases automatically when `skills.read` looks up a
model-visible executor or orchestrator skill package.
- Update skill prompts and tool documentation to tell models to pass the listed
package locator directly.
## Testing
- Exercise reading an executor skill through its shortened package locator when
the skills catalog exceeds its context budget.
GitOrigin-RevId: d1cdfd64002510b616146929deb5b7077850b951
## What changed
- Add `http_headers_helper` configuration for local streamable HTTP MCP servers. The configured shell command runs once per connection and returns a JSON object of headers that is cached across requests.
- Apply helper headers to MCP startup and OAuth flows while restricting them to the server origin, stopping redirects, rejecting reserved or duplicate headers, and enforcing output and execution limits.
- Reject helpers for remote or managed-disabled servers, use the local environment working directory, and redact helper commands from `codex mcp list` and `codex mcp get` output.
## Testing
- Cover configuration validation, helper lifecycle and output parsing, origin isolation, OAuth discovery and token refresh, managed requirements, environment selection, and CLI redaction.
GitOrigin-RevId: 84e0e26ce75520b0869d37c72b1678e033bd6818
## What changed
- Mark developer messages received from clients with `client_authored` harness
metadata when `retain_client_developer_messages` is enabled.
- Carry that provenance through pending input and persist it alongside rollout
response items without adding it to provider requests or the serialized
`TurnInput` payload.
- Preserve existing behavior for unannotated response items and when the
feature is disabled.
## Testing
- Cover client item injection before and during turns, additional application
context, rollout replay, image resize notices, and serialization boundaries.
GitOrigin-RevId: f385c177732becde732272e4b8440eb91f5c1039
## What changed
- Add the `lru_plus_lexical_v1` selector, combining the 50 most recent skills
with weighted lexical matches through reciprocal rank fusion.
- Include the combined selector in the shadow-selection experiment and propagate
query and candidate truncation metadata from both inputs.
- Generalize the existing reciprocal-rank fusion helper to accept a rank
constant while preserving the existing lexical/character selector behavior.
## Testing
- Cover lexical-only selection, merging recent and matching skills, promotion
from agreement between both rankings, and weak overlaps.
- Extend the skills extension test to verify invocation metrics for the new
selector alongside `lru_v1`.
GitOrigin-RevId: 1b7b82bc97ea919c719cd05a009351b701019306
## What changed
- Track the 50 most recently invoked skills for each thread and evaluate them
as the `lru_v1` shadow-selection method.
- Filter stale and duplicate entries while preserving recency order.
- Increase the shadow result limit to 50 and add a `21_50` rank bucket.
## Testing
- Add unit coverage for recency refresh, eviction, filtering, limits, and rank
buckets.
- Add an extension test showing that `lru_v1` recovers a skill invoked on an
earlier turn.
GitOrigin-RevId: 7aa56514db57cf180cc3f57b4d493dee3304e766
## Why
Executor skills required a `skills.list` lookup before their contents could be
read, even when the catalog already identified the skill.
## What changed
- Render executor skill catalog entries as package locators, including shortened
locators when skill roots are aliased.
- Tell the model to pass those packages directly to `skills.read`, while keeping
`skills.list` as the fallback when no package is available.
- Use the shorter package locators when applying the skills context budget.
## Testing
Update catalog, aliasing, budget-pressure, and selected-skill coverage, including
an executor package ID containing a literal backslash.
GitOrigin-RevId: 2ace5e527dc4f29651a8f3214475ccc90d52c73f
## What changed
- Resolve user message admission when Core accepts the input as a new turn or a steer, without waiting for rollout persistence.
- Remove persistence- and hook-specific admission errors and task bookkeeping.
- Delete queued messages after Core accepts them for turn processing, including messages subsequently stopped by a prompt hook.
## Testing
- Update concurrent admission and queue service tests for acceptance-based admission.
GitOrigin-RevId: 7dcc311cfecd3d710733b420f2add546edb86153
## What changed
- Detect executor-owned skill document reads and script executions across native and URI-based working directories.
- Match skills only within the active execution environment while preserving host skill detection for local commands.
- Emit resource-backed implicit invocation events and deduplicate repeated accesses within a turn.
## Testing
- Add unit coverage for document reads, script executions, and environment-scoped matching.
- Add an integration test for environment selection, resource-backed analytics, and repeated-access deduplication.
GitOrigin-RevId: f78a48c3a4766fe8775bd88926b45a76761f6af8
## What changed
- Emit skill invocation analytics when a resource-backed skill is explicitly selected or its main resource is successfully read from the first page.
- Preserve provider-supplied skill IDs and user scope when available, and derive a stable ID from the main resource otherwise.
- Deduplicate repeated implicit reads of the same main resource within a turn.
## Testing
- Extend the orchestrator skill integration test to cover explicit and implicit invocation events, stable fallback IDs, failed reads, and repeated-read deduplication.
GitOrigin-RevId: 7d8453b31b5a2205847e65cda2c46183d6c97b45
## What changed
- Add structured `usageLimitExceeded` metadata to failed image-generation
items, including the image limit ID and optional reset timestamp.
- Preserve the failure metadata in completion events, app-server thread
history, thread reads and resumes, and migrated legacy rollouts.
- Export the new failure type in the generated JSON and TypeScript schemas.
## Testing
- Cover usage-limit responses through item completion, persistence, and thread
resume.
- Verify legacy rollout migration retains image-generation failure metadata.
GitOrigin-RevId: 91c31a2a47456b6b916ee03002ff314b05946dd4
## Why
`skills/list` can load multiple working directories in one request, but bundled
skill discovery did not account for different effective configurations across
those directories.
## What changed
- Resolve `skills.bundled.enabled` from each load input's effective config layer
stack inside the host skills service.
- Include or exclude system-scoped skills for each working directory based on
that resolved setting.
- Keep bundled skills enabled by default when the setting is absent or invalid.
## Testing
- Add a multi-directory `skills/list` test with bundled skills disabled in one
project and enabled in another.
- Add config-layer tests for defaults, overrides, and malformed bundled-skill
configuration.
GitOrigin-RevId: e4e97dc7d0a374ac71d0aa11e55a9e337f661717
## What changed
- Add `goals.max_goal_token_budget` as a positive-integer configuration setting.
- Use the configured maximum as the default budget for new goals and when `tokenBudget` is reset to `null`.
- Reject goal creation and updates whose token budget exceeds the configured maximum, including requests through goal tools and `thread/goal/set`.
- Respect managed configuration precedence and per-thread configuration overrides.
## Testing
- Cover configuration parsing and managed overrides.
- Cover defaulting, resetting, and rejecting oversized budgets through the goal service, goal tools, and app-server API.
GitOrigin-RevId: f8d7e6418cdc237d454c8cf47bb32ba0d44a60cf
## What changed
- Add `codex-history` for model-history and persisted-rollout domain types, including `RolloutItem`, `RolloutLine`, `CompactedItem`, and initial/resumed history state.
- Re-export the persisted types from `codex-rollout` and update consumers to use the new crate boundary instead of `codex-protocol`.
- Preserve existing rollout serialization, including legacy numeric compacted-window IDs.
## Testing
- Add `codex-history` tests for rollout JSON round trips, compacted-history compatibility, persisted history modes, and multi-agent version selection.
GitOrigin-RevId: 944daa9297ddd231d3aebbdcb05fff4adf8b4e1b
## What changed
- Restrict host loading, snapshot, and outcome implementation details to the
skills extension crate.
- Require `HostSkillsLoadInput` construction through its public constructor
instead of exposing its fields.
- Remove redundant implicit-invocation helpers from `SkillLoadOutcome`; use the
`ImplicitSkillLookup` interface for enabled-skill lookup instead.
GitOrigin-RevId: e79c77fc3e69ecc0231b0c87e5f9f24a5487f9e4
## Why
The plugin and skill test suites were excluded wholesale on Windows, even though
most cases do not depend on POSIX behavior.
## What changed
- Make generated TOML and JSON fixtures escape Windows paths correctly.
- Use Windows-safe path canonicalization and normalize advertised skill paths.
- Select test environments through the environment-aware builders.
- Run the suites on Windows while narrowly skipping cases that execute POSIX
commands or require matching host and executor path conventions.
GitOrigin-RevId: aadf31013c2bf9bac728adc4dd96f572d4a3bf3f
## Why
The app server should not need access to host skill root internals to decide
which paths require filesystem watching.
## What changed
- Add `HostSkillsService::watchable_skill_root_paths` to return non-plugin,
non-system skill roots for the watcher.
- Make `HostSkillRoot` and root resolution private to the skills extension.
- Update the app-server watcher to consume the filtered paths directly.
## Testing
Add a host service test confirming that user skill roots remain watchable while
plugin and generated system roots are excluded.
GitOrigin-RevId: b3e3b576e4ffe96230af71d9bf7c6c315b1705d3
## Why
A single `skills/list` request should use one view of shared skill roots across
all requested workspaces while still applying each workspace's skill rules.
## What changed
- Add a request-scoped host skills view that reuses non-plugin root snapshots
across `cwd` entries without persisting them across requests.
- Resolve user-scoped plugin skill roots once per request, then apply workspace
skill configuration separately for each `cwd`.
- Make `forceReload` refresh plugin roots before building the request-scoped
view so subsequent entries see the refreshed skills.
## Testing
Expanded `skills/list` and host skills service tests to cover multiple ordered
workspaces, per-workspace skill rules, request-local snapshots, cached results,
and forced plugin-root refreshes.
GitOrigin-RevId: eedd3a4c3e213b7f30df6cacd3adf23ba2967437
## What changed
- Load an optional package-supplied config file as the lowest-precedence
configuration layer, so every existing layer can override its values.
- Report the layer as `packagedDefaults`, including its source path, through
config diagnostics and the app-server protocol.
- Return an error when a configured packaged defaults file is missing.
## Testing
- Cover precedence across packaged, system, user, and session layers.
- Cover the missing-file error path.
GitOrigin-RevId: 52406890f4d580eedabc90bf2a9ee3affa36fee1
## What changed
- Make `package` the only required argument to `skills.read`, resolving the
owning orchestrator or executor catalog automatically.
- Default omitted `resource` values to the package's main `SKILL.md`.
- Render orchestrator skills as package locators and instruct the model to read
them directly without first calling `skills.list`.
- Update skill extension and app-server coverage for direct main-resource
reads, referenced resources, aliases, and the revised tool schema.
GitOrigin-RevId: 9faf57a8d0935566a15094931eaabaa8f0613e9e
## What changed
- Move `SkillLoadOutcome` and its implicit-path indexing into
`codex-skills-extension`.
- Import shared skill types directly from `codex-skills` and keep the skill
prompt size limit with the extension renderer that uses it.
- Remove `codex-core-skills` from the Cargo workspace and dependent crates.
GitOrigin-RevId: 4e9e84909fa2f692bcc94af990bb4671affd776f
## What changed
- Add `HostSkillsSnapshot::load_skill_prompts` so the skills extension owns reading and rendering selected host skills.
- Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts.
- Remove the legacy prompt injection and fragment implementation from `codex-core-skills`.
## Testing
- Cover prompt truncation without an installed skills extension, skill/plugin ordering, selective provider supersession, unreadable skills, and contextual fragment detection.
GitOrigin-RevId: 9c8b84ad54b90d174abc287ab49cc5a231e9e1aa
## Why
Long executor and orchestrator resource identifiers can consume enough of the
skills context budget to omit otherwise available skills.
## What changed
- Add source-aware root aliases for executor, orchestrator, and host skill
catalogs, including catalogs with a single shared root.
- Select the best combination of aliased catalogs under the shared metadata
budget while accounting for root tables and alias usage instructions.
- Explain how to expand shortened `skill://` locators and accept the resulting
description-shortening warning in app-server coverage.
## Testing
- Add rendering and production-turn coverage for singleton, executor,
orchestrator, host, and combined catalog aliases.
GitOrigin-RevId: c1bc1f3d371eae9526232674060235272cc28f16
## What changed
- Compact executor and orchestrator skill locators under metadata pressure, using provider-specific `e` and `o` aliases alongside host `r` aliases.
- Derive alias roots from executor discovery paths and orchestrator namespaces while preserving host plugin root handling.
- Centralize alias ordering, deduplication, and longest-prefix matching across skill providers.
## Testing
- Cover alias planning, cross-platform executor roots, and host plugin discovery.
GitOrigin-RevId: e7d15bd3891c08ae20170e96c4ad45c76d353707
## What changed
- Define skill config selectors, ordered rules, and layer-stack parsing in `codex-config`.
- Resolve disabled skill paths from generic skill name/path pairs, so configuration logic no longer depends on `SkillMetadata`.
- Update plugin and host skill consumers to use the `codex-config` API and consolidate the rule tests with the skill config tests.
GitOrigin-RevId: 3fe67869708df2652befe28d58cdeba933256f84
## What changed
- Use `HostSkillRoot` throughout host root resolution and loading, including plugin roots.
- Remove the duplicate loader, root snapshot, and product-filtering implementation from `core-skills` now that loading is owned by the skills extension.
- Move and expand loader coverage for discovery, namespaces, filesystem routing, root merging, symlinks, and frontmatter parsing.
## Testing
- Added focused unit and integration tests under `ext/skills` and `skills` for the consolidated loader behavior.
GitOrigin-RevId: 214d06d59bf3033ee0f220ea5959ee4feff66782
## What changed
- Inject the host skill loader into `PluginsManager` so plugin discovery and agent turns use the same loading and product-policy behavior.
- Share plugin skill snapshots across those paths, preserving a consistent view of skills across workspaces.
- Apply migrated-command precedence after product filtering, allowing an eligible migrated command to replace a filtered native skill with the same name.
## Testing
- Add coverage for product-restricted plugin skills, native-versus-migrated command precedence, and the skills exposed to agent turns.
GitOrigin-RevId: f5ef0d0766ebeeb30d73ffaf044d003c2906ea4d
## Why
Converting each environment's working directory to a host-native path caused
turn-input contributors to omit environments with foreign path formats.
## What changed
- Expose `TurnInputEnvironment.cwd` as a `PathUri`.
- Pass every turn environment to contributors without host-path conversion.
## Testing
Added an integration test that submits a foreign working-directory URI and
verifies the contributor receives the environment unchanged.
GitOrigin-RevId: a122526be47f5331614381e9c6e4b85087a96bed
## What changed
- Carry plugin identity, namespace, root, and discovery mode through host skill loading.
- Apply the owning plugin namespace and IDs to loaded skill metadata.
- Respect direct-child discovery for Agent Plugins and reject skills that resolve outside the plugin root or are not regular files.
- Preserve recursive discovery and symlink behavior for legacy plugin roots, and allow the full 64-character namespace plus 64-character skill name.
## Testing
Add host-loader coverage for plugin metadata, namespace ownership, direct-child filtering, path containment, recursive symlinks, shared assets, and maximum-length qualified names.
GitOrigin-RevId: cdde821643ce39bd030d0c3753b3304b75161690
## What changed
- Add a storage-neutral queue extension for listing, adding, editing, reordering, deleting, and explicitly starting queued user messages.
- Dispatch queued messages in FIFO order when a thread becomes idle after a completed turn, while leaving them queued after interruptions or failures.
- Wait for user input to be persisted before removing its queue item, and report hook rejection, task termination, and persistence failures distinctly.
- Snapshot local image and audio attachments into validated data URLs before storing them, enforce input limits, and emit `ThreadQueueChanged` events after mutations.
## Testing
- Cover queue mutations, automatic and explicit dispatch, interruption and failure behavior, hook rejection, invalid records, input limits, and local attachment snapshotting.
GitOrigin-RevId: 14f39d7c8cbaccb767a6da84b82cced0edfcb4b9
## What changed
- Add `transparentBackground` to image-generation items and legacy completion events.
- Map Images API backgrounds to `true` for transparent, `false` for opaque, and `null` for automatic or unavailable values.
- Preserve the metadata in live notifications and persisted or resumed thread history while continuing to deserialize older items that omit it.
## Testing
- Cover transparent, opaque, and automatic backgrounds, including image edits and thread read/resume flows.
- Verify the stable JSON shape and optional TypeScript field.
GitOrigin-RevId: 08527f37f23431df45fab1ed34eb82b2139b49d7
## What changed
- Move the integration test for reusing plugin-manager skill snapshots into
`codex-core`, which owns both the plugin manager and host skills service
integration.
- Keep the `codex-core-plugins` test focused on resolving local and remote
plugin identities on effective skill roots, and remove its skills-extension
dev dependency.
- Use the skills extension's `HostSkillsSnapshot` type in its world-state
catalog implementation.
## Testing
- Verify the host skills service reuses the plugin manager's parsed snapshot
after the underlying skill file changes, while preserving plugin identity
metadata.
GitOrigin-RevId: afc8a0ebccb629360c59a4546bdb9a134c74da4f
## What changed
- Add `session_source()` to `McpServerContributionContext` for thread-scoped MCP resolution.
- Propagate each thread's `SessionSource` through initial setup, per-step resolution, and runtime refreshes.
## Testing
- Verify global contexts omit the source while thread-scoped contexts retain it.
- Verify MCP contributors observe distinct sources for a root thread and its spawned subagent.
GitOrigin-RevId: 23da1509858e023fbd9e2d179034ddc83553f17b
## What changed
- Load ordinary recursive host skill roots with the skills extension's host loader.
- Keep plugin-specific roots on the existing loader so plugin snapshot caching and namespacing continue to work.
- Merge both kinds of root snapshots through the existing precedence and deduplication logic, including discovery paths and source filesystem mappings.
- Move `HostSkillsSnapshot` into the skills extension as the owner of host skill loading.
## Testing
- Cover merged host and plugin catalogs, precedence for symlinked roots, discovery paths, and end-to-end rendering and invocation of host, repository, and plugin skills.
GitOrigin-RevId: c18080afb917c33c57bc17e36b40dd0f3c72d1d7
## What changed
- Move the orchestrator skill catalog from thread context into its own
`orchestrator_skills` world-state section so unchanged catalogs remain
incremental across turns.
- Discover executor, orchestrator, and host catalogs together and render them
against one context-window-aware metadata budget, preserving executor entries
before orchestrator and host entries under pressure.
- Emit catalog metrics and budget warnings when each world-state section is
rendered.
## Testing
- Cover incremental orchestrator catalogs across production turns, combined
catalog budgeting, disabled and unavailable providers, caching, warnings, and
metrics.
GitOrigin-RevId: a0fb25d39dcaf43c978aff9da7972a1206f736e4
## Why
Symlinked skills have a canonical `SKILL.md` path that can differ from the path
under the configured skill root. A catalog entry that advertises the discovery
path must still select the canonical skill.
## What changed
- Track each loaded skill's discovery path alongside its canonical identity.
- Render discovery paths in the skill catalog and accept either form for
structured selections and linked skill mentions.
- Preserve enabled-state checks, deduplication, and product filtering when
resolving discovery paths.
## Testing
Added loader, catalog, mention-resolution, and end-to-end turn coverage for
skills discovered through directory symlinks.
GitOrigin-RevId: bae539b766cc3782c7c121a4276c337699cbb509
willwang-openai