(defvar llm-tools--hl-bigrams (list "aa" "ab" "ac" "ad" "ae" "af" "ag" "ah" "ai" "aj" "ak" "al" "am" "an" "ao" "ap" "aq" "ar" "as" "at" "au" "av" "aw" "ax" "ay" "az" "ba" "bb" "bc" "bd" "be" "bf" "bg" "bh" "bi" "bj" "bk" "bl" "bm" "bn" "bo" "bp" "br" "bs" "bt" "bu" "bv" "bw" "bx" "by" "bz" "ca" "cb" "cc" "cd" "ce" "cf" "cg" "ch" "ci" "cj" "ck" "cl" "cm" "cn" "co" "cp" "cq" "cr" "cs" "ct" "cu" "cv" "cw" "cx" "cy" "cz" "da" "db" "dc" "dd" "de" "df" "dg" "dh" "di" "dj" "dk" "dl" "dm" "dn" "do" "dp" "dq" "dr" "ds" "dt" "du" "dv" "dw" "dx" "dy" "dz" "ea" "eb" "ec" "ed" "ee" "ef" "eg" "eh" "ei" "ej" "ek" "el" "em" "en" "eo" "ep" "eq" "er" "es" "et" "eu" "ev" "ew" "ex" "ey" "ez" "fa" "fb" "fc" "fd" "fe" "ff" "fg" "fh" "fi" "fj" "fk" "fl" "fm" "fn" "fo" "fp" "fq" "fr" "fs" "ft" "fu" "fv" "fw" "fx" "fy" "fz" "ga" "gb" "gc" "gd" "ge" "gf" "gg" "gh" "gi" "gj" "gl" "gm" "gn" "go" "gp" "gr" "gs" "gt" "gu" "gv" "gw" "gx" "gy" "gz" "ha" "hb" "hc" "hd" "he" "hf" "hg" "hh" "hi" "hj" "hk" "hl" "hm" "hn" "ho" "hp" "hq" "hr" "hs" "ht" "hu" "hv" "hw" "hx" "hy" "hz" "ia" "ib" "ic" "id" "ie" "if" "ig" "ih" "ii" "ij" "ik" "il" "im" "in" "io" "ip" "iq" "ir" "is" "it" "iu" "iv" "iw" "ix" "iy" "iz" "ja" "jb" "jc" "jd" "je" "jf" "jg" "jh" "ji" "jj" "jk" "jl" "jm" "jn" "jo" "jp" "jq" "jr" "js" "jt" "ju" "jw" "jx" "jy" "ka" "kb" "kc" "kd" "ke" "kf" "kg" "kh" "ki" "kj" "kk" "kl" "km" "kn" "ko" "kp" "kr" "ks" "kt" "ku" "kv" "kw" "kx" "ky" "la" "lb" "lc" "ld" "le" "lf" "lg" "lh" "li" "lj" "lk" "ll" "lm" "ln" "lo" "lp" "lr" "ls" "lt" "lu" "lv" "lw" "lx" "ly" "lz" "ma" "mb" "mc" "md" "me" "mf" "mg" "mh" "mi" "mj" "mk" "ml" "mm" "mn" "mo" "mp" "mq" "mr" "ms" "mt" "mu" "mv" "mw" "mx" "my" "mz" "na" "nb" "nc" "nd" "ne" "nf" "ng" "nh" "ni" "nj" "nk" "nl" "nm" "nn" "no" "np" "nr" "ns" "nt" "nu" "nv" "nw" "nx" "ny" "nz" "oa" "ob" "oc" "od" "oe" "of" "og" "oh" "oi" "oj" "ok" "ol" "om" "on" "oo" "op" "oq" "or" "os" "ot" "ou" "ov" "ow" "ox" "oy" "oz" "pa" "pb" "pc" "pd" "pe" "pf" "pg" "ph" "pi" "pj" "pk" "pl" "pm" "pn" "po" "pp" "pq" "pr" "ps" "pt" "pu" "pv" "pw" "px" "py" "pz" "qa" "qb" "qc" "qd" "qe" "qh" "qi" "ql" "qm" "qn" "qo" "qp" "qq" "qr" "qs" "qt" "qu" "qw" "qx" "qy" "ra" "rb" "rc" "rd" "re" "rf" "rg" "rh" "ri" "rk" "rl" "rm" "rn" "ro" "rp" "rq" "rr" "rs" "rt" "ru" "rv" "rw" "rx" "ry" "rz" "sa" "sb" "sc" "sd" "se" "sf" "sg" "sh" "si" "sj" "sk" "sl" "sm" "sn" "so" "sp" "sq" "sr" "ss" "st" "su" "sv" "sw" "sx" "sy" "sz" "ta" "tb" "tc" "td" "te" "tf" "tg" "th" "ti" "tj" "tk" "tl" "tm" "tn" "to" "tp" "tr" "ts" "tt" "tu" "tv" "tw" "tx" "ty" "tz" "ua" "ub" "uc" "ud" "ue" "uf" "ug" "uh" "ui" "uj" "uk" "ul" "um" "un" "uo" "up" "uq" "ur" "us" "ut" "uu" "uv" "uw" "ux" "uy" "uz" "va" "vb" "vc" "vd" "ve" "vf" "vg" "vh" "vi" "vj" "vk" "vl" "vm" "vn" "vo" "vp" "vq" "vr" "vs" "vt" "vu" "vv" "vw" "vx" "vy" "vz" "wa" "wb" "wc" "wd" "we" "wf" "wg" "wh" "wi" "wj" "wk" "wl" "wm" "wn" "wo" "wp" "wr" "ws" "wt" "wu" "wv" "ww" "wx" "wy" "xa" "xb" "xc" "xd" "xe" "xf" "xh" "xi" "xl" "xm" "xn" "xo" "xp" "xr" "xs" "xt" "xu" "xx" "xy" "xz" "ya" "yb" "yc" "yd" "ye" "yf" "yg" "yh" "yi" "yj" "yk" "yl" "ym" "yn" "yo" "yp" "yr" "ys" "yt" "yu" "yv" "yw" "yx" "yy" "yz" "za" "zb" "zc" "zd" "ze" "zf" "zg" "zh" "zi" "zk" "zl" "zm" "zn" "zo" "zp" "zr" "zs" "zt" "zu" "zw" "zx" "zy" "zz") "List of bigrams for use with hashline reads/writes. Each of the bigrams resolve to a single token in standard LLM vocabulary, unlike a hash's hex digits. Taken from https://github.com/can1357/oh-my-pi. Precisely: https://raw.githubusercontent.com/can1357/oh-my-pi/85003ca/packages/coding-agent/src/hashline/bigrams.json") (defun llm-tools--hl-hash (line) ;; logand is to force unsigned number (elt llm-tools--hl-bigrams (% (logand (sxhash line) #xffffffff) 647))) (defun llm-tools--hl-file-lines (file &optional beg end) "Return FILE contents as a list of strings. With optional BEG and END (inclusive, 1-based), return the lines between that range." (with-temp-buffer (insert-file-contents-literally file) (let ((lines (string-lines (buffer-string)))) (if beg (cl-subseq lines (1- beg) end) lines)))) (defun llm-tools--hl-format-lines (lines &optional start include-content?) "Format LINES in hashline format. START is 1-based (default 1). If INCLUDE-CONTENT is non-nil, append `|LINE' after each hash." (string-join (cl-mapcar (lambda (line i) (if include-content? (format "%d%2s|%s" i (llm-tools--hl-hash line) line) (format "%d%2s" i (llm-tools--hl-hash line)))) lines (number-sequence (or start 1) (+ (or start 1) (1- (length lines))))) "\n")) (defun llm-tools--hl-file-read (file) "Return FILE contents in hashline format." (llm-tools--hl-format-lines (llm-tools--hl-file-lines file) nil t)) (defun llm-tools--hl-file-read-range (file beg end) "Return FILE contents in hashline format from lines BEG to END." (llm-tools--hl-format-lines (llm-tools--hl-file-lines file beg end) beg t)) (defun llm-tools--hl-file-read-hashes (file) "Return FILE contents as a list of hashline strings without line content. Each element is a line number and two-character hash, like `1vx'." (string-lines (llm-tools--hl-format-lines (llm-tools--hl-file-lines file)))) (defun llm-tools--hl-file-line-hash (file n) "Return the hash of the Nth line in FILE." (let ((lines (llm-tools--hl-file-lines file))) (llm-tools--hl-hash (elt lines (1- n))))) ;;;; Diff Parsing (defun llm-tools--split-patch-sections (patch) "Return a list of (FILENAME . REST) cons cells from PATCH. Each section starts with '@@ PATH' on the first line; the car is PATH and the cdr is the remainder of that section." (let ((pos (string-match "^@@" patch))) (when pos (let (sections (start pos)) (while (string-match "\n@@" patch (1+ pos)) (let ((nl (match-beginning 0))) (push (substring patch start (1+ nl)) sections) (setq start (1+ nl))) (setq pos (match-end 0))) (push (substring patch start) sections) (mapcar (lambda (sec) (let ((end (string-match "\n" sec))) (cons (substring sec 3 end) (substring sec end)))) (nreverse sections)))))) (defun llm-tools--hl-get-anchors (patch) "Returns an alist of (FILENAME . ANCHORS) from PATCH. ANCHORS is a sorted, deduplicated list of all line anchors referenced by the operations in that file's sections. Each anchor is a string like \"5ff\" or a list of two strings from a range like (\"3gv\" \"6be\")." (let ((sections (split-patch-sections patch))) (delete-dups (mapcar (lambda (patch) (cons (car patch) (delete-dups (sort (flatten-list (mapcar (lambda (line) (if (length> line 0) (let ((op (char-to-string (elt line 0))) (anchor (substring line 2))) (pcase op ((or "+" "<") anchor) ((or "-" "=") (split-string anchor "\\.\\.")))))) (string-lines (cdr patch)))))))) sections)))) (defun llm-tools--hl-verify-anchors (patch) "Verify that all anchors in PATCH match the current file contents. Returns a list of booleans, one per file, indicating whether every anchor in that file's patch sections still matches the corresponding line in the on-disk file." (let ((patch-anchors (llm-tools--hl-get-anchors patch))) (mapcar (lambda (section) (let* ((file (car section)) (anchors (delete "EOF" (cdr section))) (hl (llm-tools--hl-file-read-hashes file))) ;; cl-subsetp uses eql by default which compares by identity and not content (cons file (cl-subsetp anchors hl :test #'equal)))) patch-anchors))) (defun llm-tools--hl-verify (patch) "Verify if the files in PATCH need to be re-read. Returns a string message that states which files need to be re-read. Empty string means no files need to be re-read." (string-join (delete-dups (remq nil (mapcar (lambda (elem) (unless (cdr elem) (format "%s had incorrect anchors. Use the 'read_file' tool to get correct anchors." (car elem)))) (llm-tools--hl-verify-anchors patch)))) "\n")) (defun llm-tools--hl-parse-section (section) "Parses operation and optional payload from SECTION." ) (defun llm-tools--hl-apply (patch) "TODO rewrite docstring. Applies a patch." ;; when performing each operation, I need to make sure that the line ;; numbers of subsequent operations in same file also get updated. (let ((sections (split-patch-sections patch))) (llm-tools--hl-parse sections))) (defun llm-tools--hl-edit (patch) "TODO write better docstring. First verifies if any files in PATCH needs to be re-read. Then, applies the changes in PATCH. If any files need to be re-read, the edit operation is cancelled for all files." (let ((msg (llm-tools--hl-verify patch))) (if (string= msg "") (progn (llm-tools--hl-apply patch) (format "Finished applying patch.")) (format "%s" msg)))) (let* ((patch "\ # Replace one line (the payload must re-emit the original indentation) @@ mod.ts = 1vx..1vx ~const TITLE = \"Mrs\"; # Replace a full multiline statement (widen to a self-contained boundary) @@ mod.ts = 3gv..6be ~ return [ ~ \"Mrs\", ~ name?.trim() || \"guest\", ~ ].join(\" \"); # Insert AFTER/BEFORE a line @@ mod.ts + 4ei ~ \"Dr\", < 5ff ~ \"Dr\", # Append to file @@ mod.ts + EOF ~export const done = true; # Delete a line @@ mod.ts - 5ff..5ff # Blank a line (replace with LF) @@ mod.ts = 5ff..5ff ")) (llm-tools--hl-apply patch)) (provide 'llm-tools-hl)