Skip to content

fix(connections): Jira/Confluence start Atlassian sign-in in KAS chats; card says how KAS chats sign in - #30823

Merged
iamwhatever merged 1 commit into
mainfrom
fix/kas-signin-words
Nov 6, 2026
Merged

iamwhatever merged 1 commit into
mainfrom
fix/kas-signin-words

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: In a KAS chat, asking about Jira or Confluence offers the Atlassian sign-in, and the Connections card tells KAS users how their chats sign in.

On 0.12.0 a KAS chat offers an MCP sign-in only when the user's typed message names the server (want_mcp_sign_in_named / text_names_mcp_server, since #26481). For atlassian the only alias is atlassian, so "show my Jira issues" gives no Authorize banner and no tools. The Connections card meanwhile shows Connected, because its sign-in wrote a kiro-cli grant that KAS never reads. Users see "Connected" and a chat that cannot use it.

Why it matters

Every KAS user of the Atlassian connection (KAS is the default chat harness) hits this: the natural words "Jira" and "Confluence" never start a sign-in, and the card gives no hint that a KAS chat needs one. This is the short-term stopgap; the full fix (card sign-in runs on KAS, so card and chat share one grant) is a separate, larger change.

Not a goal

What changed (motivation → approach → change)

Symptom → cause → change:

  • 5a. "Jira" is not an alias of atlassian → a registry provider may now declare optional sign_in_words (connections/registry.json: atlassian → jira, confluence; validated as lowercase single words of 3+ characters). text_names_mcp_server also tries the words of the provider whose slug is the server name, with the same whole-word, case-insensitive match as an alias. No other provider declares words, so nothing else changes.
  • 5b. The card says nothing about KAS for DCR rows → the status feed adds signInInChat on a connected row while agent.acp_backend is KAS (chat_backend_is_kas; an unreadable config answers no). It is not set on a row that already carries backendLacksOauth, since KAS cannot sign those in by name. The card reuses the existing "In chats" line (or the shared-grant tip): "Chats sign in separately: type <slug> in a chat once." It names no harness, like the backendLacksOauth copy: the line shows only while chats run on KAS (UX Review on 19df0b2; "separately" per UX Review on e158c20). The word is the slug: for Atlassian, atlassian always works and jira/confluence do too, so the line names one word to keep it short. "Once" is once per gateway while agent.kas_persist_mcp_sign_in is on (the default). New string pages.connectionsPage.chat_use_kas_sign_in in en.manual.json and all 12 shipped locales; en-XA regenerated.
  • Specs updated: acp-client.md (what names a server) and connections.md (the new row flag and its copy).

Backwards compatibility

Compatible: sign_in_words is optional, signInInChat is an added optional field, and alias matching only gains words for atlassian.

Removes nothing: the change only adds an optional registry field, an optional status field, one catalog string and extra matching words.

Tests

  • test/test_kas_mcp_sign_in.py: "show my Jira issues" and "search CONFLUENCE …" name atlassian; unrelated text, jiras, and the same words for linear/notion do not.
  • test/test_connections_registry.py: malformed sign_in_words is rejected; only atlassian declares words; an unknown slug has none.
  • test/test_connections_backend_oauth.py: KAS + connected DCR row → signInInChat; KAS + not connected → none; Kiro CLI → none; pre-registered row on KAS keeps backendLacksOauth and no signInInChat; unreadable config → not KAS.
  • website/src/test/ConnectionsPage.coverage.test.tsx: the line renders with signInInChat, and no "In chats" line without it.

Proof: not provable -- other: prove.py was not run in this worktree; the new matcher and status cases assert behavior that main lacks (no sign_in_words, no signInInChat).

Local: 220 passed (the three Python files + test_connections_status*), 65 passed (ConnectionsPage.coverage), i18n parity + i18n-check.mjs with I18N_BASE_REF=origin/main green.

Manual verification

Rendered the real built SPA against stubbed APIs (Playwright, as capture-connections-caveat-tip.mjs does): connected Atlassian and Notion rows with signInInChat show the line, and without it show none, in light and dark. Not checked against a live KAS chat.

Screenshots / video

Chat harness KAS: connected Notion and Atlassian rows show the "In chats" line.

KAS light

KAS dark

KAS with a shared grant: the line joins the tip beside Disconnect (opened).

Shared tip light

Shared tip dark

Chat harness Kiro CLI: no line.

Kiro CLI light

Kiro CLI dark

The "Couldn't load your starred Bots" toast is from the stubbed APIs, not this change.

Related Issues

Refs #26481, #26525

Sibling sweep

Swept: git grep -n "mcp_server_aliases\|text_names_mcp_server" -- src/
Siblings: none -- text_names_mcp_server is the one matcher; its only caller is _match_mcp_sign_in_ask.

Pattern harvest

Not generalizable: the gap is a missing product vocabulary entry (brand names of one provider), not a code pattern.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Contribution License Agreement

Contributed under the project's Apache-2.0 license.

@iamwhatever
iamwhatever requested review from a team and KiroCrewCaptain as code owners November 5, 2026 22:55
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 5, 2026
@github-actions

github-actions Bot commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of ac97acf99590c12645146d6a5bb92af1f7d13272 — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: PASS

Nothing blocks. The fix is a declared stopgap: the description says the card and KAS chats still keep separate grants. The new registry field has a single real value.

Notes

  • Item 2 — one consumer, generalized: sign_in_words is a validated registry schema field (_SIGN_IN_WORD_PATTERN, Provider.sign_in_words, _OPTIONAL_PROVIDER_FIELDS). Exactly one provider declares it (atlassian, pinned by test_only_atlassian_declares_sign_in_words), and it has one reader (text_names_mcp_server). Subtraction: none smaller is cleaner. The field form is the smallest way to keep brand words out of the generic matcher, so this is a note, not a demand.

What this change ships

Inventory (7 items) — 6 justified

Intent: a KAS chat user asking about Jira or Confluence gets the Atlassian sign-in, and the Connections card tells KAS users their chats sign in separately. This is a FIX (a stopgap).

  1. A KAS chat message saying "Jira" or "Confluence" now offers the Atlassian sign-in — justified
  2. New optional registry field sign_in_words, with load-time validation — one consumer, generalized
  3. On KAS, connected cards show an "In chats" line: "Chats sign in separately: type <slug> in a chat once." — justified
  4. With a shared grant, that same line joins the tip beside Disconnect — justified
  5. The status feed gains an optional signInInChat field on connected rows while chats run on KAS — justified
  6. chat_backend_is_kas(): an unreadable config answers "not KAS", so no caveat shows — justified
  7. New catalog string chat_use_kas_sign_in in 13 locales, plus updates to the acp-client and connections specs — justified

[FIRST-PRINCIPLES-REVIEWED] ac97acf

Description read

[DESCRIPTION-READ] 3ad299c6de5bae42b396565327e7967f9458edd138df9cb1cfe99f8f206979ea

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of ac97acf99590c12645146d6a5bb92af1f7d13272 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: a registry vocabulary entry fed to the one existing matcher, and an optional status flag. It is additive and easy to revert, and screenshots are attached.

Notes

  • text_names_mcp_server in acp/ now imports connections.registry on every call. The matcher only finds these words because the MCP server key happens to equal the provider slug (tool_aliases.py:133). That holds today, but nothing pins it. A registry-backed mcp_server_aliases would keep that link in one place.

[DESIGN-REVIEWED] ac97acf

Description read

[DESCRIPTION-READ] c42f045fac95d814d854b42c2ed60ce4d34adcad348d30822f916ecae87b6441

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS

UX-level review of ac97acf99590c12645146d6a5bb92af1f7d13272 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

Nothing blocks. The one addition is a passive line of copy, every state it can be in is shown in a screenshot, and the blind reader read it roughly as intended.

Notes

  • The reader asked "once per chat or once ever?" about chat_use_kas_sign_in. Per the PR it means once per gateway. Change "Chats sign in separately: type {{word}} in a chat once." to "Chats need their own sign-in: type {{word}} in any chat once."
  • {{word}} renders as plain prose ("type notion in a chat"), so it doesn't stand out as the word to type. Wrap the interpolated slug in <code> or put it in quotes.
  • On a shared-grant row this instruction only appears in the hover tip beside Disconnect (shot-03), and the reader thought the line had disappeared. The instruction is needed before a chat can use the service, so keep it on the card's "In chats" line in that case too.

[UX-REVIEWED] ac97acf

Description read

[DESCRIPTION-READ] 56b8221a97808fd1f7854370f6da50f66278202cc7b467205989d4d25aa2bec0

That sha256 names everything this verdict read: the PR description, plus the 9 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed ac97acf99590c12645146d6a5bb92af1f7d13272 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] ac97acf

Verdict parsed from the review's SHA-scoped output markers for commit ac97acf99590c12645146d6a5bb92af1f7d13272.

False positive or not applicable? A repository writer can comment:
/ai-review override fable ac97acf99590c12645146d6a5bb92af1f7d13272 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 5, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of ac97acf99590c12645146d6a5bb92af1f7d13272 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] ac97acf

False positive or not applicable? A repository writer can comment:
/ai-review override gpt ac97acf99590c12645146d6a5bb92af1f7d13272 false-positive: <reason, 20 to 500 characters>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Nov 5, 2026
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Nov 5, 2026
…s; card says how KAS chats sign in

registry: optional sign_in_words per provider (atlassian: jira, confluence); text_names_mcp_server matches them whole-word, like an alias. status: connected rows carry signInInChat while chats run on KAS; the card says to type the slug once in a chat.
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 6, 2026

@buluoray buluoray left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🤖 Kiro Crew Auto-Pipeline [operator: buluoray]:

Verdict: APPROVE at ac97acf.

What this does for users. In a KAS chat (the default harness), "show my Jira issues" or "search Confluence" now offers the Atlassian sign-in. Before this, only the word "atlassian" did. While chats run on KAS, each connected card also tells the user that chats sign in separately and which word to type. That closes the gap where the card said Connected and the chat still had no tools. Kiro CLI chats are unchanged.

Evidence

  • KAS identity is checked positively. chat_backend_is_kas (src/kiro_crew/connections/status.py:191-205) compares the loaded agent.acp_backend to ACP_BACKEND_KAS, and an unreadable config answers no. The loader already resolves a Kiro CLI pick that runs on the v3 relay into KAS (src/kiro_crew/config/loader_builders.py:510-518), so a relayed install gets the line too.
  • The flag is set only on a connected row that does not carry backendLacksOauth (status.py:523-524). Pre-registered rows keep their existing caveat.
  • The matcher extension is scoped. sign_in_words(name) returns words only when the server name equals a registry slug that declares them (src/kiro_crew/connections/registry.py:743-747). Only atlassian declares any. Each word is validated as one lowercase word of 3+ characters (registry.py:516-527). Matching reuses the existing whole-word, case-insensitive pattern (src/kiro_crew/acp/session_handle_mcp.py:663-666).
  • No credential or URL is involved. The new code reads config and a static word list, and it logs nothing.
  • The copy is a new string in the catalog, pages.connectionsPage.chat_use_kas_sign_in, present in en.manual, en-XA and the 12 shipped locales. It gives a fact the card did not show before (chats need their own sign-in, and the word to type) and names no harness.
  • Tests at this head: test_kas_mcp_sign_in, test_connections_registry and test_connections_backend_oauth gave 167 passed. ConnectionsPage.coverage.test.tsx gave 65 of 65 on two runs. On the first, cold run, the new KAS test failed once and then passed alone and in two full-file runs, so it may be order or warm-up sensitive. CI has 83 success, 11 skipped and 0 failing, and PR Readiness is green. The merge with main is clean.
  • I ran four mutations, one at a time, and restored the tree after each:
    • chat_backend_is_kas returning True turned test_kiro_cli_never_marks_sign_in_in_chat and test_an_unreadable_config_claims_no_kas_chat red. This pins "Kiro CLI chats behave as on main".
    • Dropping sign_in_words from the matcher turned both new test_a_server_is_named_by_its_name_or_an_obvious_alias[atlassian-...] cases red.
    • Dropping the connected-status gate turned test_kas_leaves_a_not_connected_row_without_the_caveat red.
    • Removing signInInChat from chatUseNote in ConnectionsPageCard.tsx turned "tells a connected row on KAS to type the server name once in chat" red on 2 of 2 runs.

Checked from source only (not run): that the extra words reach the sign-in offer only on KAS. The only caller is _match_mcp_sign_in_ask (session_handle_mcp.py:712), and on Kiro CLI begin_mcp_sign_in refuses every start (acp-client.md). I did not check against a live KAS chat.

Bot lanes: First Principles, Design, UX, Opus and GPT all pass, with no HOLD.

  • The Design lane notes that the matcher finds these words only because the MCP entry key equals the slug, and nothing pins that link. I checked this: mcp_server_alias(slug) is the identity for today's slash-free slugs (connections.md, "Tool-alias key shape"). It does not gate, and it is follow-up 2 below.
  • The UX lane raises three points: "once" is ambiguous, the word is not set apart in the copy, and on a shared-grant row the line is hidden in a tip. These are copy and placement suggestions, not regressions, and they are follow-up 1 below.

Follow-ups (non-blocking)

  1. Copy and placement. "Once" holds while agent.kas_persist_mcp_sign_in is on (the default). With it off, a KAS chat signs in again each time its process restarts, so the line overstates for those users. Either show the line only while persistence is on or drop "once". In the same change, consider the UX lane's points: set the word apart, and keep the line on the card for shared-grant rows.
  2. Add a test that fails if a connection's mounted MCP entry name stops equal to its registry slug, or move sign_in_words into mcp_server_aliases so the slug and alias link lives in one place.
  3. The new ConnectionsPage coverage test failed once on a cold run and then passed three times. Worth watching for flakiness.

@iamwhatever
iamwhatever merged commit 02a7173 into main Nov 6, 2026
98 of 99 checks passed
@iamwhatever
iamwhatever deleted the fix/kas-signin-words branch November 6, 2026 06:41
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 6, 2026
buluoray pushed a commit that referenced this pull request Nov 6, 2026
…s; card says how KAS chats sign in (#30823)

registry: optional sign_in_words per provider (atlassian: jira, confluence); text_names_mcp_server matches them whole-word, like an alias. status: connected rows carry signInInChat while chats run on KAS; the card says to type the slug once in a chat.

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit 02a7173)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants