@c4a/context-cli 0.7.30 → 0.7.34

package/indexers/release-manifest.json

@@ -1,7 +1,7 @@
 {
   "protocol": "context.indexer.cli-release-manifest/v1",
   "package": "@c4a/context-cli",
-  "version": "0.7.30",
+  "version": "0.7.34",
   "issuer": "context4ai/context",
   "bundles": [
     {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c4a/context-cli",
-  "version": "0.7.30",
+  "version": "0.7.34",
   "type": "module",
   "description": "Local runtime and Agent integration for traceable knowledge production",
   "license": "MIT",
@@ -24,17 +24,17 @@
   },
   "dependencies": {
     "@c4a/agent-graph": "0.3.0",
-    "@c4a/context": "0.7.30",
-    "@c4a/extract": "0.7.30",
-    "@c4a/extract-contract": "0.7.30",
-    "@c4a/extract-go": "0.7.30",
-    "@c4a/extract-mdx": "0.7.30",
-    "@c4a/extract-proto": "0.7.30",
-    "@c4a/extract-rush": "0.7.30",
-    "@c4a/extract-sql": "0.7.30",
-    "@c4a/extract-style": "0.7.30",
-    "@c4a/extract-thrift": "0.7.30",
-    "@c4a/extract-ts": "0.7.30",
+    "@c4a/context": "0.7.34",
+    "@c4a/extract": "0.7.34",
+    "@c4a/extract-contract": "0.7.34",
+    "@c4a/extract-go": "0.7.34",
+    "@c4a/extract-mdx": "0.7.34",
+    "@c4a/extract-proto": "0.7.34",
+    "@c4a/extract-rush": "0.7.34",
+    "@c4a/extract-sql": "0.7.34",
+    "@c4a/extract-style": "0.7.34",
+    "@c4a/extract-thrift": "0.7.34",
+    "@c4a/extract-ts": "0.7.34",
     "@mermaid-js/layout-elk": "0.2.0",
     "commander": "^11.0.0",
     "fast-xml-parser": "^5.10.1",

package/plugins/VERSION

@@ -1 +1 @@
-0.7.30
+0.7.34

package/plugins/claude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "c4a",
   "description": "Start or continue a project-local knowledge workspace through one graph-routed entry.",
-  "version": "0.7.30",
+  "version": "0.7.34",
   "author": {
     "name": "c4a"
   },

package/plugins/claude/commands/context-inspect-search.md

@@ -13,6 +13,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -184,6 +189,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -195,6 +204,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/plugins/claude/skills/context-inspect-search/SKILL.md

@@ -12,6 +12,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -183,6 +188,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -194,6 +203,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/plugins/codex/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "c4a",
-  "version": "0.7.30",
+  "version": "0.7.34",
   "description": "Start or continue a project-local knowledge workspace through one graph-routed entry.",
   "author": { "name": "c4a" },
   "homepage": "https://github.com/context4ai/c4a",
@@ -10,7 +10,7 @@
   "skills": "./skills/",
   "interface": {
     "displayName": "C4A Context",
-    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.7.30",
+    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.7.34",
     "longDescription": "Create a Context workspace and use agent-guided next steps to register sources, run extraction, review candidates, build package outputs, and verify health without silently mutating source repositories.",
     "developerName": "c4a",
     "category": "Productivity",

package/plugins/codex/skills/context-inspect-search/SKILL.md

@@ -12,6 +12,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -183,6 +188,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -194,6 +203,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/plugins/cursor/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "c4a",
   "displayName": "C4A Context",
-  "version": "0.7.30",
+  "version": "0.7.34",
   "description": "Start or continue a project-local knowledge workspace through one graph-routed entry.",
   "author": {
     "name": "Context4AI",

package/plugins/cursor/commands/c4a-context-inspect-search.md

@@ -11,6 +11,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -182,6 +187,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -193,6 +202,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/plugins/cursor/skills/context-inspect-search/SKILL.md

@@ -12,6 +12,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -183,6 +188,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -194,6 +203,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/plugins/skills/context-inspect-search/SKILL.md

@@ -12,6 +12,11 @@ language. The invocation authorizes read-only investigation of the selected
 knowledge packages, available workspace and identified sources within that scope,
 including isolated source retrieval and bounded non-destructive checks. The Skill
 can run from a global installation with host-provided packages and no workspace.
+The ordinary query path is contained in this file. Reuse instructions already
+read in this response; do not reopen them for each stage. When actual delivery
+requires separate host link or response Skills, read their still-unread main
+instructions together once, and open conditional references only for the case
+being handled. Do not prepare delivery that the host's progress mode skips.
 Resolve scope from the request, conversation and configuration before asking.
 Continue through non-blocking issues; ask only for missing access, genuinely
 unresolved scope or effects outside existing authorization.
@@ -183,6 +188,10 @@ Distinguish implementation,
 declared contracts, test assertions, runtime observations and inferences. Perform
 bounded non-destructive validation only when useful; inspect its effects first
 and do not run unrelated scripts, builds or tests.
+Do not turn a symbolic constant or version-like name into a numeric value without
+checking its actual imported definition at the inspected revision. A mock value
+is not the production definition. Keep the symbol when its numeric value is not
+needed; verify the value when the user's concrete boundary depends on it.
 
 Link material actually read: source files at the inspected commit, knowledge
 website articles and original documents. If no reliable clickable link exists,
@@ -194,6 +203,15 @@ appear in source URLs without requiring a separate version audit in the prose.
 Collect citation targets after the relevant evidence is established and resolve
 them in one batch using the host's existing link resolver when available. Reuse
 known workspace, repository and site parameters; do not rediscover them per link.
+Include knowledge pages and original-source locations in that same batch. For
+each source file, retain the actual inspected repository, full commit, path and
+line range from the investigation; a recorded source reference alone may resolve
+to an older baseline. Pass the inspected commit through the resolver's supported
+contract, or supply a verified commit-specific URL when needed. Never first
+resolve baseline links and then replace them with branch-head links merely as a
+formatting step. If the revision cannot be established, state the attribution
+limit rather than silently substituting another commit. Resolution formats
+citations; it does not prove file contents, accessibility or live deployment.
 If later evidence adds targets, resolve only those missing from the results.
 Without a host resolver, use an already available `context-site-map.json` from
 the selected package or website output. Do not search for `dist/` merely to

package/providers/context/manifest.json

@@ -2,7 +2,7 @@
   "schema": "agent-graph.bundle.v1",
   "provider": {
     "id": "c4a/context",
-    "version": "0.7.30"
+    "version": "0.7.34"
   },
   "providerManifest": "provider.yaml",
   "graphs": [
@@ -183,7 +183,7 @@
     {
       "id": "context.sdk.lark-resources",
       "path": "resources/manuals/guides/lark-resources.md",
-      "digest": "sha256:d5b6b44fe800f302232300adbdb4f32b04b78588ea7879dc9a5c247f36658b9d"
+      "digest": "sha256:ca488cf7d5c818b82c81ea2d9a058cb5e7b91b7de2656506dbc40f19c79fada8"
     },
     {
       "id": "context.sdk.package-outputs",
@@ -288,7 +288,7 @@
     {
       "id": "procedure.document-capture",
       "path": "resources/procedures/document-capture.md",
-      "digest": "sha256:2e6b4e45587fffc1930a3dce0fc6b68d659499a034a367e1cc34a2ef46cb50d9"
+      "digest": "sha256:fea23e68a535ff1a567439fe8b05e027575762c4a8f04da2fd181c17e58076f4"
     },
     {
       "id": "procedure.document-code-investigation",
@@ -575,7 +575,7 @@
     },
     {
       "path": "provider.yaml",
-      "digest": "sha256:50adfb493675f902e6df4d6eade84bb279c64b767084aa15277d65870825458e"
+      "digest": "sha256:ba2618496299deb80171ab9e7472a26b09d9187083347f22bdf65294564acc5d"
     },
     {
       "path": "resources/contracts/indexer-provider-guide.yaml",
@@ -635,7 +635,7 @@
     },
     {
       "path": "resources/manuals/guides/lark-resources.md",
-      "digest": "sha256:d5b6b44fe800f302232300adbdb4f32b04b78588ea7879dc9a5c247f36658b9d"
+      "digest": "sha256:ca488cf7d5c818b82c81ea2d9a058cb5e7b91b7de2656506dbc40f19c79fada8"
     },
     {
       "path": "resources/manuals/guides/markdown-indexer-skill-authoring.md",
@@ -695,7 +695,7 @@
     },
     {
       "path": "resources/procedures/document-capture.md",
-      "digest": "sha256:2e6b4e45587fffc1930a3dce0fc6b68d659499a034a367e1cc34a2ef46cb50d9"
+      "digest": "sha256:fea23e68a535ff1a567439fe8b05e027575762c4a8f04da2fd181c17e58076f4"
     },
     {
       "path": "resources/procedures/document-code-investigation.md",
@@ -878,5 +878,5 @@
     "indexer": [],
     "workspace": []
   },
-  "digest": "sha256:36c06f801f991b92bb78cc94676c8d338389bdc031f49577eb196a96628b2f76"
+  "digest": "sha256:b68d36eaf96c10f0a19ed342e9b15dc21e8ebec3e5864586e66e5f4af8c198f6"
 }

package/providers/context/provider.yaml

@@ -1,6 +1,6 @@
 schema: agent-graph.provider.v1
 id: c4a/context
-version: 0.7.30
+version: 0.7.34
 name: Context workflow
 description: Internal work contract for Context knowledge workspaces.
 graphs:

package/providers/context/resources/manuals/guides/lark-resources.md

@@ -18,7 +18,8 @@ resource checks; it does not fetch that supplied body again. See
 
 | Resource | Default capture behavior |
 |---|---|
-| Image and attachment | Download the original file and link it from the Markdown projection. |
+| Image | Download the original; on explicit download permission denial, try a same-identity preview once and mark it as a preview. |
+| Attachment | Download the original file and link it from the Markdown projection. |
 | Sheet | Read the complete selected sheet, render a Markdown table, and retain a CSV snapshot. |
 | Base | Read the selected table/view with pagination, render a Markdown table, and retain a canonical JSON snapshot. |
 | Whiteboard and diagram | Retain a readable preview plus the raw structured export. |
@@ -34,21 +35,22 @@ preserves an unavailable-resource notice with the reason code
 `document.resource.source-missing`, reports a warning, and continues capture;
 it does not pretend that the deleted content was materialized. When the current
 identity can read the document body but the API explicitly returns
-`authorization/permission_denied` for an embedded resource, Context records
+an explicit permission denial (including HTTP 403) for an embedded resource, Context records
 `document.resource.permission-denied`, keeps the stable resource identity in
 the audit layer, renders the same unavailable-resource notice, and continues
-with a warning. Missing scopes, transient network errors, malformed payloads,
-and unclassified authorization failures still block capture. Reference-only
+with a warning. Explicit missing-scope and access-denied resource responses are
+likewise recorded without changing identity. Transient network errors, malformed
+payloads, and unclassified failures still block capture. Reference-only
 resources remain explicit in the capture report. Unknown non-empty XML blocks
 stay auditable in the raw XML and receive a warning; the CLI does not infer
 their meaning.
 
-Document and resource reads share one access identity. Context first uses the
-user identity; it falls back to the bot identity only when user credentials
-are unavailable, never when the source denies permission or reports missing
-scopes. This prevents a capture from mixing document text read by one identity
-with attachments read by another. A bot fallback is reported in the capture
-result and remains subject to the bot's own access boundary.
+Document and resource reads share one access identity. The configured default is
+user. Bot mode permits one whole-document user fallback for a body authorization
+failure, restarting all pages. After the body is read, resources remain under
+that identity. A resource failure never requests another identity's credentials.
+Legacy explicit auto mode may select Bot when user credentials are unavailable;
+all resources still use the identity that supplied the complete body.
 
 ## Storage lifecycle
 
@@ -184,3 +186,13 @@ limits. The reading meaning of an image is handled in writing and Review.
 Source document links can be retained for viewing under the reader's permissions.
 Temporary signed media links are not durable image hosting. Do not embed access
 tokens in generated pages or claim that excluded images have been interpreted.
+
+### Capture identity and unavailable media
+
+The selected document identity remains fixed for resource reads. In Bot mode,
+only an authorization failure while reading the body can restart the article
+as the current user. Resource failures never trigger that identity fallback.
+Images may use the official same-identity preview endpoint after download
+permission is denied. Previews are marked explicitly; unavailable resources
+retain references and diagnostics. Use available body evidence without inferring
+missing resource contents, and review evidence gaps before approving conclusions.

package/providers/context/resources/procedures/document-capture.md

@@ -53,19 +53,26 @@ text or scan outside the confirmed boundary.
 For Lark reads, set `CONTEXT_LARK_IDENTITY=user|bot` in the environment of every
 Context invocation that may read Lark; the default is `user`. A host/Bot prompt
 setting alone is not an exported environment variable. User mode reads only
-as the current user. Bot mode reads as the configured application, then retries
-once as the current user on a credential, scope or access denial. Subsequent
-reads in that capture use the fallback identity, including pagination, synced
-references, media, Sheets, Base and whiteboards. Network, rate-limit and format
-errors do not switch identity. The diagnostic records any fallback.
+as the current user. Bot mode may fall back once to the current user only when
+reading the document body fails with a credential, scope or access denial.
+The fallback restarts the entire body, including pagination; never combine body
+pages from different identities. Once the body is available, its identity is
+fixed for all media, synced references, Sheets, Base and whiteboard reads.
+Resource failures do not request user authorization or restart the article.
+Network, rate-limit and format errors do not switch identity.
+
+An image download denied by permissions may use the official preview endpoint
+once with the same identity. A captured preview is explicitly marked as such.
+Unavailable resources retain their location and failure reason; continue with
+other resources and usable body text. Never infer missing image contents or
+present a partial snapshot as a complete original. Assess any evidence gaps
+before approving conclusions that depend on those resources.
 
 This setting does not grant source access or change the intended audience of
 the resulting knowledge. Do not use another person's credentials. For direct
-host `lark-cli` reads, explicitly pass the selected `--as bot` or `--as user`
-on every business read, including Wiki resolution/listing and asset reads.
-If Bot access fails for the reasons above, retry that read once as user; stop
-and report a pending source if user authorization is required. In a managed
-runtime, use its authorization flow rather than repeatedly running `auth login`.
+host reads, explicitly pass the article's selected identity on every read.
+Only an article-level fallback may request the current user's authorization;
+use the managed runtime's authorization flow once when needed.
 Local help and embedded skill discovery require no document authorization;
 do not request user OAuth just to read a CLI guide.