- api/streaming.py SSE payload now falls back to agent.model_metadata.get_model_context_length when compressor doesn't supply context_length (mirrors the session-save fallback shipped in v0.50.247).
- api/streaming.py also falls back to s.last_prompt_tokens to avoid using the cumulative input_tokens counter.
- static/ui.js tracks rawPct separately from pct and shows '(context exceeded)' tooltip when rawPct > 100 instead of misleading '100% used (0% left)'.
- static/messages.js clears 'Uploading...' composer status after upload completes.
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Frontend companion to backend fix in v0.50.246 (#1341 + a5c10d5).
Default context window to 128K when usage.context_length is falsy.
Show '(est. 128K)' label when using the default.
Use input_tokens as fallback for last_prompt_tokens.
Co-authored-by: jasonjcwu <jasonjcwu@users.noreply.github.com>
From PR #1338. Already independently APPROVED by nesquena before being absorbed into v0.50.246.
CHANGELOG entries from this PR were dropped during squash (the v0.50.245 section is already
shipped); they will be re-added under [v0.50.246] in the release commit.
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
release: v0.50.243
Batch release of 2 PRs.
- #1301 — fix: remove PRIMARY chip badge + add Claude Opus 4.7 label
Drops the chip-projected configured-model badge added in #1287 (chip
width 235px → 164px). Adds Claude Opus 4.7 label entries so the picker
no longer renders "Claude Opus 4 7" (missing dot).
Independently reviewed and approved by nesquena (commit c0bbd23).
- #1297 (@franksong2702) — fix: preserve cron output response snippets
Fixes#1295. /api/crons/output now preserves the ## Response section
when a large skill dump appears in the prompt section; falls back to
file tail when no marker exists.
Tests: 3254 passed, 2 skipped, 3 xpassed.
Independently reviewed and approved by nesquena (commit b262e4d).
The post-stream renderMd() in static/ui.js only handled #, ##, ### — lines starting with #### through ###### fell through and emitted as literal text after streaming finalized.
Extend the heading replacer chain to cover h4-h6, ordered longest-first, so ###### cannot be partially captured by the shorter ### rule. Add the matching .msg-body h4/h5/h6 CSS rules (and data-font-size variants) so the new tags inherit the same visual rhythm as h1-h3.
Adds 3 node-driven tests in test_renderer_js_behaviour.py pinning all six heading levels and the longest-first replacer order.
Closes#1258
Addresses reviewer feedback on #524 — the compress affordance was only
reachable via hover (desktop). Mobile users can now tap the context ring
button to toggle the tooltip and access the compress button.
- CSS: add .ctx-tooltip-active class with opacity + pointer-events
- JS: tap-to-toggle handler on ctxIndicator with outside-click dismiss
- aria-hidden toggled correctly for accessibility
Ref: #1223 review comment
- Add 512 KB cap for inline diff rendering to prevent DOM bloat on large patch files
- Add diff_error and diff_too_large i18n keys in all 7 locales for clear error messages
- Improve error state to show explanatory message instead of just filename
- Addresses reviewer feedback on file size cap and missing diff_error i18n key
- Fenced code blocks with diff/patch lang hint render with colored lines
(green +lines, red -lines, italic @@ hunks)
- MEDIA:.patch/.diff files render inline instead of download link
(async fetch via loadDiffInline() in post-render pipeline)
- CSS: diff-block, diff-line, diff-plus/minus/hunk classes
- i18n: diff_loading key in all 7 locales
- 12 tests: renderer, MEDIA inline, CSS classes, i18n parity
Closes#483
When context usage reaches 50% (yellow), a subtle hint button appears
in the context ring tooltip suggesting /compress. At 75%+ (red), the
hint intensifies with a warning style.
Clicking the button pre-fills /compress into the composer and focuses
it, so the user can add a focus topic or just hit send. No auto-fire
— the user stays in control.
- static/ui.js: conditional visibility + click handler in _syncCtxIndicator
- static/index.html: ctxCompressBtn element inside ctxTooltip
- static/style.css: muted button style, red variant for ctx-high
- static/i18n.js: ctx_compress_hint / ctx_compress_action in all 7 locales
Closes#524
The inline rename via double-click (nameEl.ondblclick) was not updating
the _expandedDirs and _dirCache when renaming a directory, unlike the
context-menu rename path (_inlineRenameFileItem) which already had this
logic. This could cause the tree view to show stale expand state after
a directory was renamed via double-click.
The file tree already supported file rename (double-click), file delete
(button), and create file/folder. This adds the missing directory
operations:
Backend:
- _handle_file_delete now supports directories when recursive=true
(uses shutil.rmtree instead of blocking with an error)
Frontend:
- Right-click context menu on all file/directory items with Rename
and Delete options (follows the project context menu pattern)
- Directory delete button (x) with confirmation dialog
- _inlineRenameFileItem() for renaming dirs via context menu prompt
- Expanded-dir cache is updated on rename/delete to stay consistent
- Context menu auto-positions within viewport bounds
i18n: delete_dir_confirm, rename_title, rename_prompt in all 7 locales
Closes#1104
- Drop btnCancel element and all JS show/hide call sites across
boot.js, messages.js, sessions.js, ui.js (superseded by single
primary action button)
- Remove .cancel-btn CSS rules including mobile media-query override
- Route updateSendBtn() title/aria-label through t() with English
fallbacks; add composer_send/queue/interrupt/steer/stop keys to all
7 locales (en, ru, es, de, zh, zh-Hant, ko)
- Branch disabled-state tooltip on reason: clarify lock, compression
running, or idle-empty, each with its own i18n key
- Update test_sprint10 / test_sprint36 to reflect single-button model:
assert btnSend present and id="btnCancel" absent; replace
test_hides_cancel_button with test_clears_composer_status
- Restore deepseek-chat-v3-0324 and deepseek-reasoner with '(legacy)' labels;
these are deprecated 2026-07-24 but still live until then
- Fix zai (Z.AI/GLM) default_base_url: use /api/paas/v4 instead of /api/coding/paas/v4;
the coding plan path is for the glmcode custom provider, not the general API
- Update test assertions to match
- Remove deepseek-chat-v3-0324 (DeepSeek V3) and deepseek-reasoner (R1)
from _MODEL_LIST, _PROVIDER_MODELS, static/index.html, and static/ui.js
- Keep only deepseek-v4-flash and deepseek-v4-pro
- These old model IDs are deprecated since 2026-07-24
Add deepseek-v4-flash and deepseek-v4-pro model entries to:
- api/config.py (_MODEL_LIST and _PROVIDER_MODELS)
- static/index.html (model dropdown)
- static/ui.js (static label map)
These are the latest DeepSeek models with 1M context window,
replacing the legacy deepseek-chat/deepseek-reasoner (deprecated 2026-07-24).
When multiple providers expose the same bare model ID (e.g. two custom
providers both listing gpt-5.4), the model picker cannot distinguish
them — both rows appear active and clicking the other provider's copy
is a no-op.
Fix:
- Add _deduplicate_model_ids() post-process in api/config.py that
detects duplicate bare model IDs across groups and prefixes
collisions with @provider_id: so each entry is globally unique
- Update norm() regex in static/ui.js to strip @provider: prefixes
for fuzzy matching, so existing sessions with bare model IDs still
restore correctly
- First occurrence stays bare for backward compatibility with sessions
that already store the bare model name
- Update test_model_resolver to be dedup-aware
Closes#1228
When context usage reaches 50% (yellow), a subtle hint button appears
in the context ring tooltip suggesting /compress. At 75%+ (red), the
hint intensifies with a warning style.
Clicking the button pre-fills /compress into the composer and focuses
it, so the user can add a focus topic or just hit send. No auto-fire
— the user stays in control.
- static/ui.js: conditional visibility + click handler in _syncCtxIndicator
- static/index.html: ctxCompressBtn element inside ctxTooltip
- static/style.css: muted button style, red variant for ctx-high
- static/i18n.js: ctx_compress_hint / ctx_compress_action in all 7 locales
Closes#524
Batch release v0.50.232 — 4 fixes.
## PRs included
| PR | Author | Fix |
|---|---|---|
| #1192 | @nesquena-hermes | Model chip fuzzy-match false positive (#1188) |
| #1193 | @nesquena-hermes | openai-codex not detected in model picker (#1189) |
| #1196 | @nesquena-hermes | Workspace files blank after second empty-session reload |
| #1197 | @bergeouss | Session timestamps wrong with server/client clock drift (#1144) |
All four PRs independently reviewed and approved by @nesquena.
## Integration fixes applied
**#1193:** Updated misleading comment — `OPENAI_API_KEY` does NOT authenticate the default Codex OAuth endpoint (that uses `chatgpt.com/backend-api/codex` and requires a separate OAuth flow). The comment now accurately states the known limitation. Also replaced a fragile 400-char source-scan test with an isolation-safe unit test. Note: OAuth-authenticated users already get detected via `hermes_cli.auth` — this fix only addresses the env-var fallback path.
## Test results
**2764 passed, 2 skipped** (macOS-only workspace tests). Browser QA: **21/21**. `/api/sessions` confirmed returning `server_time` and `server_tz` fields.
Batch release v0.50.231 — 3 fixes.
## PRs included
| PR | Author | Fix |
|---|---|---|
| #1186 | @nesquena (Claude Code) | macOS `/etc` symlink bypass in workspace blocked-roots |
| #1187 | @nesquena-hermes | Workspace panel stuck closed after empty-session reload |
| #1190 | @bergeouss | Fenced code content leaking into markdown passes (#1154) |
All three PRs were independently reviewed and approved by @nesquena.
## Test results
**2729 passed, 2 skipped** (2 macOS-only tests correctly skipped on Linux). Browser QA: **21/21**.
## Key fix notes
**#1186:** `_workspace_blocked_roots()` now returns both literal and `Path.resolve()` forms of each blocked root. macOS symlinks (`/etc → /private/etc`) previously let a resolved candidate slip past the literal check. New `_is_blocked_system_path()` helper with `/var/folders` and `/var/tmp` carve-outs for pytest temp dirs.
**#1187:** Regression from #1182 — `syncWorkspacePanelState()` force-closed on any no-session state. Now only closes in `'preview'` mode. Both boot paths restore localStorage panel pref before sync.
**#1190:** Fenced code blocks are now stashed as `\x00P<n>\x00` tokens through ALL markdown passes (list/heading/table regexes), restored at the very end. Previously, diff hunks and markdown headings inside code blocks triggered those regexes, injecting `<ul>/<li>/<h>` tags that broke `</pre>` closure.
Merged as v0.50.226.
Integration branch absorbed @aronprins's original PR #1141 with one reviewer fix from @nesquena (`1d11646`: queue hide tooltip updated to reference the queue pill, not the removed titlebar badge).
**Full gate results:**
- 2595 tests passing ✅
- Browser QA 21/21 (desktop 1440×900 + mobile iPhone 14) ✅
- Independent review: APPROVED by @nesquena ✅
Thank you @aronprins for the clean PR — the titlebar is properly restored.
* feat: attention state for broken cron jobs + Korean i18n (#1133, @franksong2702)
* fix: pytest state isolation for direct session saves (#1136, @franksong2702)
* fix(#1095): image thumbnails in composer + lightbox in chat (#1135)
* fix(css): restore cron attention + detail-alert rules overwritten by style.css merge (absorb)
* docs: v0.50.225 release notes and version bump
---------
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
* fix(#604): model picker shows all configured providers
Two fixes to ensure the model picker surface every provider a user has
configured:
1. Added env var detection for XAI_API_KEY (→ x-ai) and MISTRAL_API_KEY
(→ mistralai). Previously these providers were only detectable via
hermes auth or credential pool, not via environment variables.
2. Added config.yaml providers section scanning. Users who configure
providers in config.yaml (e.g. providers.anthropic.api_key) without
setting the corresponding env var will now see those providers in the
model picker. Only providers with known model catalogs are added.
- Added 12 regression tests
* fix(#1112): allow Google Fonts in CSP style-src and font-src
Mermaid themes inject @import for fonts.googleapis.com at render time.
CSP style-src blocked these requests, causing console violations.
- Add https://fonts.googleapis.com to style-src (CSS stylesheets)
- Add https://fonts.gstatic.com to font-src (WOFF2/WOFF font files)
- Add 3 regression tests + verify existing CSP tests still pass
* fix(#1118): retry api() calls on network errors after long idle
After a long idle period, the browser's TCP keep-alive connection to the
server can become stale. The next fetch() throws a TypeError (network
failure), causing 'Failed to load session' instead of transparently
reconnecting.
- Added retry loop in api() (workspace.js): up to 3 attempts
- Only retries on TypeError (network failures), NOT on HTTP errors (4xx/5xx)
- 401 redirects still fire immediately
- Added 6 regression tests
* feat(#1116): composer placeholder reflects active profile name
When a named profile is active (not 'default'), the composer placeholder
and title bar show the profile name (capitalised) instead of the global
bot_name. Falls back to bot_name/'Hermes' for the default profile.
- boot.js: applyBotName() checks S.activeProfile before _botName
- panels.js: switchToProfile() calls applyBotName() after switch
- Added 5 regression tests
* feat(#1097): drag and drop workspace files into chat composer
Files and folders in the workspace file tree are now draggable.
Dropping them into the composer inserts @path reference at cursor
position. OS file drag-and-drop (attach files) still works.
- ui.js: _renderTreeItems sets draggable + dragstart with ws-path
- panels.js: drop handler checks for application/ws-path first,
inserts @path with smart spacing and cursor positioning
- Added 9 regression tests
* fix(#1096): copy buttons work — add clipboard-write Permissions-Policy
Copy buttons on messages and code blocks were silently failing because
the Permissions-Policy header did not include clipboard-write=(self).
Firefox blocks navigator.clipboard.writeText() without explicit permission.
- api/helpers.py: add clipboard-write=(self) to Permissions-Policy
- ui.js: _copyText now catches clipboard API errors and falls back
to execCommand('copy'). _fallbackCopy extracted as separate function
with proper focus() call and visible-but-hidden positioning (not -9999px)
- Added 8 regression tests
* chore: CHANGELOG for v0.50.223
---------
Co-authored-by: bergeouss <bergeouss@users.noreply.github.com>
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
* fix(#1096): copy buttons fall back to execCommand on HTTP contexts
- Add _copyText() helper: tries navigator.clipboard first, falls back to
document.execCommand('copy') with hidden textarea when not in secure context
- Update copyMsg() and addCopyButtons() to use helper instead of direct
navigator.clipboard.writeText()
- Code block copy button now has .catch() handler (was silently failing)
- Error messages use t('copy_failed') for i18n instead of hardcoded string
- Add copy_failed key to all 6 locale blocks (en, ru, es, de, zh, zh-Hant)
- Add 10 regression tests
* fix(#1095): render pasted/dragged images as inline preview instead of paperclip badge
- User message attachments with image extensions now render as <img> via
api/media endpoint, with click-to-fullscreen support
- Non-image attachments still show paperclip + filename badge
- Extracts filename from full path for display
- Add 5 regression tests
* fix: hoist _IMAGE_EXTS to module scope, add avif (absorb fix)
* fix: improve mobile touch responsiveness for session list items
iPad Safari has known issues with the click/dblclick pattern on touch:
- :hover-triggered padding-right layout shift causes the first tap click
to target the wrong element (actions button that just appeared)
- No touch-action:manipulation means iOS still delays taps for
double-tap zoom detection
- The old onclick+ondblclick pattern is designed for mouse, not touch
Changes:
- CSS: Remove :hover from padding-right rule to prevent layout shift
- CSS: Add touch-action:manipulation and -webkit-tap-highlight-color
to .session-item for immediate tap response
- JS: Replace onclick/ondblclick with onpointerup + manual 350ms
double-tap detection — works consistently on mouse and touch
* fix(#1106): iterate custom_providers[].models dict keys for dropdown population
- After reading singular 'model' field, also iterate 'models' dict keys
- Deduplicate: model field value not repeated if also in models dict
- Skip non-string keys gracefully
- Works for both named and unnamed custom_providers entries
- Add 7 regression tests
* fix(#1105): allow custom_providers hostnames through SSRF check
- Build trusted hostname set from custom_providers[].base_url in config.yaml
- These are user-explicitly configured endpoints — not SSRF risks
- Hardcoded allowlist (ollama, localhost, 127.0.0.1, lmstudio) still active
- Unknown private IPs still blocked
- Add 7 tests (5 source analysis + 2 functional with mocked socket)
* fix(tests): update hover padding assertions for #1110 touch fix (absorb)
* fix(css): restore hover padding via @media (hover:hover) for mouse devices (absorb)
* fix: filter right/middle-click from pointerup handler (absorb)
* docs: v0.50.221 release notes and version bump
---------
Co-authored-by: bergeouss <bergeouss@users.noreply.github.com>
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Co-authored-by: sheng <378978764@qq.com>
* fix(css): add overflow-wrap:anywhere to chat bubbles — prevents long URL overflow (#1080)
* fix(projects): rename now works via dblclick timer guard + right-click color picker (#1078)
* fix(renderer): block-level constructs inside blockquotes now render
Fenced code blocks, headings, horizontal rules, and ordered lists inside
blockquotes now render correctly. Six related bugs documented in
blockquote-rendering-bugs.md were collapsed into one architectural fix
in renderMd().
Bugs fixed (all 6):
1. Fenced code blocks inside blockquotes -- > prefixes leaked into the
<pre> body and the blockquote got fragmented around the rendered
code, sometimes leaving raw <pre>/<div class="pre-header"> as
visible text.
2. Blank > continuation lines fragmented multi-paragraph blockquotes
into separate <blockquote> elements with literal > between them.
3. ## headings inside blockquotes rendered as literal "##" text.
4. Numbered lists inside blockquotes rendered as plain prose.
5. Complex blockquote (mixed headings + code + list + inline code)
collapsed into a monospace blob with raw markdown syntax leaking
everywhere.
6. Horizontal rules (---) inside blockquotes rendered as literal text.
Root cause:
The per-line passes for fenced code, headings, hr, ordered lists all ran
BEFORE the blockquote handler and could not match lines that started
with >, so by the time blockquote stripping ran those constructs had
already been mishandled.
Fix:
A new blockquote pre-pass at the top of renderMd():
- Walks lines fence-aware so > -prefixed lines inside non-blockquote
code fences (e.g. shell prompts in bash code blocks) are not
miscaptured as a blockquote.
- Groups consecutive > -prefixed lines, strips the > prefix, and
recursively calls renderMd() on the stripped content. The recursive
call handles all block-level constructs (fenced code, headings, hr,
ordered/unordered lists, nested blockquotes) using the same pipeline.
- Wraps the rendered HTML in <blockquote> and stashes it with a \x00Q
token. Restored at the very end of renderMd() so no later pass can
mangle the inner HTML.
The old _applyBlockquotes regex-replace is removed entirely along with
its limited inline branches for nested blockquotes and unordered lists.
Behaviour change:
Blockquotes now produce CommonMark-compliant <p> wrapping for text
content (was: bare text directly inside <blockquote>). The visual
output is the same in browsers but the HTML structure is now standard.
Tests:
- 14 new behavioural tests in tests/test_renderer_js_behaviour.py
drive the actual renderMd() via node and lock all 6 bug fixes.
- .local-review/test_blockquote_bugs.js -- node harness covering the
same scenarios, runnable manually for fast iteration.
- 2407/2408 tests pass (1 pre-existing macOS-only failure deselected).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(renderer): entity decode before blockquote pre-pass + CSS margin fix
- Move the >/</& entity-decode to run at the very top of
renderMd(), before the blockquote pre-pass. Previously decode() ran
at line 756 (after the pre-pass at line 697), so LLM output containing
>-encoded blockquotes was never matched by the pre-pass.
- Add .msg-body blockquote p{margin:0} and .preview-md blockquote p{margin:0}
so the new CommonMark-compliant <p> wrapping inside blockquotes doesn't
add extra vertical spacing. Prior shape (bare text) had no default p-margins.
- Add Node-driven tests: TestBlockquoteEntityEncodedInput covers > prefix
and >-encoded fenced code inside blockquotes.
- Add struct test: TestBlockquotePrePassOrdering::test_entity_decode_runs_before_blockquote_pre_pass
locks decode < _bq_stash ordering in ui.js.
Fixes found during Opus independent review of #1083.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs: v0.50.218 release notes, test count 2458, roadmap update
---------
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Co-authored-by: Nathan Esquenazi <nesquena@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(workspace): add .html/.htm to MIME_MAP so HTML preview renders correctly
MIME_MAP was missing entries for .html and .htm. The server fell back to
Content-Type: application/octet-stream, which browsers refuse to render as
HTML in an iframe — causing a blank white preview.
The rest of the pipeline was already correct: the iframe exists in
static/index.html, openFile() in static/workspace.js routes .html to
showPreview('html'), and _handle_file_raw() in api/routes.py sets the
correct CSP sandbox header when ?inline=1 is present. The only missing
piece was the MIME type.
* test(workspace): lock in MIME_MAP entry for .html/.htm
PR #1070 added .html/.htm → text/html to MIME_MAP in api/config.py
to fix the blank workspace HTML preview iframe. Without a direct
assertion on the MIME_MAP entries, the fix could silently regress
(the existing test_779_html_preview.py tests cover the iframe wiring,
the inline=1 query handling, and the CSP sandbox header — but none of
them touch MIME_MAP itself).
Add a single regression test that asserts MIME_MAP['.html'] and
MIME_MAP['.htm'] are both 'text/html' so any future removal of those
entries fails CI immediately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(composer): raise .approval-card.visible z-index above .queue-card
.queue-card has z-index:2. .approval-card.visible had no z-index, so the
queue flyout would render on top of the approval card when both were visible
simultaneously — obscuring the Allow/Deny buttons.
Fix: add z-index:3 to .approval-card.visible so approvals always render
above the queue flyout. Approval is a blocking, security-relevant interaction
and must never be obscured by passive UI elements.
* test(composer): pin approval-card z-index > queue-card invariant
PR #1071 raises .approval-card.visible to z-index:3 so the security-
relevant Allow / Deny buttons stay clickable when the queue flyout is
also open. Without a regression test, a future CSS edit could silently
drop the z-index back below queue-card (z-index:2) and reintroduce the
bug — there is no automated UI test covering this stacking interaction.
Add a focused regex check that pins the invariant:
.approval-card.visible z-index must be strictly greater than
.queue-card z-index.
Modeled on the existing CSS-regex regression style in
tests/test_mobile_layout.py (test_profile_dropdown_not_clipped_by_overflow).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: intercept /steer /interrupt /queue before busy-mode routing in send()
Root cause: slash commands entered while the agent is busy never reached
the command dispatcher. send() enters the busy block and returns early at
line ~50, so the slash-command intercept (~line 56) is never reached.
The text was queued as a plain message. When it drained after the turn
ended, cmdSteer / cmdInterrupt ran on an idle session, saw no active stream,
and showed "No active task to stop."
Fix: at the top of the busy block, before checking busyMode, check if the
text starts with / and is one of the three control commands. If so, dispatch
the handler immediately and return. This lets the user type /steer, /interrupt,
or /queue at any time — including while the agent is mid-stream — and have
them execute against the live session.
Two new regression tests added:
- test_slash_commands_intercepted_before_busymode_routing: verifies the
intercept appears before the busyMode routing in the busy block
- test_steer_intercept_calls_handler_directly: verifies the intercept calls
_bc.fn(_pc.args) and returns, not queues
* test(busy-intercept): pin sync input-clear before await in slash intercept
PR #1072's intercept clears the msg input before awaiting the handler.
Order matters: if the await happens first (or if the clear is moved
inside the handler), the input still shows '/steer foo' for the duration
of the await. A reflexive second Enter press during that window — common
while waiting for the toast — re-runs send(): either re-fires the
handler (double-steer) or, if the turn just ended, falls through to the
non-busy slash dispatcher and drops a confusing "No active task to stop."
Add test_steer_intercept_clears_input_before_await pinning the order so
this UX invariant cannot silently regress.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: update steer i18n and settings copy — steer no longer interrupts
With the real /steer implementation (agent.steer() via /api/chat/steer),
steer injects a correction mid-turn WITHOUT interrupting the current stream.
The previous copy said "falls back to interrupt", "Steer (interrupt + send)",
etc. — accurate only for the old placeholder, not the real implementation.
Changes across all 6 locales (en/ru/es/de/zh/zh-Hant):
cmd_steer: "falls back to interrupt" removed
settings_busy_input_mode_steer: "interrupt + send" → "mid-turn correction"
cmd_steer_fallback: "interrupted" → "queued for next turn"
busy_steer_fallback: "interrupted instead" → "queued for next turn"
settings_desc_busy_input_mode: "currently falls back to interrupt" removed
Also:
static/index.html: inline fallback text updated to match
static/commands.js: internal comment clarified (fallback = queue+cancel,
not "interrupt mode" which implies the primary action)
* fix(renderer): group consecutive blockquote lines into single element
Root cause: the old rule `s.replace(/^> (.+)$/gm, ...)` had three bugs:
1. `.+` required at least one character — bare `>` lines (blank
continuation lines) did not match and passed through as literal `>`
2. Each matching line became its own `<blockquote>` element — a 10-line
blockquote produced 10 stacked `<blockquote>` tags with no grouping
3. When a fenced code block sat inside a blockquote, the fence-stash
pass consumed the code content and left orphaned `>` lines that the
old `.+` pattern could not match
Fix: replace the single-line regex with a group-based approach that matches
one or more consecutive `>` lines as a single block, strips the `>` prefix
from each line, passes each non-empty line through inlineMd(), turns blank
`>` lines into `<br>`, and wraps the entire group in one `<blockquote>`.
14 regression tests added covering:
- Single-line blockquotes (regression)
- Multi-line grouping (2 and 10 lines)
- Two separate blockquotes staying separate
- Bare `>` and `>text` (no space) edge cases
- Blank continuation lines → <br>
- Bold / italic / inline-code inside blockquotes
- Blockquote followed by normal paragraph
* fix(renderer): drop empty trailing line from blockquote match
The new group-based blockquote rule introduced in this PR captures the
trailing newline in its (?:\n|$) clause. After block.split('\n') that
trailing newline produces an empty final element. The original filter
only dropped lone bare '>' artifacts on the last line, so the empty
final element survived, and the .map(blank → '<br>') step turned it
into a phantom <br> immediately before </blockquote>.
Visible symptom: any blockquote whose source ends with \n (the common
case — a quote followed by another paragraph or end-of-message) renders
with an extra blank line at the bottom of the quote.
Reproducer:
'> Hello\n\nThe rest of the message.'
→ '<blockquote>Hello\n<br></blockquote>\nThe rest of the message.'
^^^ phantom <br>
Fix: replace the single-line filter with a while-loop that pops trailing
lines while they are either empty OR a bare '>'. This matches the
intent the Python test mirror in tests/test_blockquote_rendering.py
already had (the mirror was correct; the JS was not — that's why
the original tests passed despite the bug).
Also add four new regression tests in TestNoPhantomTrailingBr that pin
the no-trailing-<br> invariant for the common shapes:
- input ending with \n
- quote followed by paragraph (the real-world case)
- multi-line quote ending with \n
- quote with blank continuation + trailing \n (internal <br> stays,
trailing <br> does not)
Verified end-to-end with node against the actual JS regex.
244 renderer-adjacent tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(renderer): comprehensive markdown fixes — strikethrough, task lists, CRLF, nested blockquotes
Five additional fixes on top of the blockquote grouping from the initial commit:
1. CRLF normalisation: strip \r\n → \n at start of renderMd so Windows
line endings do not produce stray \r characters in rendered output
2. Strikethrough: ~~text~~ → <del>text</del> in both inlineMd() (for use
inside blockquotes/lists) and the outer pass (for plain paragraphs).
Added <del> to SAFE_TAGS and SAFE_INLINE so it is not HTML-escaped.
3. Task lists: - [x] / - [ ] items in unordered lists render as ✅/☐
via task-done/task-todo span wrappers. Checks [X] (uppercase) too.
4. Nested blockquotes: >> / >>> etc. now recurse so each level gets its
own <blockquote> element rather than passing through as literal >.
Implemented by extracting the blockquote rule into _applyBlockquotes()
which calls itself recursively on the stripped inner content.
5. Lists inside blockquotes: > - item now renders <ul><li> inside the
blockquote instead of a literal "- item" string. Task list items work
inside blockquotes too (> - [x] done → ✅ inside <blockquote><ul>).
Also fixed test_issue342.py search window (5000→10000 chars) — the CRLF
strip at the top of renderMd pushed the autolink regex past the old limit.
68 new tests in test_renderer_comprehensive.py + test_blockquote_rendering.py
covering all constructs, edge cases, and combinations.
* fix(renderer): restore space in blockquote prefix-strip regex
Commit 04e7b53 changed the blockquote prefix-strip regex from
/^>[ \t]?/ (consume "> ", "\t>", or just ">")
to
/^>[\t]?/ (only consume "\t>" or just ">")
The space character was dropped from the character class. Since
practically every blockquote an LLM produces is "> " (greater-than
followed by a space), this leaves a leading space artifact on every
stripped blockquote line. Worse, the leading space breaks the
list-detection regex `^(?: )?[-*+] ` inside the new `_applyBlockquotes`
helper — that regex requires either zero or two leading spaces, never
one — so the new "list inside blockquote" feature never fired for
the canonical input shape `> - item`.
Reproducer (against the actual ui.js via node, before the fix):
> Hello world → <blockquote> Hello world</blockquote>
^ phantom leading space
> Steps: → <blockquote>Steps:
> - one - one
> - two - two</blockquote>
^ literal text, NOT a <ul>; lists-in-quote feature broken
> - [x] done → blockquote with literal "[x] done", no checkbox span
Tests passed despite the bug because tests/test_blockquote_rendering.py
and tests/test_renderer_comprehensive.py validate against a Python
mirror (`_apply_blockquotes`) whose strip regex is `^>[ \t]?` — i.e.
the mirror is correct, the JS is not, and the static-mirror tests
can't catch the divergence. Same shape of bug as commit 94d63d0
(phantom <br> in trailing line) where the mirror was right and the JS
was wrong.
Fix: restore the space character in the strip regex's character class.
Add tests/test_renderer_js_behaviour.py — 11 tests that drive the
ACTUAL renderMd via node and assert on rendered output for the most
common LLM shapes (single-line quote, multi-line quote, list inside
quote, task list inside quote, nested >>>, strikethrough inside and
outside quote, top-level task list, quote followed by heading,
multi-paragraph quote with list, CRLF normalisation).
Verified: the buggy regex makes 6 of those 11 tests fail; the corrected
regex makes all 11 pass.
Suite: 2354 passed, 0 new failures.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Collapse agent session compression chains
* Restore upstream changelog entries
* fix(agent_sessions): bubble active compression chains to top by tip last_activity
The original PR merge kept the chain head's id/title/started_at and overrode
id/model/message_count/ended_at/end_reason from the tip — but did NOT override
last_activity. Since the projected list is sorted by last_activity DESC and
the WebUI sidebar surfaces updated_at = last_activity, an actively-used
compression chain whose tip is being edited NOW would sort by the ROOT's
old last_activity and fall below recently touched standalone sessions.
Reproducer (with the harness against actual code, before the fix):
- root: started 30 days ago, last msg 30 days ago
- tip: started 28 days ago (parent_session_id=root), last msg 5 seconds ago
- standalone: last msg 2 days ago
Sidebar order with original PR:
[0] standalone (48h ago)
[1] active_tip (last_activity=root's 720h ago) ← wrong
Sidebar order after fix:
[0] active_tip (last_activity=tip's 0h ago) ← correct
[1] standalone (48h ago)
This matches Hermes Agent's own list_sessions_rich projection at
hermes_state.py:903-909, which overrides "last_active" from the tip
exactly so that the agent CLI's session list orders the same way.
Add ``last_activity`` to the merge-from-tip key list, update the existing
test_compression_chain_collapses_to_latest_tip_in_sidebar assertion to
expect tip-derived updated_at, and add
test_compression_chain_bubbles_to_top_by_tip_activity locking in the
bubble-to-top invariant — without this regression test the previous
behaviour passed CI because no test exercised the sort order against a
mixed set of chains and standalone sessions.
The chain head's started_at (created_at) and title remain preserved, so
users can still find the conversation by its original date and name.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: v0.50.216 release notes and version bump
Compression chains, renderer fixes, HTML preview, approval z-index, /steer fix.
* chore: gitignore local-only review harness directory
Adds .local-review/ to .gitignore so renderer drivers, sample inputs,
fixture builders, and other reviewer scratch files do not accidentally
get committed. Nothing under that path is ever shared in the repo;
keeping the entry tracked makes the boundary explicit for any future
contributor who creates the directory locally.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Keep reasoning chip visible for None effort
* test(reasoning): pin chip render output via node, not just source regex
The PR's static checks in test_reasoning_chip_btw_fixes.py validate the
shape of _applyReasoningChip (no display='none' literal, the right
classList.toggle call exists, the right label literals are in the
function body) but pass even if the runtime detail is wrong — for
example if `inactive` were inverted, _normalizeReasoningEffort
mishandled whitespace, or _formatReasoningEffortLabel returned the
wrong literal for an unknown input.
Add tests/test_reasoning_chip_js_behaviour.py — 11 tests that drive
the actual _applyReasoningChip() via node and assert on the rendered
DOM state for each effort value:
TestChipAlwaysVisible
- empty / null -> "Default" label, inactive=true
- "none" -> "None" label, inactive=true
- "low"/"high" -> verbatim label, inactive=false
TestNormalizationEdgeCases
- "NONE" -> normalises to "None"
- " none " -> trims and normalises
- unknown junk -> falls through visible, never hidden
TestTitleAttributeAccessibility
- title attribute carries the human-readable label for tooltip /
screen-reader use
Sanity-checked against master's pre-fix ui.js: 11/11 fail (bug caught).
Against this PR's ui.js: 11/11 pass.
This pattern (drive the actual JS via node) caught two regex-only
regressions in PR #1073 where the Python mirror was correct while the
JS was broken. Same protection added here so the chip-visibility
contract can't silently break in a future refactor.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: add #1074 to v0.50.216 changelog, bump test count to 2428
* fix(i18n): restore broken Unicode in Russian and Spanish steer strings
Commit 56c7a14 (fix: update steer i18n and settings copy) accidentally
stripped the `\u` prefix from Unicode escape sequences in two locales,
producing garbled literal hex strings visible to users:
Spanish (es):
- cmd_steer: correcci00f3n → corrección
- cmd_steer_fallback: 2014 en cola → — en cola
- busy_steer_fallback: 2014 en cola → — en cola
- settings_desc_busy_input_mode: qu00e9, est00e1, correcci00f3n → qué, está, corrección
- settings_busy_input_mode_steer: correcci00f3n → corrección
Russian (ru):
- settings_desc_busy_input_mode: the entire Cyrillic string was
replaced with raw 4-hex-char code-points without the \u prefix
(041e043f... instead of actual Cyrillic). Decoded:
"Определяет поведение при отправке сообщения во время работы
агента. Очередь ждёт; Прерывание отменяет и начинает заново;
Steer внедряет коррекцию без прерывания."
Fix: write the correct characters directly (UTF-8 is the file encoding
so embedding them literally is cleaner than \u escapes for long text).
All other locales (en, de, zh, zh-Hant) were not affected — confirmed
by grepping for bare hex run-ons in the updated file.
Verified: node --check static/i18n.js passes; full pytest suite green
(2365 passed, 47 skipped).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: remove duplicate compression chain entry from [Unreleased]
---------
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Co-authored-by: Nathan Esquenazi <nesquena@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Frank Song <franksong2702@gmail.com>
nesquena-hermes