Release/1.7.0#671
Merged
Merged
Conversation
…ted-turn-metadata feat(interrupted-turn): persist stopped-turn metadata so cost + message badges survive
The KB sync worker resolves the policy creator's Google token from the AgentCore Identity vault via GetResourceOauth2Token, but that call reads the refresh token *through* the Secrets Manager secret the vault auto-creates per provider (bedrock-agentcore-identity!default/oauth2/<id>). The worker role granted only the two bedrock-agentcore:* actions, so the call failed with AccessDenied on secretsmanager:GetSecretValue and every Drive sync returned "failed". Add the read-only AgentCoreIdentityOAuthSecrets grant (GetSecretValue + DescribeSecret on ...!default/oauth2/*) — the same grant app-api and inference-api already carry, minus the write lifecycle a background fetcher never needs. Covered by a new assertion in kb-sync.test.ts. Verified live in dev-ai: with the grant, the worker gets past the vault read (the remaining paused_reauth is a genuine expired-refresh-token, not this IAM gap). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…er-vault-secret-read fix(kb-sync): grant worker read on the vault's backing OAuth secrets
…r baseline `custom_parameters_for` previously injected vendor-specific OAuth params (Google `access_type=offline`, plus `prompt=consent` on the force-auth path) on top of the connector's admin-configured extras, keyed off `provider_type`. That hid a documented requirement inside the code and made the `customParameters` map depend on the call site (grant vs retrieval), which AgentCore factors into its vault key. Simplify to a single rule: every call site forwards the connector's admin-configured `customParameters` verbatim via `custom_parameters_for(admin_extras)`. Admins set `access_type=offline` and `prompt=consent` in the connector's "Custom OAuth Parameters" field (the seeded Google connector already carries both), so the same map is sent on consent and on every retrieval — no baseline merge, no `provider_type`/`force_authentication` branching, no per-call-site drift. Removes `_vendor_baseline_params`, the `provider_type_lookup` plumbing on the consent hook, and the `force_authentication=True` customParameters argument at all read sites (the SDK-level `force_authentication` flag is unchanged). Behaviour for the existing Google connector is identical (same resulting map); the win is that the vault key is now provably consistent and there are no hidden customizations in the token path. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two design specs drafted alongside recent exploration work: - tool-search-token-bloat-strategy: cross-source tool-search plan for MCP token bloat (tiered discovery, AWS Agent Registry tier). - user-markdown-memory: per-user markdown "second brain" memory, re-scoped skills reference-file mechanism, prompt-cache injection. Docs only; no code or behaviour change. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…dmin-configured-custom-params refactor(oauth): forward admin customParameters, drop hardcoded vendor baseline
…-and-user-memory-specs docs: add tool-search token-bloat + per-user markdown memory specs
A reauth pause was opaque — "credentials need re-consent" gave no hint why. The vault token is keyed by (workload identity, userId), so the overwhelmingly common cause is that the token was vaulted under a DIFFERENT workload identity than the worker queries: e.g. a consent done through local dev (AGENTCORE_RUNTIME_WORKLOAD_NAME=local_dev_inference) can't be read by the deployed worker (platform-workload), and vice versa. That exact mismatch cost hours to diagnose. Surface the workload name, userId, and provider the lookup used in the pause warning so the mismatch is obvious in one log line. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…reauth-diagnostics feat(kb-sync): log workload identity + userId on a reauth pause
KB sync ships dark: the EventBridge rule is created disabled and the
KB_SYNC_ENABLED kill switch is false unless CDK synths with
CDK_KB_SYNC_ENABLED=true (config.ts). platform.yml never forwarded that
var, so a CDK deploy always synthed the feature off — the only way to
enable it was an out-of-band CLI flip that reverts on the next deploy.
Forward it as an environment-scoped `${{ vars.CDK_KB_SYNC_ENABLED }}`
like every other CDK_ var. The development environment variable is set
to "true" (enables the rule + kill switch in dev-ai durably); production
leaves it unset, so it stays dark until validated there.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…able-dev chore(kb-sync): plumb CDK_KB_SYNC_ENABLED into the platform deploy
KB sync shipped opt-in (default off), a holdover from ship-dark
incremental development. The feature is complete and guarded, so a
deployer/cloner of the public stack should get it working by default —
a hidden default-off flag is bad DX. Invert to opt-out: enabled unless
CDK_KB_SYNC_ENABLED=false (or a `kbSync.enabled: false` cdk.json context).
The workflow forwards `${{ vars.CDK_KB_SYNC_ENABLED }}`, which is an empty
string when unset — a plain `?? false` fallback wouldn't flip the default,
so config.ts treats empty/unset as "use the default (on)" and only the
literal "false" as the kill switch. Adds config-resolution tests covering
unset / empty / "true" / "false" / context-disable.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…fault-on chore(kb-sync): default the feature ON with a kill switch
The knowledge-base sync control was a bare "Manual only" dropdown that
never explained what syncing does, and its status line only appeared
while a schedule was active — a manual-only file showed nothing.
- Lead the control with an "Auto-sync from <source>" label (with a
descriptive title tooltip) so every row states what it is and where it
pulls from.
- Rename the options to self-describing verbs: "Don't auto-sync",
"Sync daily/weekly/monthly".
- Always surface a "Last synced" line, including manual-only sources, via
a new lastSyncedAt input fed from Document.lastSyncedAt.
- Pair a relative age with an absolute date/time ("Synced 2h ago ·
Jul 3, 2:14 PM") for both "how long ago" and "exactly when".
Display-only; the timestamps already exist in the data model.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Aligns the knowledge-base sync control with the approved mockup and fixes a bug that rendered the status line as a bare "Synced · next sync". Layout: - Move the "Auto-sync from <source>" context out of the control's button row (where it forced "Pause" to wrap) and into the file's meta line. - Compact the control to just the schedule select + actions. - Add a status-line dot (green healthy / amber attention / grey idle). - Top-align the status icon and download/trash actions with the filename (items-start) instead of floating against the taller row. Timestamp bug: several generators built ISO strings as `datetime.isoformat() + "Z"`, yielding "…+00:00Z" (offset AND Z). That is invalid ISO 8601 and parses to Invalid Date in strict engines (Safari), so last-sync / next-sync rendered blank. Normalize to a single trailing Z in service, dispatcher, and worker; harden the dispatcher parser to always return a UTC-aware datetime; and harden the SPA to tolerate the legacy "+00:00Z" so already-persisted policies still render. Download and delete controls on documents are preserved. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The web-source (crawl) row shared the sync control with documents but was missing the parity bindings the document row got: no source-context line and no persistent last-synced timestamp, so a manual web source rendered as a bare dropdown while an identical document showed full context. - Add the meta-line context "Auto-sync from the web" (guarded by isCrawlSyncable), mirroring the document's "Auto-sync from <provider>". - Feed the control lastSyncedAt from crawl.completedAt so a manual web source still shows when it last refreshed (the component already prefers the policy's lastSyncAt when a schedule is active). - Make the crawl meta line wrap-safe (flex-wrap), matching the doc row. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The Web sources list had no loading flag, so it popped into existence after its network round-trip, while Uploaded Documents showed a lone centered spinner — two async lists with inconsistent, jarring loads. Introduce one initial-load gate for both lists: - Add isLoadingCrawls, set from loadSyncData (cleared on the viewer early-return and in finally), mirroring isLoadingDocuments. - isLoadingKnowledge computed gates both lists so they reveal together; raise both flags synchronously in ngOnInit so the first paint is the skeleton, not an empty flash. - Replace the documents spinner with a skeleton list (pulsing icon + two text bars, varied widths) that mirrors the final row shape — no layout shift, and consistent with the existing connector-button skeleton. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Changing the schedule (e.g. Don't auto-sync → Sync weekly) held the busy state for the whole create/update/delete round-trip but only disabled the controls — there was no positive sign anything was happening, and the select eagerly reverts to its old value until the mutation confirms, so it read as "nothing happened". While busy, the status slot now shows a spinner + "Saving…" (role=status), taking precedence over the sync status line — including for a manual-only source being enabled, where no policy or status exists yet. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…status-clarity fix(kb-sync): clarify the auto-sync control and repair blank sync timestamps
UserSyncService built timestamps as `datetime.isoformat() + "Z"`, yielding "…+00:00Z" — both an offset AND a Z. That is invalid ISO 8601 and parses to Invalid Date in strict engines (Safari), so the admin user-list "Last login" and user-detail "Created"/"Last login" dates (rendered via `new Date()`) showed "Never". Same class of bug just fixed across KB-sync (service/dispatcher/worker); this applies the identical normalization to the users domain. - Write path: add `_iso()` helper, normalize `created_at`/`last_login_at`. - Read path: add `_heal_iso()` and apply in `_item_to_profile` / `_item_to_list_item` so legacy "+00:00Z" rows render correctly. Necessary because `created_at` is preserved across logins forever (never rewritten), so pre-fix users would otherwise show "Never" in Safari permanently. - Regression tests for the write-path invariant and read-path heal. `last_login_at` also backs GSI2SK/GSI3SK (sort-by-last-login); the suffix change is lexicographically safe — ordering is dominated by the microsecond datetime prefix and a transient mix of "+00:00Z"/"Z" rows does not corrupt it. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…mestamp-zulu fix(users): normalize sync timestamps to strict ISO 8601 (single Z)
…panel Wrap the Knowledge base section on the Assistant editor in a rounded, bordered inset with a subtle gray-100/60 fill instead of the flat border-t divider shared by other sections. Against the gray-50 form column this reads as a mildly contrasted group, and the white inner lists (Web sources / Uploaded Documents) now float on the tint to reinforce the grouping. Drops the border-t/pt-8 divider since the card provides its own separation; the form's space-y-8 preserves the top gap. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add Drive, Docs, Gmail, and Calendar icon assets under public/logos. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add Google connector logo SVGs (Drive, Docs, Gmail, Calendar). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
… + spike brief Reframe the proactive-agent effort from a single "Oliver" feature into a primitive-enablement plan, mapped onto the Harness (headless run entrypoint) and Registry (catalog + governance) explorations. - agentic-platform-primitives.md: primitive maturity + gap ledger, the six fundamentals (F1 headless run entrypoint .. F6 registry/governance), phased plan, and Harness/Registry overlap. Oliver demoted to one validation use case among several. - scheduled-agent-runs.md: detailed design for F1+F2+F3 (renamed from the earlier Oliver draft; generalized so any config/prompt/cadence works). - harness-entrypoint-spike-brief.md: tight spike brief for the F1 keystone (unattended-as-user auth + server-side SSE), to run in dev-ai. Resolved decisions: F1 = minimal internal run_agent_headless(), A2A-ready; governance floor (F6a) pulled forward into Phase A, Registry discovery (F6b) deferred. Open: KB decoupling appetite, floor depth, sequencing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…primitives-plan docs(specs): agentic platform primitives plan (+ scheduled-runs design + F1 spike brief)
…ev-ai run_agent_headless in apis/shared/harness: per-owner Cognito bearer mint (workload-token + SigV4 front-door paths proven dead at the runtime gateway), server-side SSE drain pinned to live wire shapes, F6a audit records + guardrails/classification seams, delivery via the runtime's own session materialization + title override. Driver script reproduces the dev-ai proof and the negative auth probes. Findings + Phase A design in docs/specs/harness-entrypoint-spike-findings.md. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The headless-run entrypoint spike (Fable 5) is GO — proven end-to-end in dev-ai. Bring its findings doc onto develop as the decision record and lock the four gate decisions into the plan of record. - Add harness-entrypoint-spike-findings.md (design deliverables + Phase A punch list; full spike code lives on branch spike/harness-headless-entrypoint). - agentic-platform-primitives.md §6: resolve act-as-user auth policy (Cognito per-owner token behind an explicit headless-grant record), F6a floor depth (audit fail-closed now; PII checkpoint required before unattended schedules), KB decoupling (defer), sequencing (proactive-spine-first confirmed). - scheduled-agent-runs.md §8: mark unattended-auth resolved with the chosen path. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
… primitive Replace the spike's BFF-table Scan with an explicit headless-grant record (apis/shared/harness/grants.py): create-on-enable from an attended session, per-owner lookup via the sparse HeadlessGrantUserIndex GSI, revocation that deletes the stored credential, and a documented "must have logged in within 30 days" policy (TTL anchored to the login that issued the pinned refresh token, matching the Cognito refresh-token validity). CognitoRefreshBearerAuth now mints from the grant (rotation-aware: a rotated refresh token is persisted back before the mint returns — punch-list #5). Dedupe build_invocations_url into the harness as the single canonical resolver; the chat proxy imports it (punch-list #4). Document the enabled_tools=None = all-RBAC-allowed semantic and the schedule-snapshot rule (punch-list #7). Governance docstrings updated to the locked F6a decision: audit-only fail-closed + wired no-op guardrail/classification seams, implementations gated to the scheduled phase. Add an _build_http_client seam and tests covering the grant lifecycle, grant-backed minting, audit fail-closed ordering, and stream outcomes against a MockTransport runtime. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…lity POST /runs/now executes one agent turn through the exact unattended path a scheduled run will use (create-on-enable grant -> per-owner Cognito mint -> runtime /invocations -> server-side SSE drain -> governance floor -> session materialization) — the PR-1 validation surface from docs/specs/scheduled-agent-runs.md §7. GET/DELETE /runs/grant expose grant status and total revocation. Gating is two independent controls (spec §6): the SCHEDULED_RUNS_ENABLED kill switch (default ON; only the literal "false" disables — empty workflow vars can't dark-stop prod) and a new `scheduled-runs` RBAC capability resolved through the mature tools grant axis (apis/shared/rbac/capabilities.py) — GA = grant the id to the default role. Auth is the standard SPA cookie dependency per the CLAUDE.md app-api rule; mint failures surface as 409, never 401, so the SPA is not bounced through the login redirect. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…ed-conversations-iam-grant fix(infra): grant app-api task role access to shared-conversations table
Sharing a large conversation failed: ShareService.create_share inlined the full message list into a single DynamoDB item, exceeding the 400 KB item limit and surfacing to users as a bare 500 (observed in prod-ai as a PutItem ValidationException). This is separate from the IAM-grant bug in PR #657. Offload the snapshot body (messages + metadata) to a new private shared-conversations S3 bucket, keeping only control fields plus a body_ref pointer in DynamoDB — mirroring the Memory Spaces / Artifacts / Skills S3-offload pattern. Reads fall back to inline for legacy shares, so existing shares keep working with no migration and the SPA contract is unchanged. - New ShareSnapshotStore (content-addressed S3 put/get/delete, SSE-S3, dedupe) - create_share writes body to S3 + body_ref item; revoke/session-cleanup best-effort delete the object - _load_snapshot_body reads from S3 or falls back to legacy inline items - ShareStorageUnavailableError -> friendly 503 instead of a bare 500 - CDK: shared-conversations bucket + SSM param, compute-ref, app-api env (SHARED_CONVERSATIONS_BUCKET_NAME), and SharedConversationsBucketReadWrite IAM grant (app-api only) - Tests: store round-trip/dedupe, >400 KB regression, S3 + legacy reads, export-from-S3, revoke cleanup, storage-unavailable Spec: docs/specs/share-large-conversations-s3-offload.md Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…rge-conversations-s3-offload feat(shares): offload large-conversation snapshots to S3
…evelop-1.6.0 # Conflicts: # backend/src/agents/main_agent/session/tests/test_history_repair.py # backend/src/apis/inference_api/chat/routes.py
…nto-develop-1.6.0 Backmerge: main → develop (1.6.0)
Agent (assistant) model bindings persist only `model_id` — never `provider` — so previewing/invoking an agent bound to a Mantle model (e.g. `openai.gpt-5.4`) resolved to provider=None. That misroutes the model to Bedrock ConverseStream, which rejects it with "The provided model identifier is invalid", even though the same model works from the normal chat path (which always sends `provider` alongside `model_id`). Two complementary fixes: - Backend (server-authoritative): `_resolve_model_settings` now also returns the model's registered `provider` from the managed-model registry, and the invocation path backfills `effective_provider` from it when the request/binding didn't carry one. This fixes all existing agents with a provider-less stored binding — no data backfill needed — and mirrors how `mantle_api_mode`/`mantle_region` are already recovered. The app-tool-call / app-context-update rebuild paths get the same fallback so a rebuilt agent keys on the same provider as its main turn. - Frontend: the Agent Designer save payload now persists the selected model's `provider` (from the catalog `meta.provider`) alongside `modelId`, so newly created/edited bindings are self-describing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Resume turns (interrupt_responses set — OAuth-gated MCP consent or tool-approval) crashed with `NameError: cannot access free variable 'effective_enabled_tools'`. The variable is referenced unconditionally by the `stream_with_quota_warning` streaming closure (attachment guidance + tabular inventory) but was only assigned in the non-resume branch. On resume the closure raised before its first yield, the inference-api container returned 500, and the AgentCore Runtime data plane translated that into a 424 Failed Dependency to app-api and the SPA. This broke every interrupt-resume turn since the agent-designer tool-binding refactor (0b9b039) — most visibly "connect to Gmail for employees", which completes via an OAuth-consent resume. Bind effective_enabled_tools from the paused-turn snapshot on the resume branch (the same source the resume get_agent call uses). Adds a resume-path regression test to tests/routes/test_inference.py that drives /invocations with interrupt_responses and asserts a 200 stream; without the fix it fails with the NameError. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…er-resolution fix(agents): resolve model provider for agent-bound invocations
…tive-enabled-tools-nameerror fix(inference): bind effective_enabled_tools on resume path (prod 424 on OAuth-gated MCP connect)
…nto-develop-1.6.1 Backmerge: main into develop (1.6.1)
…2026-07-10 chore(kaizen): weekly research scan 2026-07-10
Generated by the kaizen-research skill. Top 5 ideas appended to docs/kaizen/review-queue.md for the kaizen-review-prep run later this morning. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Root-cause spec for the SessionMetadata parse-failure warnings: the session
row's sort key encodes lastMessageAt, forcing a delete+put row move every turn.
Concurrent writers race that move and upsert bare ghost rows. Also drives the
first-turn duplicate-row race.
Fix: static SK (S#{session_id}) + sparse SessionRecencyIndex GSI for recency
listing. Covers the expand -> migrate -> backfill -> contract migration,
downstream/forked-deployment safety (marker gate + graceful GSI-missing
fallback), pagination-token compatibility, and the test matrix.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…175 Phase 0) Sparse recency index (GSI4_PK=USER#{id}, GSI4_SK={lastMessageAt}#{session_id}, projection ALL) for newest-first active-session listing once the base sort key becomes static. Phase 0 of the static-sort-key migration: adding the index is a no-op until rows populate GSI4 keys, so it deploys safely ahead of any code change. IAM already covers it via the SessionsMetadataAccess /index/* wildcard. Update tables-detailed test to assert all four GSIs (the "2 GSIs" title was already stale after DueScheduleIndex) and the new index's key schema. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…metadata-static-sk-phase0 feat(infra): SessionRecencyIndex GSI on sessions-metadata (issue #175 Phase 0)
…Phase 1a)
Expand-read step of the static-sort-key migration. list_user_sessions now reads
the UNION of two disjoint sources so a session is visible whether or not its base
sort key has been migrated to the static S#{session_id} form:
- legacy (un-migrated): base table, SK begins_with 'S#ACTIVE#'
- migrated: SessionRecencyIndex GSI (GSI4_PK=USER#{id}, GSI4_SK={lastMessageAt}#{id})
Pagination switches to a value cursor ({lastMessageAt}#{session_id}) so each page
is derived independently from the last returned position, with no cross-page
buffering; fetching limit+1 valid rows per source is provably enough to detect a
next page. The cursor decoder is tolerant — legacy/undecodable tokens fall back to
first page (a harmless reset across the deploy boundary).
Degrades to legacy-only if SessionRecencyIndex doesn't exist yet (code ahead of the
CDK GSI): the GSI query's ResourceNotFoundException is caught.
No writes change and no row migrates in this phase — this only teaches every reader
to cope with both schemes, which must be fully rolled out before Phase 1b turns on
self-migrating writes.
Tests: union ordering, cross-union pagination (no dupes/gaps), migrated-only via
GSI, ghost/preview skip, and graceful fallback when the index is absent. conftest
sessions_metadata_table fixture gains the SessionRecencyIndex GSI to match prod.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…metadata-static-sk-phase1a feat(sessions): dual-scheme union read for session listing (issue #175 Phase 1a)
Auto prompt caching (CacheConfig strategy=auto) appended its cachePoint after the last user message's content, so any turn attaching a non-PDF document (txt/docx/csv/...) sent [text, document, cachePoint] and Bedrock's Anthropic adapter rejected it with "ValidationException ... messages.N.content.M.type: Field required", surfacing to users as "Agent force-stopped" (prod incidents Jul 14-16, e.g. session dd1a647a on a .txt transcript upload). strands 1.48.0 places the cache point before the first non-PDF document block instead (upstream issue #1966); every placement it produces was verified live against global.anthropic.claude-sonnet-4-6 ConverseStream. Also corrects the model_config comment that credited PR #1438/1.39.0 with this fix - #1438 was the auto-caching feature itself. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ce-stop-validation-791e6f fix(deps): bump strands-agents to 1.48.0 for cachePoint-attachment fix
…2026-07-17 chore(kaizen): weekly research scan 2026-07-17
… missing GSI (issue #175) The Phase 1a dual-scheme read (PR #667) catches a missing SessionRecencyIndex to fall back to legacy-only listing, but only handled ResourceNotFoundException — what moto raises. Real DynamoDB raises ValidationException ("The table does not have the specified index") for a missing GSI (verified against the prod table). So if the 1a backend deployed to an environment before the CDK GSI existed, list_user_sessions would 503 instead of degrading. Broaden the catch to also handle ValidationException (scoped by the "specified index" message so genuinely malformed queries still surface). This restores the intended order-independence: 1a is safe whether or not SessionRecencyIndex exists yet, which matters for prod deploy ordering (backend.yml vs platform.yml) and for forked deployments. Add a test that reproduces the real ValidationException on the index query (moto masks it), asserting fallback to legacy-only results. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Provision a full Word (.docx) toolset behind the single create_word_document capability toggle. Each tool runs python-docx in Bedrock Code Interpreter and uses the existing user-files store (S3 + DynamoDB) for persistence and delivery. - create/modify/list/read tools in agents/builtin_tools/word_document_tool.py, injected per-request via _build_word_document_tools (inference_api/chat/routes.py). - Frontend inline-visual 'word_document' renderer with an accessible download button (Tailwind utilities, no scoped CSS). - Restore-time content-block sanitizer in TurnBasedSessionManager: drops empty/typeless blocks from restored history that caused Bedrock ConverseStream 'messages.N.content.M.type: Field required'. - Seed create_word_document in bootstrap DEFAULT_TOOLS ('Word Documents') + updated seed tests.
…ument-tools Add Word document tools (create/modify/list/read)
…-missing-index-fallback fix(sessions): degrade to legacy-only on real ValidationException for missing GSI (issue #175)
Feature release: Word (.docx) document toolset for the agent plus the read-side phases of the session-metadata static-sort-key migration (issue #175). - Add create/modify/list/read Word document tools (python-docx in Code Interpreter, user-files store) behind the create_word_document toggle, with an inline word_document renderer + download button (#670) - Session listing dual-scheme union read across legacy + SessionRecencyIndex, value-cursor pagination (issue #175 Phase 1a) (#667) - New sparse SessionRecencyIndex GSI on sessions-metadata (issue #175 Phase 0) (#666) - Degrade session listing to legacy-only on ValidationException for a missing GSI (#669) - Bump strands-agents to 1.48.0 to fix cachePoint-after-attachment 'Agent force-stopped' on non-PDF uploads (#668) - Restore-time content-block sanitizer in TurnBasedSessionManager (#670) Bump VERSION 1.6.1 -> 1.7.0 and sync manifests + lockfiles.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Release 1.7.0
Feature release (minor bump
1.6.1→1.7.0).🚀 Added
create_word_document,modify_word_document,list_word_documents,read_word_document, each runningpython-docxin a Bedrock Code Interpreter session and persisting to the user-files store, with an inlineword_documentrenderer + download button. Behind thecreate_word_documentcapability toggle; seeded into bootstrapDEFAULT_TOOLS(Add Word document tools (create/modify/list/read) #670)✨ Improved
list_user_sessionsreads the union of legacy +SessionRecencyIndexrows with a self-derived value cursor, so sessions list regardless of migration state (feat(sessions): dual-scheme union read for session listing (issue #175 Phase 1a) #667)🐛 Fixed
ValidationExceptionfor a missingSessionRecencyIndex(not justResourceNotFoundException), keeping deploy order non-load-bearing (fix(sessions): degrade to legacy-only on real ValidationException for missing GSI (issue #175) #669)strands-agents1.47.0 → 1.48.0 so the auto-cachecachePointlands before the first non-PDF document block (upstream #1966) (fix(deps): bump strands-agents to 1.48.0 for cachePoint-attachment fix #668)TurnBasedSessionManagerdrops empty/typeless blocks that broke ConverseStream on resume (Add Word document tools (create/modify/list/read) #670)🏗️ Infrastructure
SessionRecencyIndexGSI on the sessions-metadata table (issue Refactor session metadata schema: stable SK + recency GSI #175 Phase 0) — no-op until rows populate keys; deploys safely ahead of code (feat(infra): SessionRecencyIndex GSI on sessions-metadata (issue #175 Phase 0) #666)📦 Dependencies
strands-agents1.47.0 → 1.48.0 (fix(deps): bump strands-agents to 1.48.0 for cachePoint-attachment fix #668)Deployment
🏗️ CDK deploy required for the new
SessionRecencyIndexGSI (platform.ymlbeforebackend.yml). The Phase 1a reader degrades gracefully if the GSI is absent, so deploy order is not load-bearing. No data migration, no breaking changes. Word toolset is dark until an admin enablescreate_word_document.See
RELEASE_NOTES.mdandCHANGELOG.mdfor full detail.🤖 Generated with Claude Code